7 papers
Reinforcement Learning-driven Diffusion Models: Language, Vision, and Beyond
Zhiyuan Ma, Jiabao Wei, Tianyu Wang +21
Diffusion models (DMs) have steadily demonstrated outstanding performance in high-fidelity, controllable generation across diverse scenarios, following the "pretraining-finetuning"…
Unified Trajectory Matching Policy Optimization: Diverse T2I Generation and VLA Generalization
Zhiyuan Ma, Jiaming Li, Lingzhen Li +7
Reward-maximizing reinforcement learning (RL) is widely used to post-train stochastic diffusion and flow policies for text-to-image (T2I) generation. However, reward-maximizing RL…
DeltaV: Thinking with Visual State Updates in Unified Large Multimodal Models
Pengjie Wang, Linger Deng, Zujia Zhang +6
Current Unified Large Multimodal Models (ULMMs) support interleaved multimodal reasoning through textual reasoning and intermediate visual states, but typically generate each visua…
Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously
Yiran Guan, Liang Yin, Dingkang Liang +5
Online Video Large Language Models (VideoLLMs) play a critical role in supporting responsive, real-time interaction. Existing methods focus on streaming perception, lacking a synch…
GeoFocus: Blending Efficient Global-to-Local Perception for Multimodal Geometry Problem-Solving
Linger Deng, Yuliang Liu, Wenwen Yu +4
Geometry problem-solving remains a significant challenge for Large Multimodal Models (LMMs), requiring not only global shape recognition but also attention to intricate local relat…
DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document Understanding
Wenwen Yu, Zhibo Yang, Yuliang Liu +1
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in document understanding. However, their reasoning processes remain largely black-box, making it…
Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle
Linghao Zhu, Yiran Guan, Dingkang Liang +6
Reinforcement learning (RL) has emerged as an effective post-training paradigm for enhancing the reasoning capabilities of multimodal large language model (MLLM). However, current…