5 papers
MaskSense: Confronting the Visual Exploration Trap in Masked Image Generation
Yawen Shao, Jie Xiao, Kai Zhu +6
Reinforcement learning (RL) has shown strong potential for aligning generative models with human intent, but adapting RL to masked generative models (MGMs) remains largely underexp…
Code Plans, Diffusion Renders: Open-Ended Generative World Modeling
Zixun Fang, Yawen Shao, Kai Zhu +7
We introduce \textbf{CoDeR}, a new paradigm for world modeling. Unlike existing video world models that implicitly represent world dynamics through visual observations, our system…
Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models
Yawen Shao, Jie Xiao, Kai Zhu +6
Reinforcement learning (RL) holds immense promise for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, progress is fundamentally constraine…
Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment
Yawen Shao, Jie Xiao, Kai Zhu +4
Group Relative Policy Optimization (GRPO) has proven highly effective in enhancing the alignment capabilities of Large Language Models (LLMs). However, current adaptations of GRPO…
GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding
Yawen Shao, Wei Zhai, Yuhang Yang +3
Open-Vocabulary 3D object affordance grounding aims to anticipate ``action possibilities'' regions on 3D objects with arbitrary instructions, which is crucial for robots to generic…