4 papers · 1 filter
Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution
Bingjun Luo, Jialin Guo, Siqi Li
Video understanding agents acquire evidence through an executable harness that controls what they observe and how they use those observations. However, execution traces contain onl…
SkillTrace: Traversing a Query-Skill Graph for Composable LLM Agents
Yue Yao, Shengyuan Wang, Xin Chen +4
Large language model agents increasingly solve complex tasks by composing reusable skills from a library. To address this, the key challenge is not merely to retrieve individually…
ST-SimDiff: Balancing Spatiotemporal Similarity and Difference for Efficient Video Understanding with MLLMs
Bingjun Luo, Tony Wang, Chaoqi Chen +1
Multimodal Large Language Models (MLLMs) face significant computational overhead when processing long videos due to the massive number of visual tokens required. To improve efficie…
Enhancing Visual Token Representations for Video Large Language Models via Training-Free Spatial-Temporal Pooling and Gridding
Bingjun Luo, Tony Wang, Hanqi Chen +1
Recent advances in Multimodal Large Language Models (MLLMs) have significantly advanced video understanding tasks, yet challenges remain in efficiently compressing visual tokens wh…