3 papers
cs.CV2026
Contamination, Prior, or Evidence? Decomposing and Training Evidence Use in Whole-Slide Vision-Language Models
Wenhao Zhang, Zhongliang Zhou, Shiyuan Zhang +6
Pathology vision-language models (VLMs) are conventionally evaluated by accuracy, but accuracy alone does not measure evidence use: it may conflate dataset contamination, prior kno…
cs.CL2026
Finding the Cracks: Improving LLMs Reasoning with Paraphrastic Probing and Consistency Verification
Weili Shi, Dongliang Guo, Lehan Yang +3
Large language models have demonstrated impressive performance across a variety of reasoning tasks. However, their problem-solving ability often declines on more complex tasks due…
cs.CV2025
HFS: Holistic Query-Aware Frame Selection for Efficient Video Understanding
Yiqing Yang, Yun Li, Daiqing Qi +5
Key frame selection is essentially a set-level optimization problem: the quality of the selected subset depends on the interactions among frames, rather than the score of any singl…