AI.info

Xiangxiang Chu

Explore Xiangxiang Chu on AI.info.

• R2M-Bench: Evaluating Revisit Memory via Relative Consistency in Interactive Video World Models
• DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation
• Visually-Guided Policy Optimization for Multimodal Reasoning
• Code2World: A GUI World Model via Renderable Code Generation
• FASA: Frequency-aware Sparse Attention
• Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models
• Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
• Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning
• MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation
• Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context Learning