TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning

2026-05-04T08:51:40Z8fcbe50ec6ff9591aa6c077c8019dfacf64cc6fcc5f151866dababa7d9666ec9
6GMIMObeamformingfoundation-modelslocation-spoofingmedical-device-safetymicrowave-hyperthermiamodel-robustnessprivacyradar-modelsspoofingtime-series-forecastingwireless-physical-layer

What happened

This collection of arXiv papers highlights several advances with security and safety implications across wireless, radar, ML, and medical-device contexts. Most notable is a proof-of-concept blind angular-spoofing method for uplink MIMO that uses a blind analog precoder to manipulate perceived angle-of-arrival/departure (near-perfect spoofing achievable without channel-gain knowledge), trading off communication rate—direct relevance to location-privacy attacks and spoofing defenses. Related wireless/PHY work includes proposals to adopt chirp-based subcarriers for 6G (improving Doppler/ISACrob-

Why it matters

A reviewed impact interpretation has not been published for this record.

Evidence and limitations

Source ID
arxiv_eess_sp
Record identifier
8fcbe50ec6ff9591aa6c077c8019dfacf64cc6fcc5f151866dababa7d9666ec9
Enrichment time
2026-05-04T08:51:40Z
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.