Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
CARE: Contrastive Alignment for ADL Recognition from Event-Triggered Sensor Streams
Junhao Zhao, Zishuai Liu, Ruili Fang +3
The recognition of Activities of Daily Living (ADLs) from event-triggered ambient sensors is an essential task in Ambient Assisted Living, yet existing methods remain constrained b…
cs.CV2026
Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization
Jinghan Li, Junfeng Fang, Jinda Lu +5
Reinforcement Learning with Verifiable Rewards (RLVR) and Group Relative Policy Optimization (GRPO) have significantly advanced the reasoning capabilities of large language models.…
cs.CV2026
LARV: Data-Free Layer-wise Adaptive Rescaling Veneer for Model Merging
Xinyu Wang, Ke Deng, Fei Dou +2
Model merging aims to combine multiple fine-tuned models into a single multi-task model without access to training data. Existing task-vector merging methods such as TIES, TSV-M, a…