5 citations · 5 across the 8 of their papers we have counts for
Showing 2026 · cs.CVShow all
3 papers · 2 filters
cs.CV2026
DynamicDx: Evaluating Evidence Acquisition in Video-Based Diagnosis
Jiahui Li, Yutong Guo, Nan Yang +3
Diagnosing a patient from video requires more than recognizing the sign: a vision-language model must turn what it sees into hypotheses, questions and tests. DynamicDx evaluates ea…
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…