Baitaphish
Security intelligence
SearchLatest briefing
Source

arXiv Research

The consolidated arXiv research source identity; historical category collections remain available separately.

Source ID: arxiv_research

750 item(s)
← Back to all sources
Publisher
arXiv
Source family
academic_research
Publication state
PUBLIC_NOINDEX
Visit the canonical publisher page

Baitaphish provides this source identity and attribution. Publisher full text is not republished here.

Published 2026-10-27T04:00:00Z
DairySocialTwin: Auditing the video-to-graph evidence chain in cattle social networks
ff6384b1853b…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
Linear-Time Context Compression with State-Space Encoding
f7cb5ce58b30…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
SLICE-Mem: Salience-Gated Lightweight Information Curation for Efficient LLM Agent Memory
e89b4eb88d04…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
Veracity labels flip the emotional tone of language models but leave racial disparities intact
d4b7b154c9ac…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
LLM-as-a-Judge Version Shift: The Instrument Changed, Not the Standard
d2c6cd5fd398…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
TraceQuery: learning what to recompute from full-denoising trajectory in diffusion language models
d02eaa3a61de…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
Merge-Based Vocabulary Extension Stalls at the Pre-Tokenizer: An English-Preserving Repair for Nepali, Tested in Continued Pretraining
cb7a2e552f53…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
From Writing Advice to Manuscript Governance: A Constrained-Transformation Framework for Academic Revision
cb30305809c1…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
Conceptizer: Next-Token Prediction Is Not All You Need
c66d1e434e32…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
OpenHamoye: A Multi-Scale Open Geospatial Intelligence Framework for Decision Support Across Nigeria
c0050018ded7…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
False Belief Dissemination, Persistence and Mitigation in Multi-Agent Social Networks Through the Lens of the Mandela Effect
bf53ebef395d…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
Mine or Yours? Mind-Bridged Language Models Take Each Other's Memories as Their Own
bb7b85ef3cf5…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
Governing Artificial Intelligence as a Macro Socio-Technical Regime: The F-I-C-P Framework for Regime-Level AI Infrastructure and Governance
a984656555e0…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
Whispering Wisely: Smart Subset Selection for ASR Fine-Tuning
9f3981c72547…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
OpenESM: Energy-Steered Models Are Scalable Foundation Learners
9d9ffb91abe6…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
Knowledge-Guided LLM for Intent-Driven Service Orchestration in Integrated Terrestrial and Non-Terrestrial 6G Networks
99641a27c225…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
AdaptTok-Indic: Script-Aware Adaptive Tokenization for Indic Languages
8ba1a46286d6…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation
68b371c81042…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
Recursive Semantic Divergence for LLM Agent Consistency
595172227dd7…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
Can Language Models Learn While They Think? Testing Gradient Adaptation Across Architectures
5369c1778706…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
The Social World Model Evaluation Gap
4ed981cd106d…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
Lessons from Luck: Do LLM-Written Lessons Carry Chance into an Agent's Next Decision?
3d37ddcc5b23…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
New Lenses on Learning Design: Course Types and Indicators from Large-Scale Moodle Data
13f50a61f0ec…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
SUDO: From Scientific Publications to Global Scholarly Discourse
10d4f73fcc3f…
Source →arXiv PDF ↗Open →
Published 2026-10-27T04:00:00Z
Entity-Aware Evaluation of OCR Systems for Historical Document Transcription
029e33f99236…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
MisconceptDialogue: Evaluation Criteria Shape Measured Success in LLM Math Tutoring
f026d772111e…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Does LeWorldModel Preserve Local Action Geometry?
e6de16773cb0…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Towards Adversarially Robust Multigraph Neural Networks for Financial Crime Analysis
dff57f3c234e…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Mining the Design Space of Multi-Agent Workflows
dfe69342b91f…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Omni-UBench: Benchmarking Omni-Modal LLM-based Guardrails Across Safety, Utility, and Reliability
dfa4a3a2ba49…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Collaborative In-Context Learning for Indoor Radio Map Estimation
d6e433efd71a…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Distributional Alignment of LLMs and Its Generalization Properties
cd4aa7e18a61…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Rethinking Structured Generation: Can Graph-Based Reasoning Resolve Ambiguity?
aaf7aa5b3b5c…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Tradeoff-Aware Territory Design: A Multi-Objective Decision System for Enterprise Customer-to-Seller Allocation
9d3c203b9f2d…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Autoregressive Physics-Informed Neural Operator Surrogates and Joint 4-D Seismic-Production Bayesian History Matching
7fbe02447171…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
The Schema Coherence Inventory: Measuring Whether an Assigned Belief Organizes a Language Model's Cognition
75f8a0240f49…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Understanding Tool-Mediated Interaction Failures in Agentic GUI Software: An Empirical Study
5cdd1e546ad2…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Before the Ticket: Grounding HPC User Support in Documentation and Resolved Tickets with an Agentic LLM Assistant
5b57baadbd47…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Compact-Bench: Measuring What Context Compaction Costs Long-Horizon Coding Agents
556871a32b3a…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
An Agentic Approach with Evidence-Grounded Verification for Multimodal Emotion Reasoning in Conversation
510aaee8e2df…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
RubricCraft: Where Solutions Diverge, Criteria Emerge
510a818bdf47…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
From Target Selection to Condition Reuse: Auditing Residual Interventions in Tool-Use Models
4671976bb289…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Multi modal perceived conversation success prediction for spontaneous autistic and non-autistic dyadic interactions
3efdd03b424a…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
The Path to NDE 4.0: A Review of Algorithms, Techniques, and Strategies for Autonomous Inspection
3d8d2856c75d…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Validating the Comparison, Not Just the Scorer: Why Overall Accuracy Can Mislead in Interactive LLM Evaluation
3b8cc7e87e9b…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
What Open-Source Projects Tell Their Coding Agents: A Census of AGENTS.md and CLAUDE.md
2df4572b748b…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Reuse, Rewrite, or Reject: Evidence-Constrained Trace Reuse for Repeated Mobile GUI Control
2a088b707c4d…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
MBABench-2.0: Evaluating AI Agents on Constructing Financial Spreadsheets Beyond Simple Verifiability
0608849d40be…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Knowledge Graphs Quality Assessment in the Era of LLMs: A Conceptual Framework
034e60a1dc73…
Source →arXiv PDF ↗Open →
Published 2026-10-26T04:00:00Z
Fooling LLM Safety Guards into Judging the Wrong Text
02a952d0c58b…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
MPIDetector: Detecting Multi-modal Prompt Injection via LLM-based Reasoning
f5d3cbc10e81…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
Accelerating Wildfire Hazard Mapping Across Canada with an AI Surrogate Modelling Framework
eac8b7829f11…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
The Cost of Saying Hello: An Empirical Study of Handshake Overhead in AI Agent Communication Protocols
dc724843c9eb…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
FlexVDR: Learning to Allocate Matryoshka Representation Budgets for Visual Document Retrieval
d519c261e8ee…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
baseVultra: Compact Nonlinear Recurrence with Reallocated Capacity
cb36e3169100…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
Neural Networks with Differentiable Belief-Function Layers
92dfb3ddcbf8…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
Differentially Private Synthetic Data via Generalized Moment Matching
8de55d2dca35…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
Self-Evolving Static Analysis via LLM Pseudo-Labeling
84045a607fed…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
When Stable and Preferred Semantics Agree: A Path-Based Approach
7d199391f8af…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
Protection Is Not One Event: A Survey of RAG Protection Research by Measured Endpoint
7b04376e2d0a…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
Deep Search in Real-World Web Environments
7a92c62dc5b5…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
FormBench: A Benchmark for Fine-Grained Retrieval in Formulation Patents
7038eece1e1d…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
Lighthouse: On Building a Trustworthy Digital Assistant for Exploring History with Civil Rights Archives
5a7539b88b9d…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
IRAH: Hierarchical Agentic Tree Search for Retrieval Pipeline Optimization
49a500b91f30…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
Detecting AI Training in Datacentre Power
410a7ef00f43…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
TauIndianBankBench: Procedure-Aware, Action-Oriented Evaluation of Tool-Using Conversational Agents
37f33c454afb…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
FusionEval: Benchmarking Model Fusion for Large Language Models
359afa880794…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
The EU AI Act Beyond Europe: A Practical Readiness Framework for Non-EU Organisations. Comparative Evidence from Four African Countries
329c4ee83753…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
Association between Player Perception and AI Disclosure on Steam: An Exploratory Study
23bf7760dcd1…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
Why Constrained Updates Still Forget: A Functional-Path Analysis of Continual SFT
1ad1aef14db5…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
When EVM Defaults Break: Three SDK Patterns for UTXO-Family Wallets
0d26c5ad7531…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
Agentic Verified Optimization of Real-World Software
0b5233bb5e76…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
Detection Is Not Enough: Reasoning Traces as Testable Program Hypotheses
0a2e04fffa64…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
QProtFuse: Query-Guided Layer Fusion for Retrieval-Augmented Protein Function Prediction
08a0728183e8…
Source →arXiv PDF ↗Open →
Published 2026-10-23T04:00:00Z
MCP vs CLI for AI Agents: A Comparative Analysis of Tool Integration Strategies for Autonomous Systems
08284d6e4090…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
TAGR: Task-Adaptive Geo-Semantic Retrieval across Heterogeneous Urban Delivery Tasks
faf9c9135d5c…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
How Far Can the Gemma 4 Speech Encoder Go Without Changing Its Weights? Saudi and Gulf Arabic Speech Recognition with a Frozen and an Adapter-Augmented Encoder
f9f1f478bdff…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
Scalable Stress-Constrained Topology Optimization: A Super-resolution and Simultaneous Approach Based on Machine Learning
f42df7223461…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
STAR-XPC: Set Transformer for Estimating X-ray Transmission in Polymer Composites
e5a580714d7f…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
Borrowing Strength Across Stores: Transfer Learning for Choice-Based Revenue Management
e50861c5e441…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
Controllable Generative Recommendation via Guided Token Refinement
d9ef115dcfd0…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
Benchmarking the Quantum Leap: Auditing LLM Evaluation for Quantum Code Generation
cf5cd4310b94…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
VerifierBench: Benchmarking the Generation of Executable Verifiers for LLM Agents
ce47ca760114…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds
cd87e06f3648…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
Can AI Chat Replace Traditional Search? Evidence from a RAG-based Live Events Experiment
c0d73df8f644…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
Who Approved This? Coding Agents, Human Accounts, and Merge-Gate Evidence at a Fintech Startup
abe7a07ed653…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
Runtime Semantic Discovery for Evolving Action Alphabets
a93cfc4f3245…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
RESEARCHHUB: A Personalized Literature Discovery System for Biomedical Preprints
9a9566cd9131…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
Transaction Foundation Models for Retrieval-Augmented Generation over Financial Transaction Data: A Comparative Evaluation with Text Embeddings
7b9889fc0180…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
To Keep or Not to Keep: Learning KV Cache Retention in Disaggregated LLM Serving Systems
785c59f4885c…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
PCLA-Bridge: A Framework for Cross-Domain Deployment of CARLA Agents
76d18948d1f1…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
Who Verifies the Builder? Toward Independent Assurance for Agent-Produced Software
745dd7225da8…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
Translation and data ethics
65ae7386695a…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
Multi-agent LLMs on the Cloud-Edge-IoT Continuum: A Systematic Mapping Study on Architectures, Deployment, and Evaluation
5587899579cc…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
Compilation Is Not Correctness: Scan-by-Scan Evaluation of LLM-Generated PLC Programs
50797d9d751c…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
A Small Model Asks Better: Fine-Tuning Query Clarification for Retrieval-Augmented Generation
32ada68d2797…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
SimHack: Predicting the onset of detectable reward hacking before RL training
15903a171a4b…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
Interaction-Gated Time-Frequency Learning for Parameter-Efficient PPG-Based Heart Rate Estimation
1198e883d678…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
Reinforcement learning for hardware acceleration and system-level optimization on FPGA and integrated-circuit platforms: A survey
0ed17346d049…
Source →arXiv PDF ↗Open →
Published 2026-10-22T04:00:00Z
SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery
0d1a92c489e1…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution
fb5aee040904…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
Large language model and reinforcement learning based autonomous construction and progress updates
f620d2532aff…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
Do We Need the Largest LLMs for Every Clinical Decision?
e7199e7a4b5d…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
Quadratic Sample Complexity for Strictly Replicable Realizable Learning with Unknown Marginals
e09f9306efe1…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
StarMind: Challenges and Opportunities in Orbital Computing
cea5b1ec8cce…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
H2DF: Calibrated Target Bands for Controllable Language-Model Unlearning
ce3950a5f0a7…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
AutoTerm-SST: Adaptive Terminology Memory with Zero Session-Time Setup for Streaming Speech Translation
b7d68e2bea48…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
GRaSP: Latency-Aware Optimization for Geo-Distributed Retrieval-Augmented Generation
b1dd5d2a95aa…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
AtomSD: Procedural Atom-Guided Self-Distillation for LLM Agents
ae90e5d3c85b…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
Pareto-Optimal RTL Code Generation via Multi-Objective Reinforcement Learning with Large Language Models
a371d88cf54a…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
Expert-Guided Rubrics as Dense Reward Signals for Reinforcement Learning in Non-Verifiable Domains
84d19607a4df…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
Learning from Past Mistakes: AI-Assisted Analytics of Software Defects and Their Fixes for Future Defect Prevention - An Industrial Case Study
79f3618ab480…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
Navalia: Advancing Cowork Agents through Verifiable Task Synthesis and Long-Horizon Post-Training
71ea4040f3ab…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
Mixture of Phonetic Experts Based Low-Rank Adaptation of Conformer Models for Accented English Speech Recognition
6d404cde9f0b…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
MOSS: A Production Framework for Monitoring and Diagnosing Semantic Failures in Search and Recommendation Systems
6977dd7a899d…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
High-dimensional layer-state trajectories reveal the internal dynamics of transformer inference
518eb8b2feae…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
Multimodal Ambivalence and Hesitancy Recognition with Bidirectional Audio--Text Cross-Attention
4294800e15e9…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
Industrial Agentic AI: LLM-Driven New-Generation Agents for Smart Manufacturing
3eab82dd3584…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
Fix, Not Just Resample: Bounded Compiler-Guided Repair in Lean 4
3c814cdd7639…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
WaveCommitments: Private and Verifiable Speech-Agent Marketplaces
2ff76829edb0…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
InterType: Breaking the Single-Function Barrier in Neural Binary Type Inference
2b82e7250f74…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
MedPAO-Assist: Edge-Deployable, Modality-Aware Agentic AI for Radiology Report Structuring
2889cd9580d2…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
MAMath-Bench: Process-Aware and Robust Evaluation of Multimodal Multi-Agent Mathematical Reasoning
19b0e886d3aa…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
How Intervention History Changes AI Agent Sabotage on Subsequent Tasks
15106f2d61d7…
Source →arXiv PDF ↗Open →
Published 2026-10-21T04:00:00Z
Steerable Pluralistic Policy Alignment from Anonymized Crowd Feedback
10207a59f91e…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
miniTE: Diagnosing and Bridging the Execution Gap in Native NVFP4 Reinforcement Learning
f4559d282695…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
A Group-Aware Comparative Study of Classical Machine Learning and Deep Learning Methods for Sensor-Based Human Activity Recognition
da42ac5ef25a…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
Announced Breaks Separate Conformal Reliability from Frequency Calibration
d6a2e4c80ef6…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
Organizing LLM Inference for Aggregate Predictions from Behavioral Data
d1cb295a36ef…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
How Data Scales in Agentic Reinforcement Learning: Laws and Synthesis Strategies
b88e4166482d…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
Composable Parametric Demographic Injection for Values Survey Simulation
b6fbeed6439d…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
GardenBench: A lightweight, daily evaluation of LLM capabilities
9f0e0225f199…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
Pack and Extract: An Effective Graph-Based Approach for Feature Selection
9a81784b1159…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
Modeling Human Behavior in the Prisoner's Dilemma with Large Language Models
972fffbadba1…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
SECURE-AI: Multi-Signal Uncertainty Quantification for Trustworthy Acoustic Cough Detection
889894c1eea1…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
Forecasting Patient Trajectories from the Electronic Health Records with Action-Conditioned World Models
8675b8257135…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
SAGE-CP: When Marginal Coverage Hides Route-Conditional Failures in Adaptive VLM Ensembles
8675841b3b8d…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
PolyGraph: Plan-Buffered CUDA Graphs for Adaptive Speculative Decoding
85431effb0a2…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
PeekKV: The First Content Token Already Knows Which Heads Matter
7f99a7fdaf13…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
TeleTwin: A Calibrated Digital Twin of Telegram Crisis Discourse as a Ground-Truth Testbed for Detecting LLM-Powered Information Operations
748dfe451d27…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
Improving Fake Profile Detection Through Multimodal Learning and Research-Guided Feature Integration
676c15c4dcea…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
Beyond Prediction: A Component-Level Study of Concept Recovery in In-Context Learning
5c921a819ac8…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
Fast Construction of Inner Sphere Trees Using Machine Learning
57c636f58da3…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
ReTTT: Reflection-Driven Test-Time Training via Experience-Based Parametric Memory
3c880a32d772…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
Doing Less with More: A First-Principles Exploration of the Suitability of Agentic Computing over Alternative Architectural Choices
161a3a6f1b1c…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
Measuring the Influence of Modality-Specific Node Representations on Graphs
13ca25fdc55e…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
Web Agent Agentic Reinforcement Learning Decision Model Under Multi-Cost and Failure Risk
1319d5a3d667…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
Translating in style: An open-weight alternative to GPT-4 for culturally aligned machine translation
0c8a10c0823b…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
Factorization-Guided Training and Inference for Diffusion-Drafted Speculative Decoding
06dbae1f2e99…
Source →arXiv PDF ↗Open →
Published 2026-10-20T04:00:00Z
Zero-Shot Tabular Learning via Hypergraph Reasoning with LLMs
004971a171d0…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
Generative adversarial networks with Monte Carlo dropout uncertainty quantification for structural health monitoring: Fibre Bragg grating data augmentation comparison in Hawk T1A aircraft
f9b8b249f490…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation
f5ca99ccb7ff…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
Decomposing URLLC Deadline Failures in Beam-Managed 6G Networks: Implications for Mission-Critical Wireless Systems
f266bea4fff8…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
Sparse Autoencoders Can Induce Local Geometry for Mitigating Catastrophic Forgetting
f116ff93ec2e…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
Recoverability-Controlled Safety Miscalibration in Large Language Models
dd2238747e1e…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
From Events to Reasoning: Hierarchical Rule Composition over Explicit States
dc8acb3005e5…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
Embeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language Models
d2618effe4fa…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
An Agentic ENF Framework for Forensic Video Authentication Against Generative AI
d0d6bb95125c…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
Eliciting Specifications: When Does Interactive Clarification Help?
c782f17b0a8a…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
BOLT: Multi-Bottleneck Bound-Guided Learning for Flexible Job-Shop Scheduling with Time Lags and Resource-Coupled Transport
bb3dec8c48f8…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
GPU-Accelerated Robust MA--RIS Pre-Optimization for Communication and Target Illumination
ba73a39e7755…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
Rank Measures of Fine-Tuning Updates Need a Noise Baseline
b9a7fe02ae6c…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
Rethinking User Encoders: Routing Diffusion States for Scenario-Adaptive User Representation
9b173f392b5e…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
Social Bias or Social Desirability? Comparing Factorial Survey Experiments for Humans and Large Language Models
948d484d4118…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
When is a large language model a good calibration agent? Physics-labeled prompting for budgeted engineering simulator calibration
8e56a6d2d9eb…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
Structured Authority Injection: Persistent Human Control for LLM Agents via Typed MCP Overrides
7f7473d79e63…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
PRIME: Towards Verifiable Evidence-Grounded Reasoning in LLM Agents
7e7a4fd3e8fa…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
CGDT-CESN: Correlation-Guided and Dynamics-Trained Clustered Echo State Network for Multivariate Time-Series Prediction
7644000b8948…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
CF-NODE: Counterfactual Spatial Node Intervention for Test-Time Adaptation Under Domain Shift, Evaluated Across Five Diabetic Retinopathy Datasets
751540e718b8…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
Trust but Verify: Designing Region-Inhomogeneous Forward Dynamics for Discrete Diffusion
61be1dd912cc…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
Aligning Information Theory and Formal Verification: A Lean Formalization of Rate-Distortion Theory
5056b540d6f3…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
TRACE: Transformer Residual Activation Codebook Encoding for Communication-efficient Distributed Edge Inference
47ea7df7281d…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
Sensitivity Analysis of Decision Rules in an Agent-Based Agro-Ecological Model
30aad1fdbe3f…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
Binding-Specific Relearning Savings for Test-Time Continual Learning
23110e665631…
Source →arXiv PDF ↗Open →
Published 2026-10-19T04:00:00Z
EnterpriseSynth: Zero-Execution SFT and Evaluation Data from OpenAPI Specs
0ee9b7240eb4…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
Same Answer, New Box: How Much of RLVR's Out-of-Domain Gain Is Answer Format?
f20f9d1fd1dd…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
Harnessing MPI mutations for AI error detection
f0e9c98de010…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
Unmasking the Secret Code: Using Canaries to Show How Masked Context Controls Memorization in SFT
df9cd9162de9…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
FlowBudget: Training-Free Sampling-Budget Estimation for Flow Matching Models
d8c2f1df6690…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
Feature Elicitation for SAE Steering of Deceptive Behaviour in Small LLMs
ccbdec48a2e7…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
PRISM: PRIvileged Sibling-guided Multi-Agent Topology Design
bb4ed1edbf55…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
Jev-as-a-Judge for RAG Claim Verification: Confidence-Gated Cascading Between a Non-Generative Verifier and a Frontier LLM
b88288f0b444…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
An exact computer-assisted lower bound for Fisher-information convexity along the two-dimensional heat flow
b6a2528f7250…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
KNOU-Flood: Advancing global streamflow forecasting with lead-aware probabilistic machine learning
a692cf3916ca…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
CoTS: Competitive Token Selection for Latent Reasoning in Large Language Models
983d1c8f4c3f…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
Real-time Chatbot Romance Scam Detection in Stage Classification
849250fae725…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
Empirical Evaluation of Machine Learning for Cloud Cryptojacking Detection: Effects of Preprocessing and Evaluation Protocols
822bb657717b…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
Forensic Analysis of the HackRF One with PortaPack Mayhem Firmware
8163cd0b584f…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
A polylogarithmic bound for list replicability
7b3713aa29e7…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
MeddeX: A Retrieval-Augmented LLaMA-3 System with Gemini Vision for Evidence-Backed Medical Report Analysis
7846e77f7967…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
A Large-Scale Dataset for Multi-Class Financial News Classification in Brazilian Portuguese
74b379be434b…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
Developer Experiences with Cursor AI-native IDE
578b938e0ccf…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
Hybrid DeepXAI Fusion Network for Interpretable Big Data Analytics and Secure Cloud Decision-Making Systems
45945c1dab03…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
Expanding Attention: A Taylor-Series Route to Linear-Time Transformers with a Fixed Number of Recurrent States
39878bff33f8…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
AbridgeKV: Compressing Long Reasoning into the KV Cache of Learned Pause Tokens
29191baffb2c…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
DeepUnfolding_Agent: A Classical_Quantum Adaptive Control API
1fab75d4ac23…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
Does Personalization Break Trust? Open-Set Rejection Calibration Under Few-Shot On-Device Intent Adaptation
0ffaebaa5196…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
Exploring the Design Space of Permutation Diffusion LLMs
0d0a3e11066c…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
Context Injection and Long-Horizon Reliability: Separating Duplicate Recognition, Local Processing, and Counter Tracking
0a3a7ccb11cc…
Source →arXiv PDF ↗Open →
Published 2026-10-16T04:00:00Z
Latent Annealed Posterior Sampling with a Variance-Preserving Bridge for Sparsely Observed Random Fields
01db3eda14d3…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Evaluating Large Language Models for Multilingual Abstractive Summarization: A Comprehensive Study of English and Bengali
facf5bd123ed…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Lotus: Learning to Understand Time-series by Learning to Forecast
f4e57705e0de…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat
ed4d03bda1f6…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Discovering Undisclosed Concepts in LoRA Adapters for Diffusion-Based AIGC Models
ea1690ad6e92…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Beyond Equation Search: Conjecture-Guided Discovery with SCOPE and ClosureBench
e7f7f3ec7694…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Stabilizer entropy cones as self-dual slices of linear rank cones: a five-party gap and dependence on the local dimension
e7e0652f8f01…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Why Static Skill Inconsistencies Do Not Equate to Runtime Risks: A Behavioral Analysis of LLM Agent Execution
e513b88e1a8b…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery
e3f738370ac4…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Inverse Reasoning Models for Efficient Post-Training and Verification from Answer-Only Data
d4df20049607…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Semi-Amortized Bayesian Inference with Reusable Local Posteriors
cd4941cb8bf3…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Do Vision CIL Methods Transfer to Protein? A Diagnostic Benchmark of Frozen Protein Encoders
9b69fc60180e…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Data Density Scaling Laws for Image Self-Distillation
8f263200cb3c…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Limits of Statistical Assurance for Embodied and Agentic AI under Adaptive Adversaries
872d4d61fc00…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Discrete Diffusion Models are Minimax Optimal Under Sparsity
7e73115c542d…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Wong--Zakai Convergence and FNO Learning for Stochastic Volterra Equations
631f5ca3515b…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
IR-PRM+ with Previous-Utility Prediction: Constant Regret and Best-Iterate Convergence
61bf95895c09…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Do Perturbation Predictors Learn Gene Interactions? Diagnosing Extrapolation in Agentic Screening
6128d399c0a7…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
PMO-Dock: Benchmarking Docking, Specificity, and Generalization in Molecular Optimization
56ba15f75933…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Physical Layer Anomaly Detection via Adaptive Gaussian Mixture Model
51b8f1fa38c6…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection
4d9a1ede5e7f…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Bayesian Causal Forests for Zero-Inflated Continuous Outcomes
4b92174a9d8a…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Token Utility for On-Policy Distillation via Local Trust-Region Optimization
33bbbfba7583…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Scaling Cheap Synthetic Pretraining Improves Indoor Radio-Map Prediction
2f01747f6285…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
Delay Complexity Dimension: Learning with Delayed and Censored Labels
279c4c9af7d1…
Source →arXiv PDF ↗Open →
Published 2026-10-15T04:00:00Z
On the Investigation of Antenna Beam Pattern Models for Fast Beam Placement in LEO Satellite Networks
2592ae25e648…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
EliteTable: Self-Improving Program Search for Executable Control Policies
fb2b9c595795…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
Transformer-Based Masked Diffusion Models Provably Learn Distributions with Latent Structure
fa7764968fb2…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of Edits
e00ed0ec3098…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
SoK: Privacy-Preserving Order Matching
d8127845403e…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
An all-transistor physical-learning transformer can be trained to perform in-context learning
b13b5cc3e1e6…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
SWE-Duel: Towards a Self-Scaling Arena for Coding Agents
a4a8b30ee866…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
Sample-Adaptive Zeroth-Order Post-Training
9cd6287f7f19…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
Proceedings of the Seventh miniKanren and Relational Programming Workshop (miniKanren 2025)
9c7bd9dc20d0…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
Kairos: Toward a Byte-Level Foundation Model for Every Modality
92df548532e5…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
CircuitTree: Composing Circuits into A Syllable Transcriber
8c3820df4aec…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
Fix What's Wrong, Keep What's Right: Hallucination Repair for LLM-Based Optimization Modeling
8354709629f3…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
Faithfulness Without Anchors: A Position Paper on the Structural Misalignments of Explainable AI Faithfulness Metrics for Feature Importance
7a12822a078d…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
An Exploration of Attacks on AI Agent Systems
76c8b48f2c32…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
CTML: A Comprehensive Framework for Continuous Testing in Machine Learning Operations
70099b0ca94f…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
An Input-Dependent Readout Phase for Resonant Sequence Models
676ba012b78b…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
CacheScope: Exact-Compute Allocation for Training-Free Diffusion Acceleration
60f1a9adddd1…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
Equal-Budget Monte Carlo Tree Search versus Randomized-Restart List Scheduling for DAG Workflows: A Controlled Equal-Budget Computational Study
4ef2fdfc2c28…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
Algebraic Integer Quantization for Machine Learning Applications
436b07414b0c…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
Behind-the-Meter Photovoltaic Visibility from Net Smart Meters: Deployment Regimes and Operational Insights
412d1bf69c20…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
Efficient Learning of Survival Analysis Models Under Outcome-Dependent Truncation and Censoring
31144c30e8d5…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
Enriched Holomorphic Neural Networks for 2D and 3D Laplace Problems
230bfe73e153…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
GlucoPRISM: Protocol-Supervised Pretraining for Cross-Cohort Glucose Transfer
20ac7c845da3…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
Organizational Context for the Enterprise Security Brain
1c0873fc3769…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
Contextual Correction of Parallel Draftsfor Speculative Decoding
1062d0edd578…
Source →arXiv PDF ↗Open →
Published 2026-10-12T04:00:00Z
Market Impact Estimation via Causal Foundation Models
060a724753be…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
Code Understanding is a Bottleneck for Coding Agents
f91a0e841733…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice
f3715b16b7ca…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
DLCB: Ahead-of-Time Compilation for Dynamic Deep Learning
eca327dfc21c…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction
ebc4cb1902fe…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
Freeze the Decoder, Heal the Encoder: Parameter-Efficient Adaptation for SVD-Based KV-Cache Compression
e0f4fa683dd2…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
Performance Analysis and Sensing-Aware Resource Allocation for Full-Duplex Massive MIMO ISCC Networks
cf1b85592a21…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
Verification and Self-Improvement in Agentic AI: Foundations and Limits
cb6ca810d116…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction
c85955ba33d3…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
Diffu-LoRA: A Novel Low-Rank Adaptation for Personalized Diffusion Models
c5c5ec242854…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
An Explainable Header-Centric Framework for Large-Scale Semantic Table Interpretation and Data Quality Assessment
b97c4d4f2dbd…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking
b544d23818e4…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
From Investigation Failures to Reliable SOC Agents: Understanding and Improving LLM-Based Alert Triage
af08e5c4adbb…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
The Hellinger Conjecture for Antipodal Boolean Functions
965ed945f34f…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
When AI Finds Hidden Messages, Does It Report?
8dc4c48eeff1…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
TestJack: Should you trust the results in coding benchmarks? Agentic Coding Benchmarks Auditing via Evaluator Evolution
89a8aab06292…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
Certified Corruption Budgets: Anytime-Valid Leaderboard Claims under Adaptive Rigging
82c0a6f26b7a…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
PyCache Trap: The Inspection-Execution Gap in Agent Skill Scanners
77f2a0a8ab2a…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
Beyond Type-checking: Towards Holistic Evaluation of Formal Specification Generation
5d55c9f9f11c…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
JevForest: Path Voting for Budgeted Feature Acquisition
4af5c4af24fe…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
Wieszcz-XIX: A 3.1-Billion-Word Corpus of Pre-1918 Polish and Temporally Bounded Language Models Trained From Scratch
2465ab27316f…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
The optimal information complexity of VC learning
23730531c68b…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
LIFT: A Lifecycle-aware Interaction Factorization Transformer for Unified Retrieval and Ranking
1fa3e80a4347…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
Coverage, Not Difficulty, Sets How Much Synthetic Data an Activation Probe Needs
1b9737a782ff…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
Temporal transformer CAN encoder with federated lightweight heads for anomaly detection
0e743105fdc5…
Source →arXiv PDF ↗Open →
Published 2026-10-09T04:00:00Z
When Routing Reveals Membership: Privacy Leakage from MoE Router Telemetry
02e417324d78…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
Emo-Jev: Probabilistic Reasoning for Emotion Classification with Jev
fdccac1140fc…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
HydroSphere: A Framework for Governed, Self-Healing Wastewater Infrastructure
f79adbfe4584…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
A Vehicle-Integrated Approach to Digital Twin Deployment for Bridges Through Drive-By Sensing
f1cf4b13ed0a…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
Just for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States
e0ee3c12e2ab…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
Adaptive Workflow Intelligence: A Cognitive Architecture for Context-Driven Enterprise Automation
d6b50fbc6786…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
Route-Verify-Vote: Procedure-Conditioned Self-Consistency for Mixed-Domain Reasoning
d35ac1031cc6…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
QuanLing: Cross-Branch Validation of Language Distance Quantification on Western Romance
cf13fa296411…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
A Bayesian Mirror Architecture for Emergent Consciousness: Circular Hierarchies, Self-Manifolds, and Hybrid Event-Self Binding
c96482b494dc…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
Bounded Autonomy and Verifiable Safety for Agentic AI Enabled Automation
c477f31da74f…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
Beyond the Sycophancy Score: How Task, Model, and Pressure Shape LLM Yielding
97ba8c77fd22…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
The Cost of Long Memory: State, Context, and Stability Complexity in Sequence Models
94e6e4c5e232…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
Transferability and operational reliability of a Prithvi crop classification foundation model under phenological and geographic shift across three continents
8ced55bbcaae…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
Accelerating Floating-Point Satisfiability Solving via Gradient Normalization
803007ffbfe4…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
Leveraging LLM-Generated Explanations for Detecting Emotionally Rewritten Fake News
7b963d4882c8…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
When Forgetting Looks Like Improvement: Metric Masking in Streaming Diarizer Adaptation and the Price of Rehearsal
752049de0ecb…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
CoDR: Training-Free Confidence-Drift Remasking for Diffusion Language Models
70c8dc65b400…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
Child ASR Adaptation with Adult Retention: An Empirical Study
708f3c6d9e49…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
Task-Oriented Key-Layer KV Communication for Efficient Latent Multi-Agent Collaboration
57ddf831d54c…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
DenoFlow: Flow Matching for SSVEP Denoising under Real Physiological Artifacts
550e7cf98632…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
HCPN-GCN: Scaling Hierarchical Prototype Networks with Cone Geometry for Continual Graph Learning
4d0a07c963d1…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
Beyond Baseline Severity: Temporal and Disease-Specific Predictors of Depression Outcomes Following Mindfulness Interventions
43e0d2c38513…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
Tokka-Bench: Evaluating Tokenizers Across 100 Natural and 20 Programming Languages
41163c35cb50…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
KVFetch: Temporal Prefetching for the Missing Half of KV Cache Compression
1a320b139a15…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
Beyond Risk Prediction: Evidence Grounding and Psychosocial Factor Verification for Explainable Suicide Risk Assessment
05eedaeaaa65…
Source →arXiv PDF ↗Open →
Published 2026-10-08T04:00:00Z
LRCC: Generalizing Low-Rank Compression with Conditional Computation
006d25f8bdd0…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
Text2Dashboard: A Governed Agent Architecture for Natural-Language Dashboard Generation over Enterprise DataBrain
f46898aa3db1…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
Learning from Unreliable Trajectories: Adversarially-Robust Federated Q-Learning
f141fc63f05d…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
Comparative review of hybrid forecasting models for short-term prediction of building thermal load
e7507cab64b0…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
Learning When to Refine: Long-Horizon Reinforcement Learning for Budgeted Neural-Operator PDE Solvers
cbf1904bec08…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
Low-Rank and Structured Sparse Tensor Decomposition for Anomaly Detection in Multivariate Functional Data
c99b46468c72…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
Near-Optimal Sample Complexity for Recursive Entropic Risk Reinforcement Learning with a Generative Model
c8f9d19ef50f…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting
c443924a3e81…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
RadOnc-Agent: An LLM-Orchestrated Framework for AI Workflows Across the Radiotherapy Care Pathway
c180a6157245…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
FluidPD: In-Place Elasticity for SLO-Aware Prefill-Decode Disaggregated LLM Serving
b1ed7a1fb7ba…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
Anchor Divergence for Semantic Geometry in Contrastive Learning
b0f4b5d0da71…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
When Does External Guidance Help LLM Reasoning? A Bias-Variance Theory of Guidance-Augmented GRPO
a9cd6bf3f6d0…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
AttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVD
a6e993823499…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
Zero-Shot Visualization: Exploring Text Corpora with User-Prompted Axes
a42b2cadc46c…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
Metonymic Circuits for Abstract Concept Grounding in Vision Transformers
7cea0311a49a…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
DIBench: Benchmarking Decision Integrity of GUI-based Mobile Agents Under Deceptive Injections
79a3a1790abb…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets
75aada80eae6…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
Component and Dimension Sparsity in Transformer Refusal Mechanisms
6c2e94c91a01…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
Memory Prediction Excess: A Probabilistic Quantity for Predictive Gain and Memory Length in Stochastic Processes
5441dcdbf6d6…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
Neutrosophic Ensemble Classification for Uncertainty-Aware Bearing Fault Detection: Evidence from Laboratory and Variable-Speed Industrial Benchmarks
48a8d43bf209…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
Tree Navigation Without LLM Summaries: A Matched-Cost Study of Hierarchical Retrieval for Long-Document QA
45b7260cf87d…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
ASAP: Assembly-Source Aligned Pseudocode Refinement For Binary Decompilation
1f8a30dabe84…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
EDAP: An Efficient Data-Gathering Protocol for Wireless Sensor Networks
1045f522647a…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
Capacity, Responsiveness and Alignment: What Makes a Latent Structure Actionable
09edd3eb81b9…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
TEMPEST: Temporal Embeddings for Scalable Driver Identification via Angular Margin Learning
06f76c425d66…
Source →arXiv PDF ↗Open →
Published 2026-10-07T04:00:00Z
Event-Driven ML Pipeline Orchestration for Manufacturing: An AWS Industry Experience
00e859feb259…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses
fdab5904d226…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
Approximation Property of Dropout Neural Networks: Sobolev Rates and Confidence Bounds
e49a3afa2101…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
Nearest-neighbour baselines for fingerprint prediction from MS/MS spectra under different assumptions
e401843fd6b6…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
TRACE: A Reproducible Benchmark for Electricity Price Forecasting with Official Operational Text
d0c1650253e2…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
State-Space Unlearning for Non-Stationary Bias in Land Surface Forecasting
c2f473aad4aa…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
Effects of interpulse-interval variation on deep-learning classification of bat vocalizations
bfb25ea28ff8…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image Generation
b683ae9f5175…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
$\Psi$-Resilience: Model-Free Feature Importance from 1D Topological Signals
b35dc524b0d0…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
HakemBench: A Turkish Benchmark of Typed Decisions
a67b7dbbbe83…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
Overcoming Challenges of Interpretive Structural Modeling with Large Language Models
9f70df5711a9…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
Diffusion-Based Synthetic Data Pretraining for Enhancing Activity Recognition
9a2a016bc437…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
MACTS-EM: Multi-Agent Collaborative Time Series Forecasting with Emergent Memory
858c7034526e…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
From Mathematical to Executable Certificates for Machine Unlearning
7c8d2455b6f6…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
Parameter-Free Interval-Dynamic Regret under Heavy-Tailed Noise
6bad1340c185…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
MuLoRA: Spectrally Balanced Low-Rank Adaptation for Continual Learning
5de3e4da3a0a…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
Line-Rate GTP-U Admission Control at the Edge of a Cloud-Native 5G Core: An XDP-Based Design for Kubernetes-Hosted User Plane Functions
5b86fa0a7732…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
The AI Risk Observatory: What Can We Learn from AI Disclosures in Annual Reports About Societal Resilience?
54ac5ea5e5b0…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
MintFlow: Minimal Trajectory Intervention for Constrained Flow Matching
436f5649ff6e…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
The Price of Greenwashing: Algorithmic Verification and Market Discipline using Conformal Machine Learning
347e5ee1871e…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
Hybrid Machine Learning-Assisted Raman Spectroscopy with Generative Feature Augmentation for Pharmaceutical Identification
2d242852f087…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
Rank-Aware Speculative Sampling for Diffusion Draft Trees
2d0f4b0fa8e4…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
CLEAN: Psychometrically Consistent Incremental Cognitive Diagnosis under Concept-Space Expansion via Architectural Isolation
24bffb1ab159…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
Counterfactual Predictions in Scientific Emulators Without Controlled Experiments
16f0110bbf21…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
From Alert Floods to Precedence Forests: Zero-Prior-Knowledge Incident Triage with LOGOS
0cb256223060…
Source →arXiv PDF ↗Open →
Published 2026-10-05T04:00:00Z
Feature Freshness Budgets for Real-Time ML Inference Under Stream Lag
07ff144aee47…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
The Domestic Unprotected Zone: Algorithmic Governance and the Reproduction of Perpetrator Discourse in Conversational AI
fdb4665bd8fd…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
A Vision-Language Framework for Measuring Social Life on Sidewalks
fb299c65d41b…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
Stable and Faithful Explanations for Knowledge Tracing
ec8441cfeaf7…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
Make it SewSimple: Navigating UK Curriculum and Classroom Practice in Secondary Computing Education with E-textiles
ec8420b6b715…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
Stochastic Inertial Krasnosel'skii-Mann Iteration Achieves Near-Optimal Sample Complexity
d93ec5dcc2d5…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
TW3Cast: A Frozen Router of Lightly Fine-Tuned Foundation Models for Time-Series Forecasting on GIFT-Eval, Selected Entirely on the Training Split
ca728b51da43…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
Unsnarling the Red Tape: Computational Infrastructure for Regulatory Systems
c753b9e482e6…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
From Prediction to Explainable Provider Behavior Profiles for Fraud, Waste, and Abuse Review
c255c3d984c6…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
When Evaluators Cry Wolf: Lessons from Production LLM-as-Judge Evaluation in Educational AI
bbb2da4622a5…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
Generative AI May Reinforce Social Biases in Software Engineering Education
b3ee65b0462d…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
A weak Hellinger inequality for noisy Boolean channels
a79dbdd3296b…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
Political Sorting Can Drive AI Models Apart Through User Feedback
9b2cea875c43…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
Privacy Leakage Through AI-mediated Analysis of Smartphone Data
9aa0dd1cf228…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
Synthesizing Proofs Using Proof Sharding and Exploration
94d6dc03c07d…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
An Exposition of GPT Astra's Proof of Lower Bound on DP Continual Counting
91edf7c61f6a…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
IaC-Guard-V: A Verification Framework for LLM-Generated Infrastructure-as-Code Repairs
7e5a05fec7ba…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
RADAR: Readiness for AI Discovery and Agentic Reach
7a723bde1f55…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
Framing by Wording, Framing by Selection: A Large-Scale Two-Dimensional Audit of French News Headlines, 2022-2025
78dd023e7e8a…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
Virtual Backhaul Connectivity for Enhanced Coverage in Fiber-Less Areas
710224bf7473…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
Certified Task-Conditioned Active Observability
629df98c128c…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
Stress-Testing Structure-Aware Calibration of Malware Graph Neural Networks under Type Shift
474c672f2ef3…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
Sequential Confidence Sets for Coverage-Constrained Conformal Model Selection
4264c0e0e95a…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
Drafter: A Python Library for Full-Stack Web Development in CS1
3cdc97aef356…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
When Should Forecasting Agents Reason? Behavioral Stress Tests for Reliability Routing
33bbefbd131c…
Source →arXiv PDF ↗Open →
Published 2026-09-25T04:00:00Z
Measuring the Professional Educational Competence of Foundation Models
32b891baa7ee…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity
e7d5dea275ef…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
Spec2COBOLRot: An Agentic-AI Degradation Loop for Realistic COBOL Corpus Generation
d126a2218bdc…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
What Makes a Terminal-Bench Task Hard? Separating Genuine Hardness from Fake-Hardness on an Adjudicated Agentic Corpus
d108687f8c69…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
HARN: Hierarchical Associative Resonance Network for Event-Driven Multi-Timeframe Forecasting
cf190d9db4f8…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents
bf8041415408…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
Signal2Symbol: Neuro-Symbolic Temporal Reasoning for Explainable Physiological Time-Series Anomaly Detection
bf433ddcc343…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
Distilling Lexical Product Associations into Deep Transformers: An Extreme Multi-Label Approach for Natural Language E-Commerce Search
b3b44b60dab0…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
COPE: Continual Personalization of LLMs under Sparse User Feedback via User Embeddings and Self-Evaluation
9d1a46b7282b…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
The Drift Contract: Spectral Updates for Depth-Robust Local Learning
9c1e1dbc62bf…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
On Preference Coverage Collapse from Hindsight Relabeling in Multi-Objective Reinforcement Learning
8e2f19c3e32b…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
ItColBERT: An Italian-Specialised Late-Interaction Retriever
8c88d6e09230…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
CORE-STACK+: Meta-Learning for Deep Stacked Generalization
8c4a0c312fc7…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
Comparative Evaluation of Static Embedding Models for HTTP Request Anomaly Detection
72bbf42a09d7…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
Marginally Correct Tool Caches Can Reverse Group-Normalized Policy Updates
717d676f82d1…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
Who Finishes the Job? A Study of Follow-Up Fixes and Commit Authorship on AI Coding Agent Pull Requests
6b069d4b4c4e…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
A Hybrid Rule-Based and AI-Augmented Framework for Automatic Failure Recovery in DevOps Deployments
6656307273e0…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
QUARTET: Quad-branch cross-Attention and Random-walk Traces for Enhancing Transformers on Relational Graphs
62fbd631184a…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
A Leakage-Aware Multimodal Evaluation Framework for Early Intraoperative Acute Kidney Injury Prediction
60e93379d646…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
LWCal: Loss-Weighted Calibration for Tabular Classifiers with Noisy Calibration Labels
52c465e4acc4…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
PR-Smoother: Simulator-Preserving Non-Gaussian Smoothing for Data Assimilation
4dfeee065f63…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
ACTS: A multi-tier benchmark evaluating LLM cipher identification under controlled blind conditions
483db24a515a…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
Silent Failures in Agent-Tool Interaction: An Audit of ToolUniverse
464ffec666da…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
FedCoT-VQA: A Federated Learning and Unlearning Framework for Chain-of-Thought Planners in VideoQA
42923f0aa7ef…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
Ajar: Measuring Open Privilege in Agent Defenses
3286529dff2a…
Source →arXiv PDF ↗Open →
Published 2026-09-24T04:00:00Z
COMED: The Missing Middle Between Routing and Collaboration in Multi-LLM Inference
0a83efdf2876…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
Prompt Breadth and Rollout Refresh Interact in On-Policy Distillation
f4d27c8936ea…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
What Does Chain-of-Thought Entropy Measure? A Channel Audit of Scaffolding, Routing, and Content
f411a1bd5249…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
Peerify: Benchmarking Peer-Review Claim Verification
ed2ba70b52d1…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
AIBuildAI-2.5: Efficient Autonomous AI Model Development Through LLM-Guided Tree Search
d3393a28afa6…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
Same Quantity, Different Answer: Numerical Representation Invariance in Language Models
c8b531725807…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
From Tone to Trajectory: Continuous Sentiment and the Shape of Monetary Policy Communication
c1a411c39b52…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains
b503fea2cfa2…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
Do Synthetic Personas Predict Real Audience Response? A Sim-to-Real Study Where a No-Persona Baseline Beats Persona-Based Copy Simulation
a919f05751a8…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
Graph-Based Inference for Feedback-Driven Word Deduction: A Scalable Framework for the Jotto Problem
8f477b9f7ccc…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibratione
8bad572830e1…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
ChainDoRA: Tensor-Train Factorized Weight-Decomposed Low-Rank Adaptation for Parameter-Efficient LLM Fine-Tuning
80cc1fda78ef…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
A Computational Approach to Measuring Semantic Change in Sanskrit Literature
66a9827c23f7…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
Not All 4-bit Quantizers Are Equal: Deployment-Time Mitigation of PII Leakage in Fine-Tuned Small Language Models
666f707872bf…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
What Does 99% Accuracy Measure? A Reproducible Audit of Shortcut Learning in a Widely Used Fake News Corpus
65a472fbe277…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
LatentPort: Beyond KV Cache - Cross-Model Transfer of Recurrent Memory in Hybrid Language Models: A 4B-to-9B Hybrid-State Handoff Without Target Prefix Replay
5847e4fff99d…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
4DGS-JEPA: Temporally Compositional Joint-Embedding Prediction for Dynamic Gaussian Splatting
52b8cf6c9cd6…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
FrontierMath Erd\H{o}s
4b9c48b7344c…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
"As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It
488b182108b0…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
Training a Language Model End-to-End in Rust: An Experience Report
4492360b548c…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
MoM: Memory of Memory
4115a89fb1a6…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
Do Existing Preconditioners Improve Biomedical Tabular Foundation Learning? An Empirical Study on TabPFN Optimization
3d3fcb5100d3…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
Self-Cleaning and Captured Anyway: One Measured Primitive for Error in a Store an Agent Writes to Itself, and What a Falling Score Actually Measures
2c9768139a56…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
Compressibility is not Feedback: A Random-access Gap in Causal Semantic Repair
1fc9cd45ea83…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
LLM-Driven Training-free Location-Attribute Synergic Fusion: A Closed-Loop Paradigm for Dual-source Encrypted POIs and LULC Mapping
03391285a4a9…
Source →arXiv PDF ↗Open →
Published 2026-09-23T04:00:00Z
Retrieved-Span Training for Efficient Query-Focused Meeting Summarization on QMSum
032ba4fbc9c7…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
PRQuant: Permutation Residual Quantization for Low-Overhead Inference
f71f877823d0…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
AI-inferred expressed well-being and collective-action discourse in climate-change campaigns on X
ecb3026a3534…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
Success Leaves Detours: Learning Executable Walkthroughs for Long-Horizon Agents
df69f283a0da…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
Recognition, Simulation, and Refusal: A Contamination-Aware Study of Classic Psychological Effects in LLM Agents
d4b498dbeba1…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
Modelling daily activity patterns from mobile phone location data via deep representation learning
d310738ef2dd…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
Beyond the Text: Verifying That Agent-Written Papers Are Backed by Their Artifacts
caca5b61fdc3…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
Generalized Multimodal Foundation Model
c70719f89eeb…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
LE4Mob: Towards Inductive, Distance-Aware and General-Purpose Location Embedding for Human Mobility Modelling
c64d20e1a696…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
Correcting Learning-based Perception for Safety
c016c16feb47…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
Memory That Looks Forward: A Zero-Inference Prospective Term for Personal Memory Retrieval
ac0cb291aeff…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
Toward Fairness in Machine Learning Models for Predicting Treatment Retention and Premature Discontinuation in Medication for Opioid Use Disorder
a1b25ed6be4a…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
A Shared Learning Rate Is Not a Neutral Control in Selective On-Policy Distillation
8f347b8556d8…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
Privacy Personalization Trade offs in LLMs: The Impact of Stylometric Signal Reduction on User-Specific Text Generation
78cf5f8587a5…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
Evaluating Fine-Tuned and Base Language Models in Maternal and Vaccination Healthcare for African Settings
72778b0ee8db…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
AdaMem: Adaptive Memory Token Allocation for Soft Compression in Retrieval-Augmented Generation
6baac9f97d29…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
When Who You Are Can Change the Code You Get: A Study of Persona-Induced Bias in LLM Code Generation
52e9efa7df99…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
Evaluation Awareness Shifts from Format to Context with Model Scale
50c2578b237e…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
An Empirical Cost Attribution of Context-Compression Gateways in Multi-Turn Coding Agents
45c109c5b13e…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
TreeSpark: Calibrated, Load-Adaptive Draft Trees for Semi-Autoregressive Speculative Decoding
3c08b18da61e…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
A framework for recipe data structure with applications for culinary and nutritional insights
2f9b13b9d935…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
Token Signatures of Code: Comparing Coding Behaviors Across Large Language Models
1f2f70c44810…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
DeepInstructor: An Agentic AI Instructor for Experience-Driven Idea Evaluation
1456dd4ac23b…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
ZoAQ: Adaptive Zeroth-Order Querying via Query-Reuse Coupling
11c38d05cd56…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
Context Poisoning as Extreme-Value Attention Interference in Long-Context Language Models
08053572e326…
Source →arXiv PDF ↗Open →
Published 2026-09-22T04:00:00Z
Summarize, Judge, Refine: Decoupled Content Understanding and Policy Learning for Multimodal Content Moderation
0700f15bf581…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
Curriculum-Based Noise Adaptation for Phoneme-to-Text Reconstruction in Visual Speech Recognition
f1dacd9e8c51…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
Reviser: Revision-Capable Text Generation via Autoregressive Cursor Actions
ef8921403e52…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
MME-Safety: A Fine-grained Benchmark for Safety Evaluation of MLLMs
e74dd1b20e60…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
Recursive Language Models Generalize Out of Domain
e66121842c22…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
Rewarding Efficient Reasoning Improves Abstention on Underspecified Tasks in Reasoning Models
e33975043df8…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
Do small language models know what they don't know?
e0f9879293f9…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
From Discharge Notes to Patient Understanding: Persona-Grounded, Open-Ended Simulation of LLMs as Discharge Educators
dfe2fb05b3d8…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
A Generative Grammar Underlying the Voynich Manuscript, the Pastiche Hypothesis: Evidence from Large Language Models
cb81ff04752c…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
Reading Less While Writing: A Closed-Form Bandwidth Dial for Streaming Multimodal Decoders
c4a81281342e…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
Beyond WER: Entity and Disfluency Recall in Accented Conversational ASR
b860e6d45cce…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
PhysioBench: A Unified Benchmark for Physiological Signal Question Answering
b47105b1bf1d…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
Reading Anxiety or Reading the Label? Comparing Fine-Tuned and Frontier Models for Anxiety Detection on Social Media
90c34ed4218f…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
COAL-SQL: Coverage-Guided Augmentation and Failure-Driven Learning for Text-to-SQL Post-Training
8e295c112090…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
TatBLiMP: A Benchmark of Linguistic Minimal Pairs for Tatar
819e60cffc2a…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
Task-Oriented Quantization for Quadratic Scheduling: Centroid Water-Filling and Power-Diagram Encoders
74be0a068717…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
Boosting Deepresearch and LongContext Ability with Self-Generated Deepresearch Rollouts Traces
71d7e20b12b4…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
HERMES: Contrast-Aware Knowledge Graph Reasoning from Clinical Notes for Patient Outcome Prediction
557d45ab5f59…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
Towards Secure Cloud-Native Computing: Unveiling Kubernetes Misconfigurations with Large Language Models
375d434027ab…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
SAGE: Schema-Guided LLMs for Grant Review
30b9bb2d70ab…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
Sparse Priors for Efficient Distribution Learning
2ef187e54ffc…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
From Generation to Detection: Exploration of Discourse Driven Scenario based LLM Generated Fake News
2e55017ff6e7…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
VISPATH: Visual-Intent-Guided Path Reasoning for Multimodal Knowledge Graph Question Answering
1d522a3d7380…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
TALON: A Temporally Aware Longitudinal Framework for Radiology Report Generation
15ce46ac9bf9…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
Enhancing Audio Reasoning via Semantic Summary Prediction
093bc9b64a91…
Source →arXiv PDF ↗Open →
Published 2026-09-21T04:00:00Z
Transsion's Speaker-Attributed Multilingual ASR System for the MLC-SLM 2026 Challenge
0102117da38e…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
Federated Soft Clustering via Generalized Total Variation Minimization
fde4b2457572…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
What Do We Expect from LLMs? Mapping the Design of LLM Benchmarks
f47b4dd5029b…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
Towards Proactive Detection of User-Side Implicit Conflicts in Human-LLM Dialogue
ebcb00fea4e3…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
FakeSpotter: A content and strategy agnostic Viral Misinformation Detection Tool
ea43101d8f34…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
EvoSherlock: Towards Agentic Lifelong Evolution for Unseen Long-Tailed Security-Critical Events in Videos
e2e11ac1764e…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
Making Local Government Contracts Legible: A Computational Pipeline for Classifying and Mapping Intergovernmental Service Agreements
d07c9746cc53…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
VisKG-LM: Compiling Knowledge Graphs into Visual Memory for Multiple-Choice Question Answering
cdf4bb0af47e…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
Advantage Scale Calibration Imbalance in Group-Relative Optimization under Low-Variance Rewards: Diagnosis and Bounded Recovery
c0dc67273073…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
Modality Discrepancy Transformer for Ambivalence and Hesitancy Recognition
b9b54e7d8336…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
Reflective Recovery: A Self-Supervised Method for Reasoning by Learning from Mistakes
a6da21ae9dab…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
Position: It is Time to Virtualize Foundation Models with a Self-evolving Operating System Layer
9df15796ce50…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
Not All Nodes Are Created Equal: Homophily-Aware Stratification for Stable GNN Evaluation
98dedc46cf15…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
Layer-wise Curriculum Learning for Efficient LLM Compression
67095d145a98…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
What Do Current Systematic Generalization Tasks Miss? A Reasoning-Centered Analysis
66af44c56bc2…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
Stop Removing Stopwords: How an Inherited Preprocessing Default Distorts Legal Text-as-Data
658dec8c309f…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
Neo-Classic: A Benchmark for Evaluating Linguistic-Aesthetic Reasoning in Classical Chinese Poetry
64cf517b6e2d…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
What Users Think of Generative AI: A Cross-Platform NLP Analysis of Trust and Friction in App Store Reviews
5edb19cc8c3e…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
Sampling Reveals Style: Unsupervised, Training-Free Discovery of Prompt-Conditional Stylistic Axes in LLM Activations
565767ac51f0…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
Code-as-Auditor: Executable Compliance Reasoning via Regulation-to-Code
55ed710fa1f8…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
To Memories and Beyond: From Remembering to Knowing You across Long-Term Multimodal Personal Archives
53c14e2b12fa…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
Subliminal Prompting Beyond Static Geometry: Causal Depth and Multi-Token Confounds
45732f85949f…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
PAPC: Platform Mediation for Privacy-Propagation Externalities in AI-Mediated Workflows
2f726adc5673…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
BioPhys-Bridge: A Benchmark for Interdisciplinary Scientific Reasoning in Physics-Grounded Biological Research
2b5f47194c88…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
Generative Query Suggestion via Intent Coverage and Query-Level Credit Assignment
2b489fec349f…
Source →arXiv PDF ↗Open →
Published 2026-09-18T04:00:00Z
Regularized Emphatic Temporal-Difference Learning: Stability under Constant Stepsizes
14550e2a3bb4…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
Pay Only for Disagreement: Certified No-Regression Verdicts for Model Updates with Matching Label-Complexity Bounds
fa6cc2b965b2…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
Legal LLM Hallucination Should Be Evaluated as Failure of Legal Warrant
f734c7525954…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
English Word Sense Disambiguation in 2026: When the Labels Become the Bottleneck
f0a2d5504d0f…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
Where Grokking Happens: Distributed Utility and Fourier Recoding Without a Module Switch
d7ffa55599ff…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
Beyond Static RAG: An Adaptive, Tri-Metric Routing Framework for Efficient Long-Context Inference on Commodity GPUs
ce37a6e5b9e8…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
From Pixels to Pairs: A Comprehensive Benchmark of LLM-Based Key-Value Extraction in Noisy Document Settings
cbd0fb9685e2…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
Think Before You Comfort: Reflective Cognitive Alignment for Protocol-Grounded Elderly Stimulation Agents
96cdf7269ed3…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
Does Moral Reasoning Training Help or Hurt? Red-Teaming RL-Trained Ethical Agents with Persona Attacks
8e8b539db4d2…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
How AI Assistants Respond to Repeated Abuse
87df01ab2e80…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback
86814ebbfe53…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
R\'enyi Tracking Bounds for Langevin Dynamics with Moving Targets
849c97c6976f…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
The Limits of BPE Tokenization in Polish: Segmentation-Flexional Forms, Grammatical Anchoring, and First-Person Stability in Inflectional Language Models
830609f7ff10…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
Do Social Patterns Hold in Synthetic Data? Analyzing Cyberbullying Dynamics in LLM-Generated and Authentic Dialogues
81a58d6a4084…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
DANTINOX: A Unified Framework for Multi-Paradigm Language Modeling
7bebe0996106…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
Prior-Free Competitive Ratios for Improving Bandits: Scale, Curvature and Horizon Are Free, but Not Jointly Under Noise
78cecc5761a4…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
Faking Good and Faking Bad in LLMs: Response Distortion Across Dark Triad Personality Traits
719311609dbb…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
MudawanSn: A Gold-Standard Wolof-Arabic Parallel Corpus for Machine Translation
71664d7a8a94…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
Disentangling Algorithmic Bias from Archival Artifacts: A Controlled Audit of Vision-Language Model Valuation in Metropolitan Museum Archives
7031777d4b41…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
Large Language Models Versus Physicians in Traditional Chinese Medicine: A Real-World Clinical Case Evaluation
5ead6855014b…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
Temperon: Full-Time SAM Quality at a Third Less Wall-Clock
55ab83f958e4…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
Myovox: Reading Speech from the Muscles of the Face
537d2b75e8e6…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
Enhancing Extubation Failure Prediction with LLM-Derived Features from Respiratory Therapy Clinical Notes
4a41eaf70269…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
Register Bias in Complexity-Based Large Language Model Routing
389955ded855…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
Relation Before Entity: Deferred Commitment in Language Model Factual Recall
284aadb8d555…
Source →arXiv PDF ↗Open →
Published 2026-09-17T04:00:00Z
When the Gradient Sees Rank: Provable Necessity, Causal Recruitment, and Composition in Trained Matrix Memories
0d4054e6cc60…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Novel Iterative Construction Methods for the Blocking Job Shop Scheduling Problem
f57e88a11a8e…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
State of Thought Enables Endogenous Reasoning
dff2904d85b3…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
The Functionalizer: Lossless Functional Decomposition for Subword Tokenization
cbca5df30f70…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Nepali Legal Expertise through Generative and Extractive Pre-trained Transformers (NepLEGiT)
c7f73d2078bb…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Causal neural set filtering for online multi-target tracking
bca2bdc0bd89…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Using Codebooks to Detect Cybercrime Topics in Text Narratives
b49ff8212717…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Beyond Cultural Knowledge: Evaluating Arabic Cultural Appropriateness of Large Language Models
b374cc94095b…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Are We Grading Properly? Understanding Failure Modes in Medical Benchmarks
ac389103ab00…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Comment on arXiv:2607.01233: Survivorship Bias in Published-Paper Baselines for Research-Idea Distributions
9ec20f5ac75d…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
NepKANUN: A RAG-Based Nepali Legal Assistant
9c7c73ca6773…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents
9c6bae376e1e…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Crash Narrative-Guided Countermeasure Recommendation Using Large Language Models: A Retrieval-Augmented Generation Framework for Intersection Safety
9291a3e24dd1…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Automated Comment Moderation Enhances Social Media Advertising Performance
8f814832b59c…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Optimal Model Activation Policies for Inference Networks of Large Language Models
8ec3b0af0f6d…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Latent Undertow: How Ordinary Typos Break Probes
8c5ae7492813…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Bias Audits Detect Bias but Disagree on Ranking: Evidence from Ten Instruments and Ten Frontier Models
89f6dbe0fe08…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Social Behavior Among Autonomous AI: How Large Language Models Interact in Dynamic Networks
66f6a9ddf6a1…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Single Document Extractive Summarization using Domination in Hypergraph
60e27c95dcdd…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Few-Shot Degradation Is Not What It Seems: Behavioral Evidence, Representation Analysis, and a Random-Text Control Across 12 Models, 2 Tasks, and 2 Architectures
4d1686b7afe0…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Co-Skill: A Collaborative Communication Framework for Skill Evolution
48d84309e814…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
ViCo: Visual-oriented Coding with Self-Reflection for Chart Replication
426b64c5f27a…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Measuring AI harms with multidimensional Lorenz Zonoids
3854f51ab5ec…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Linear Programming Bounds for Locally Recovery Codes II
36fa621d2b44…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Vectorization Of Narrow Matrix Multiplication for Ascend AI Inference Acceleration
2aa08cb70739…
Source →arXiv PDF ↗Open →
Published 2026-09-16T04:00:00Z
Self-reported archetypes and behavioral failures in Large Language Models
1c552103ac59…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Land Art as a Big-Data Climate Sensor
f621a638ac21…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
BudgetBench: A Budget-Tiered Protocol and Pilot Harness for Memory Strategy Evaluation in Local Large Language Model Agents
e665e410a416…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Modeling Quantum Computing with $\pi$-calculus
e3b8df54f6c4…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Discovering and Preserving Category Correlation Knowledge via Adaptive Reciprocal Knowledge Distillation
e1c02f7e16ed…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Machine Unlearning for Speech Question Answering in Large Audio-Language Models
e17e9cdb7462…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
A Lifecycle Cost Analysis of Smart-Contract-Coordinated Federated Learning Marketplaces
de6a6a7a2ff9…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Diagnosing Faults in Reinforcement Learning Simulators and World Models with Canonical Polynomial Invariants
d902a6425e35…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
GradRepair-ODE: Certified Gradient Repair for Neural ODE Training
d72ad3c701b4…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Verification of a Generational Garbage Collector
bdfb714f66ea…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Evaluating LLM-Generated Rules for Heart Disease Prediction
bb3948f08ca6…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Scalable partial information decomposition for symptom networks via supervised embeddings
9f3336f6136e…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Algorithm Validation as a Policy Audit: Evidence from Race-blind Charging
99ae0ab1b075…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
A derivative-fidelity failure mode in physics-informed neural networks: strengthened benchmark evidence from function-value training
90123e3e9e69…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Do Tabular Foundation Models Still Need Feature Engineering?
7dab150dd2ae…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Criticality in Dissimilar Decomposition and Undersampling of Random Datasets with Anomalies
74ef177d21a8…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
PhysMent: An Interactive Approach For LLM Reasoning In Physics Problems
7189377bc745…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
SPICE: Simple Polysemantic Feature Interpretation via Clustering-based Explanation
714c6d7186b6…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
TestHallVQA: Exploring LVLMs' Document-Level Reasoning under Redundant Contexts from Scientific Exams
667bbde957d4…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Self-Indexing Attention for Compression-Compatible Sparse Long-Context LLM Inference
494dcb91184c…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Lexical Prompt Compression for Large Language Models: A Training-Free, Deterministic Pipeline with Empirical Pareto Analysis Across Eleven Task Categories
47f06f21654d…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
LLMs or Naive Bayes? Old Gems or New Ways
4134fe4b45ef…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Algorithmic Information Dynamics of Learning: A Certified, Differentiable Complexity Controller for Grokking
245760aadd24…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Forced volatility: earnings and incentives for gig work in quick commerce
0abde9fd8ea3…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Early Prediction of Satellite Collision Probability Using a Hybrid TCN-Transformer Model for a CDM-Based Conjunction Analysis Framework
08cfd3269fde…
Source →arXiv PDF ↗Open →
Published 2026-09-15T04:00:00Z
Token Merging for Multilingual Speech Recognition: A Systematic Study Across Model Scale and Fine-Tuning
027844a8f00c…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
InitGen: Candidate Generation for Interaction Initiation in Intelligent Assistants
f44e29a44efa…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
Performance, Efficiency and Collapse -- Advantages and Challenges in Offline Post-training of Code LLMs
f33eddb47956…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
Physics-Informed Conformal Prediction: Embedding PDE Consistency into Distribution-Free Uncertainty Quantification for Neural Operators
eef713126f9e…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
A Case-Bundle Operating Model for Coding Agents in OpenFOAM-Based CFD
dc04c5f1cf4f…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
Who Are We Recommending To? Recommender Systems in the Agentic Web
c96e3db57687…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
Asynchronous Parallel Search for Exact Multi-Objective Shortest Paths with Versioned Frontier Snapshots and Indexed Dominance Pruning
c7910d29a840…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
Decoding Mixture Perception through Computational Modeling of Component Interactions
b34dfd7b21e9…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
Efficient AI Model Deployment Using Quantization Analysis Tool
b2e632b2c9ac…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
R2VC: Modular Fact-Checking with Retrieval, Verification, and Confidence Calibration
b2842b947257…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
FINESSE: An Agent-Based Simulator and Benchmark Dataset for Multimodal Financial Event Sequences
affaa503f65b…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work
af377683c6c1…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
Position: Recommender Systems Should Move Beyond Platform-Centric Ranking toward Personal Agent-Mediated Recommendation
98a52690427f…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
Fed-Equilibrium Framework for Topological Pareto Control in Robust and Fair Clinical Federated Learning
8d67d146037b…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
Explainable Prediction from Mobile Sensing Data through LLM-guided Concept Integration
83fcf245992f…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
Hyperion: An AI-powered HPC cluster for sciences and humanities research that utilizes ML for predicting job turnaround time
834ce6f1f8b5…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
MemRetriever: Learning to Search, Reflect, and Retrieve from Long-Term Memory
791e4539a1af…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
A Survey on Quantum-Safe Cryptographic Mechanisms: Building Blocks and Applications
77553730c1d4…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
Assured AI-Native Network Control Loops: State of the Art, Research Challenges and the Missing Runtime Assurance Layer
6c27933818a6…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
Harness or Model? Isolating the Harness Effect in Agentic Coding with a Contamination-Controlled Private Suite
5a4030311ef5…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
PinDCO: Whole-Page Aware Dynamic Creative Optimization at Scale
5849f57072e2…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
ChemMat-AgentSafetyBench: Evaluating Long-Horizon Attacks and Defenses in Chemistry and Materials Agents
1ec925350211…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
Look Before You Leap: Pre-Action Verification for LLM Agents
16da0cfc6cec…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
On-Device Language Models for Privacy-Preserving Stress Prediction: A Multimodal Evaluation on Mobile Health
0f86fb9de25b…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
Fundamental Dynamical Units for Physics-Informed Structural Inference from Perturbation Time-Series in Networked Systems
0829aadfb175…
Source →arXiv PDF ↗Open →
Published 2026-09-14T04:00:00Z
Space as an Interventional Invariant: Cross-Modal Predictive Geometry for Stratified Cities and Em-Spaced Intelligence
07aba4b0a4d9…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
An Empirical Measurement of Jailbreaking Evaluators
edc0a8c766b5…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
Black-Box Membership Inference via Word-Level Probability Estimation
ec1dc35e16a7…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
PEARL: A Task-Aware Framework for Evaluating Differentially Private Synthetic Educational Data
d782e47c0bfe…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
AI Safety: Not Optional, Not Later
d21920ee5877…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
Understanding In-Context Multimodal Jailbreaks via Posterior Reweighting
d133f3c8eaef…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
SoK: Privacy Attacks on Machine Learning via Explainable AI
c4e19ac1dd13…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
When Passing Tests Hides Vulnerabilities: An Empirical Study of Silent Failures in Agentic Systems
b9b048b940e8…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
Halo: Improving forecast accuracy through heteroscedastic estimation
b2fb18015259…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
Optimizing AI Inference Across the Deployment Stack
a5bac7b1bb0e…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
Memory Profiling and Migration for Heterogeneous Memory Architectures
9396e4bb42c9…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
Generative AI for trustworthy systems - Towards a health check model
8be52f4dea99…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
M3-Former: Multimodal Transformer with Mixture-of-Experts for Long-Term Vessel Trajectory Prediction
7fd4082a1748…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
Collective Hysteresis and Multistability in Threshold Networks
7b00761dc9b9…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
Adaptive Diffusion Freezing: Privacy-preserving Diffusion Models Against Membership Inference Attacks
7a270ab71d0d…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
Automating Quadratic Unconstrained Binary Optimization (QUBO) Formulation Generation from Natural Language
79f6344d9d26…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
Certified Panic Mode: Repair-Invariant Error Recovery for Maximal-Munch Lexing
6f3dff5c658f…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
The Internet of Collaborating Things: Agentic Edge AI for Autonomous Cross-Domain Collaboration
675dd0335be1…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
On the Relation between Code Quality and Machine Learning Performance: A Large-scale Empirical Study
6268f8311f4a…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
Probabilistic Focal Search: Accelerating Bounded-Suboptimal Search via Lower-Bound Advancement
5ef3365981a4…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
From Token Interfaces to Token Semantics: A Formal Composition and Conformance Model for Implementation-Neutral Token Specifications
572e753cc1e2…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
MUC-FL: Block-Wise Marginal Utility Contribution for Communication-Efficient Federated Learning
420384783e75…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
From Cycle Space to Cycle Manifold: Limits and Achievability of Blind False Data Injection Attacks
32eb130070b1…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
Design and Operation of a Federated GPU Cluster for Digital Humanities within DHinfra.at
278706f55e22…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
Threshold Choice, Not Sample Size, Bounds Trustless Verification of Nondeterministic Compound AI Workflows
26cf552901ad…
Source →arXiv PDF ↗Open →
Published 2026-09-11T04:00:00Z
ReqEvolve: User-Oriented Software Self-Evolution through Automatic Requirement Interpretation
06d95dd730d9…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
Optimality of Kl{\o}ve Arrays within the Symmetric Kl{\o}ve-Mossige Class
fff197b55062…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
The Double Measurement Confound in Agent Benchmarks: De-Scaffolding, Ground-Truth Scoring, and Reliability Beyond the Mean
ff09bc8a2769…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
X-CoSD: Communication-Efficient Cross-Vocabulary Collaborative Speculative Decoding
fac6fc61daec…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
A Subsampled Davis-Kahan Bound for Large-Scale Eigenspace Estimation
f64d745e0540…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
Critical initialization destabilizes higher input derivatives in wide scalar-input networks
f53387867111…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
AgentHijack: Visual Patch Attacks on Multimodal Computer-Use Agents
eb9a6fecdb50…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
OASIS: A Rubric-Based Multimodal Assessment Platform Using Large Language Models
d54dc937f184…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts
c0addc6555af…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
SMCC-Empowered Digital Twins for Sensorless Monitoring in Large-Scale AI-Driven IoT Systems
b9d6b3d98934…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
Cost-Aware Post-Hoc Deferral Under Calibration and Shift: An Environmental AI Case Study
af31e0acdf9a…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
Evaluating Enterprise Analytics Agents: An End-to-End, Trace-Backed Methodology
abbe059723f3…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
Spectral origin of the topological gap exponent d + {\eta}: mechanism, kernel, decomposition, and scope
a5f933e4589c…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
HELIOS: Guardrailed LLM-Driven Evolution of Autonomous Resource Orchestration Policies for Multi-Cloud Distributed Systems
8c77128d2b37…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
OpenDiscoveryTrace: Process Traces for Evaluating AI Scientist Workflows
88fd0ea1a1d6…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
Compute-Bounded Security Assurance - Coverage, Verification, and Response under Resource Constraints
6c159a44656c…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
TFR-GNN: Topology- and Fault-Aware Graph Neural Scheduling for Heterogeneous Distributed Computing Systems
668a5330c16d…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
Adaptive Entangled Game Modules in Artificial General Intelligence
652a0308279b…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
LBFAST: A Lightweight Moment-Represented Lattice Boltzmann Solver for Multi-GPU Architectures
62dc07574fbb…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks
573b73210902…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
Stability of Fork-Join Systems with Redundancy and Heterogeneous Servers
48530dfdbee3…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
World-Time Compute with Verified Code World Models
39430751af1d…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
Physics-informed neural networks by Gradient-Guided Gaussian Adaptive Sampling (3GAS-PINNs)
13fecbc0379d…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
Scaling Post-Training Ternarisation to Qwen3-8B Capability Retention, Reproduction, Lossless Packing, and Packed Execution
12eb7d96b756…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning
0d198ecf072f…
Source →arXiv PDF ↗Open →
Published 2026-09-10T04:00:00Z
Talking to Itself While Coding: What Makes Comments Help Code Generation?
0471b96ab15a…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
SAGE: Semantic Attribute Graphs for Multi-Entity Visual Retrieval
f98a2de26b99…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
How Much Does Corpus Choice Change Dependency-Distance Estimates?
f646e0560d66…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
Reviewer Capability Governs Rejection Targeting, Not Repair Skill: Evidence from LLM Execute-Review-Revise Pipelines
f4bbe96dd5e6…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
Engineering as Code: Bringing Software Engineering Methodology to Engineering Design
ebf98330fe07…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
A Data Fusion Framework for Grounding Aerospace Surrogate Model via Experimental Wind-Tunnel Observations
e4edd2766973…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
SH-PDOPS: AI-Driven Cloud Native Enterprise Reliability Framework for Predictive Analytics and Intelligent DevOps Automation
de01c75060d3…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
Toward Model-Driven Digital Twin Configuration: Separating Structure Semantics and Runtime with SysML SAREF and Ditto
d54b42008ca0…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
Large Language Models for Fuzz Testing in Microservices: A Systematic Literature Review
d4b4e69c7ba8…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
Evaluating Large Language Models for Forced Outage Risk Prediction: Benefits and Comparison to Machine Learning
d22684fb5422…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
DTM: Deterministic Approaches for Black-box Test Suite Minimization with Tree-based Similarity
d0bd7cadde3f…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
Physics-Direct FPGA Tooth-Contact Computation for Deterministic Gear Digital Twins
b03fbc05e8d2…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
Breaking the Alphabet: Rethinking File Ordering in Code Review
a579ecc077c7…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
Spectral-Target Physical Latent Structuring for JEPA-Style World Models
8341bd7eb3f2…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
Data-Related Challenges and Requirements for Event Log Generation in Process Mining: A Systematic Literature Review
7216ae5158bf…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
A Governance Methodology Layer for AI-Assisted Software Development: Defect Taxonomy, Controlled Ablation, and Process-Over-Capability Evidence
4cefbdd0a9d4…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
Robustness and Trade-offs for Code LLMs on Protected Code
475105dc8017…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
Big Questions on Software Architecture: Report of the ICSE 2026 BoF on Software Architecture
3e32db61a7f2…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
ProToMEx: Rapid, Interpretable Explanations via Structured Representations
36fd49995c60…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
AI Writes Code, Humans Pay the Debt. An Empirical Study on the Sustainability and Evolution of Agent-Generated Code
2a26f7f8dd10…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
Automated Deployment of Real-Time Tasks for Phased Execution on Scratchpad-Based Multicore Platforms
1a7434aabb57…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
A Mixed-Method Empirical Study of LLM Assistance in Software Engineering Workflows
152b06eb92df…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
A systematic literature review on logging smell detection
135b51205abb…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
EXAONE Forecast for Finance
10ad9a176d44…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
The Prompt Triangle: A Registered Report on Prompts as Hybrid Artifacts
0ec0f4de470f…
Source →arXiv PDF ↗Open →
Published 2026-09-07T04:00:00Z
Quantum-Assisted Memory-Efficient Training for Parameter-Intensive Wi-Fi-Based Human Activity Recognition
046a9bd4ff9d…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
CHSR-RRF: A curriculum-gated hybrid retrieval framework with reciprocal rank fusion and leakage-aware benchmarking for educational RAG
f4094f1d60a3…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
Bounded Personas Match Retrieval on Classification but Not Regression for a Frozen Agent
ee0644e6b393…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
Probe Generalization as Subspace Selection for OOD Deception Detection
e77493a1c9e0…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
Dual-Form ASR: Semantics-Aware Inverse Text Normalization for Chinese Speech Recognition
dfb0f960f502…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
Counterexamples as Feedback for Agent Self-Correction
da66a7ac4813…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
The Illusion of Independent Quorums: Epistemic Fault Domains and Correlated Cognitive Failures in Agentic Quorums
cd6d585a3379…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
PrivateHub: Contrastive Diffusion Model for Private Sensor-Intensive Environment Data Generation
cb80d4cb887e…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
Reflect-SQL: A Self-Reflection Based Framework for Text-to-SQL
ca8c34e6a8a8…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
The Geometry of Ignorance: LLMs Know When to Temper Bayesian Priors
c6c7e766d672…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
Evaluating GNNs for Success Prediction in Artist Collaboration Networks
b85ec686b34c…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
LexIssue: Benchmarking Legal Issue Identification in Chinese Civil Litigation
b1850a1d8ae1…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
BharatGather: A Culturally-Informed Benchmark Dataset for Misinformation and Fake News Detection in Indian Public Events
a9d0a71cd3c0…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
R$^{2}$Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG
9e8af7016f4f…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
Judging LLM-as-a-Judge: Concerning Rubric Artifacts in LLM-based Automated Text Generation Evaluation
9958291cc7ea…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions
8d59a0bf168b…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
Privacy-Preserving Heterogeneous Multi-LLM Federated Inference for Cognitive Diagnosis
8c6f5692aba2…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
RL-ADA: A World-Feedback Framework for Adversarially Robust Enterprise Dialogue Agents
7a0813e8a987…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
Distilled Rapid Embedding Transfer (DRET): Parameter-Efficient Biomedical Domain Adaptation via Priority-Based Embedding Transfer
7979823b91db…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
A Public-Key-Dependent Adversarial-Deletion Ceiling for Fixed-Alphabet Multi-Bit Pseudorandom Codes
649b38adb750…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
PiPMRE: A Pipeline Based on Language Model for Medical Relation Extraction
60b45020a083…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
When Optimization Becomes Manipulation: Defending Generative Search against Malicious Generative Engine Optimization
531342e0f510…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
Direct Satellite-to-Device Communications: From Cooperative Task Offloading to Non-Cooperative Access Monitoring
39602259933f…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
Margins, Not Windows: Training-Free Per-Step Lossy Speculative Decoding
344bde608a35…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
Contamination Inflates Scores but Rarely Reorders Large Language Model Leaderboards
06b7a1792bcf…
Source →arXiv PDF ↗Open →
Published 2026-09-04T04:00:00Z
Where Does Harness-Optimization Value Live? Localized Gains and the Budget-Splitting Trap in Self-Evolving LLM Agents
01b09ae152fe…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
Incident Memory: Training-Free Operational Memory through Sequential Pattern Mining and Velocity-Stratified Retrieval
facfce367e7f…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
Whose Judgments Count? Representation Gaps in Crowdsourced Content Moderation Produce Unequal Protection from Perceived Toxicity
fa8dd4371ad8…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
When Literature Data Mislead Artificial Intelligence in Materials Discovery
f34be8b5925b…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
Discretization-free exact recovery in geometric community detection
c6431754e037…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
Prompt-Space Meta-Learning Does Not Transfer Across Users: A Frozen-LLM Negative Result
b84baa071026…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
SocialBuddy: Tailoring Search Agent for Social Scenarios
b7465efa8289…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
Marginal Expected Revenue for Jointly Ranking Auction and Fixed-Price Listings in E-Commerce Sponsored Search
b4a7c5c2ce91…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
The Utility of LLMs in Recommender Systems Explanation Evaluation
ae84f7da8efb…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
DiDrive: A Risk-Aware Hierarchical Diffusion Framework for Safe Offline Reinforcement Learning in Autonomous Driving
a9b0dc5aa3bd…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
MESSY STREETS: A Benchmark for Geocoding Real-World Addresses
9cf6570d357e…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
RecEvolve: A Knowledge-Driven Autonomous Agent System for Recommender Systems
985153236405…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
Multi-Agent Retrieval-Augmented Generation for Efficient Cloud Knowledge Base Search in Telecom SNOC Environment
91efcdf29689…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
Graph Neural Team Recommendation: An Integrated Approach
7df3cf3fcf8f…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
Omega-N: Interpretable Structural Node Descriptors and Their Applicability Domain
655d32fc8764…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
A Novel Information Workflow for Structural Behavioural Analysis in Dynamic Attributed Graphs
41412cc909c7…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
Higher-order rich clubs and configuration models on general directed hypergraphs
3ee05f5c215e…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
Skim and Skip: Hierarchical Adaptive Inference for Efficient Multimodal Retrieval
2ffa8b149033…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
MGDiff: Multi-Interest Sequence Recommendation with Masking GNN-Guided Diffusion
2fbe63e0ed4b…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
The Vocabulary Gap Is an Equity Gap: Register Mismatch in Retrieval Systems for Public-Benefits Access
2a01b9e1dd0c…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models
27491f64d11f…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modeling
1dfc3c65c7ff…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
Imagine Before Retrieval: Prospective Skill Retrieval for LLM Agents
1adb4ac44034…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
GRAND-HC: Graph-Refined Author Name Disambiguation
1751aeb9697d…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
Making Revisions Understandable: A Survey of Edit Intentions, Methods, and Applications
12e094d07224…
Source →arXiv PDF ↗Open →
Published 2026-09-03T04:00:00Z
Hybrid Retrieval-Augmented Generation with Knowledge Graph Expansion, RRF Fusion, and Per-Chunk Grounded Evaluation for Enterprise Document Search
0d2741619bee…
Source →arXiv PDF ↗Open →
Published 2026-09-02T17:59:46Z
A Common Measure of Communication for Speech Brain-Computer Interfaces
ac9501b70066…
Source →arXiv PDF ↗Open →
Published 2026-09-02T17:59:40Z
Discriminative World Models for Web Agents
b32d8f0a988d…
Source →arXiv PDF ↗Open →
Published 2026-09-02T17:56:41Z
Graph Machine: Towards Better Pretraining via Edges
c24f3cf9640c…
Source →arXiv PDF ↗Open →
Published 2026-09-02T17:56:39Z
Overcoming the Randomness-Utility Trade-off in Answering Differentially Private Linear Queries
3955eb888028…
Source →arXiv PDF ↗Open →
Published 2026-09-02T17:56:10Z
GRADSOLVE: fast exact gradients for ODE ensembles on GPUs
af3dedd99d11…
Source →arXiv PDF ↗Open →
Published 2026-09-02T17:54:57Z
Causal Probabilistic Programming via Magmadic Do-Notation
c6d65b0bf237…
Source →arXiv PDF ↗Open →
Published 2026-09-02T17:50:39Z
When Does Authorization End? Effect Closure at Provider Boundaries
28e9c28fedb9…
Source →arXiv PDF ↗Open →
Published 2026-09-02T17:44:25Z
Towards Trustworthy Autonomous Robots: An Explainable AI-Based Decision Framework
0c847efede75…
Source →arXiv PDF ↗Open →
Published 2026-09-02T17:42:44Z
User Feedback Provides a Unique Signal that LLMs Can not Detect
4750b004d1dd…
Source →arXiv PDF ↗Open →
Published 2026-09-02T17:39:52Z
Improved Gradient Descent Lower Bounds Beyond Nesterov
d322c35e44c8…
Source →arXiv PDF ↗Open →
Published 2026-09-02T17:37:22Z
The Implications of Linguistic Illegibility for LLM Security
f7ea74c65172…
Source →arXiv PDF ↗Open →
Published 2026-09-02T17:33:37Z
Post-Training Language Models for Gold-Medal Performance in Coding Competitions
a489308c811a…
Source →arXiv PDF ↗Open →
Published 2026-09-02T17:32:07Z
UE5M3 FP4 Block Scaling for Stable Language Model Pretraining
f749d914d7fd…
Source →arXiv PDF ↗Open →
Published 2026-09-02T17:16:16Z
Learning Spectral-Like Mesh-Free Discretisations
40bb658711f6…
Source →arXiv PDF ↗Open →
Published 2026-09-02T17:15:48Z
Copula Transformations for Data-Consistent Inversion
46bdcd3cf91c…
Source →arXiv PDF ↗Open →
Published 2026-09-02T17:09:30Z
AI Contextual Measurement for Recovering Individual and Group-Level Effects: Validation Against Survey Measures and an Occupational Application
0c60b71198d3…
Source →arXiv PDF ↗Open →
Published 2026-07-25T16:45:00Z
Adaptive Graph-of-Islands Evolution for Automatic Feature Engineering with LLMs
1cd5db79dd50…
Source →arXiv PDF ↗Open →
Published 2026-07-14T13:44:20Z
Aletheia: An Offline-First Clinical Decision Support System for Differential Diagnosis in Low-Resource Healthcare Settings
611d215969b2…
Source →arXiv PDF ↗Open →
Published 2026-06-01T14:57:27Z
Are Algorithm Registers Transparent? Perspectives from Germany
378e3ca2e9bc…
Source →arXiv PDF ↗Open →
Published 2026-04-21T04:59:09Z
MUCOCO: Automated Consistency Testing of Code LLMs
7a510ede2726…
Source →arXiv PDF ↗Open →
Published 2026-04-16T00:30:45Z
On the Expressive Power and Limitations of Multi-Layer SSMs
17c254cba734…
Source →arXiv PDF ↗Open →
Published 2026-03-17T17:54:08Z
Mediocrity is the key for LLM as a Judge Anchor Selection
708c505e1965…
Source →arXiv PDF ↗Open →
Published 2026-01-29T22:18:04Z
Towards Solving the Gilbert-Pollak Conjecture via Large Language Models
8f919e8a9357…
Source →arXiv PDF ↗Open →
Published 2025-10-08T16:16:46Z
CARPAS: Towards Content-Aware Refinement of Provided Aspects for Summarization in Large Language Models
f6170eedd539…
Source →arXiv PDF ↗Open →
Published 2025-10-05T01:08:39Z
Toward Uncertainty-Aware and Generalizable Neural Decoding for Quantum LDPC Codes
486bb413726a…
Source →arXiv PDF ↗Open →