Xiu Li

6 papers Bytedance

• ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning
• Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials
• MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO
• Puppeteer: Rig and Animate Your 3D Models
• Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective
• SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning