Beyond the Flat-Spike: Adaptive Sparse CCA for Decaying and Unbalanced Signals
2026-04-21T08:51:39Z•335972aa43fcfb6720a5eef760cefe5d085affff014abdaa1e64f8fe7b78faf5
6GECGGRANDKV-cache-compression','LLM-memory-compressionUAVarXivbeam-trackingbiomedical-MLcontactless-sensingerror-correcting-codesknowledge-distillationmachine-learningmedical-devicesmmWaveprivacyradarreinforcement-learningsafety-critical-systemssemantic-communicationssensor-fusionsignal-processingsleep-trackingsparse-CCAunderwater-communicationswireless-communications
What happened
Batch of newly announced arXiv papers (signal processing / communications / ML) covering: adaptive sparse CCA for structured high-dimensional signals (Bi-SEP); the impact of ECG sampling frequency on deep-learning AF detection; a contactless radar-based sleep tracker (Sleepal AI Lamp) with high agreement to PSG; knowledge-distillation for lightweight multimodal (camera+radar) mmWave beam tracking; a universal method to generate error patterns for decoding on memoryless channels; graph-guided KV-cache channel pruning for LLM long-context compression (GRACE); a Safe-Deep Q-Learning framework for
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- arxiv_eess_sp
- Record identifier
- 335972aa43fcfb6720a5eef760cefe5d085affff014abdaa1e64f8fe7b78faf5
- Enrichment time
- 2026-04-21T08:51:39Z
- AI-assisted enrichment
- Yes
This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.