-
Token-Efficient Long Video Understanding for Multimodal LLMs
Paper • 2503.04130 • Published • 96 -
Temporal Preference Optimization for Long-Form Video Understanding
Paper • 2501.13919 • Published • 23 -
MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning
Paper • 2503.07365 • Published • 61
Zhang Yuanhan
ZhangYuanhan
AI & ML interests
None yet
Recent Activity
upvoted a paper 16 days ago
RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System upvoted a paper 16 days ago
Demystifing Video Reasoning upvoted a paper about 1 month ago
UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?Organizations
-
Token-Efficient Long Video Understanding for Multimodal LLMs
Paper • 2503.04130 • Published • 96 -
Temporal Preference Optimization for Long-Form Video Understanding
Paper • 2501.13919 • Published • 23 -
MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning
Paper • 2503.07365 • Published • 61
