20 papers
Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs
Yunheng Li, Guohong Mu, Hao Li +4
Multimodal large language models (MLLMs) have become a prevailing paradigm for unified video perception. However, post-training on large multi-task datasets remains challenging, as…
GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation
Yuhao Wan, Lijuan Liu, Jingzhi Zhou +6
Previous works that leverage video models for image-to-3D scene generation often suffer from geometric distortions and blurry content. Using video generation models to implicitly m…
Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought
Yunheng Li, Hangyi Kuang, Hengrui Zhang +4
Multimodal Chain-of-Thought (CoT) reasoning requires large vision-language models to construct reasoning trajectories that interleave perceptual grounding with multi-step inference…
Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions
Yunheng Li, Hengrui Zhang, Meng-Hao Guo +5
Universal video understanding requires modeling fine-grained visual and audio information over time in diverse real-world scenarios. However, the performance of existing models is…
GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics
Modi Jin, Yiming Zhang, Boyuan Sun +3
This paper presents GeoAgent, a model capable of reasoning closely with humans and deriving fine-grained address conclusions. Previous RL-based methods have achieved breakthroughs…
Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction
Yunheng Li, Yuxuan Li, Quansheng Zeng +3
Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot recognition capability, but still underperform in dense prediction tasks. Self-disti…