AI.info

Di Zhang

Explore Di Zhang on AI.info.

• HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone
• LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
• PhysInOne: Visual Physics Learning and Reasoning in One Suite
• Learning Native Continuation for Action Chunking Flow Policies
• FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion
• Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs
• VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models