Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
When Rewards Disagree: Reward Weighting for Token-Efficient Video Reasoning
Zinuo Li, Yongxin Guo, Jun Liu +7
Human perception interprets video dynamics by constructing structured mental representations of entities, actions, and temporal boundaries before engaging in high-level reasoning.…
cs.CL2025
Watch and Listen: Understanding Audio-Visual-Speech Moments with Multimodal LLM
Zinuo Li, Xian Zhang, Yongxin Guo +5
Humans naturally understand moments in a video by integrating visual and auditory cues. For example, localizing a scene in the video like "A scientist passionately speaks on wildli…