arxiv:2512.21815
zhaoyuan yang
zhaoyuan
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 months ago
All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Models authored a paper 4 months ago
Few Tokens Matter: Entropy Guided Attacks on Vision-Language Models upvoted a paper 8 months ago
More Thought, Less Accuracy? On the Dual Nature of Reasoning in
Vision-Language ModelsOrganizations
None yet
