5 papers
Looped World Models
Hongyuan Adam Lu, Z. L. Victor Wei, Qun Zhang +28
Current world models face a fundamental tension: faithful long-horizon simulation demands deep computation, but deeper models are expensive to deploy and prone to compounding error…
See More, Think Deeper: Query-Expanded Visual Evidence and Answer-Clue Guided Reflection for Long Video Understanding
Shuning Wang, Zhiheng Wu, YiNuo Lu +6
Recent advances in Video Large Language Models (Video-LLMs) have enabled performance on long-video understanding tasks. However, existing methods still face two key limitations: ev…
Distribution Corrected Offline Data Distillation for Large Language Models
Yumeng Zhang, Zhengbang Yang, Yevin Nikhel Goonatilake +1
Distilling reasoning traces from strong large language models into smaller ones is a promising route to improve intelligence in resource-constrained settings. Existing approaches f…
See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection
Zhiheng Wu, Tong Wang, Shuning Wang +2
Recent advances in Vision-Language Models (VLMs) have benefited from Reinforcement Learning (RL) for enhanced reasoning. However, existing methods still face critical limitations,…
Decoupling Strategy and Execution in Task-Focused Dialogue via Goal-Oriented Preference Optimization
Jingyi Xu, Xingyu Ren, Zhoupeng Shou +2
Large language models show potential in task-oriented dialogue systems, yet existing training methods often rely on token-level likelihood or preference optimization, which poorly…