Picture for Zhiding Yu

Zhiding Yu

GR00T N1: An Open Foundation Model for Generalist Humanoid Robots

Add code
Mar 18, 2025
Viaarxiv icon

Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillation

Add code
Mar 17, 2025
Viaarxiv icon

Hydra-NeXt: Robust Closed-Loop Driving with Open-Loop Training

Add code
Mar 15, 2025
Viaarxiv icon

Centaur: Robust End-to-End Autonomous Driving with Test-Time Training

Add code
Mar 14, 2025
Viaarxiv icon

Token-Efficient Long Video Understanding for Multimodal LLMs

Add code
Mar 06, 2025
Viaarxiv icon

Enhancing Autonomous Driving Safety with Collision Scenario Integration

Add code
Mar 05, 2025
Viaarxiv icon

RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression

Add code
Feb 19, 2025
Viaarxiv icon

AIDE: Agentically Improve Visual Language Model with Domain Experts

Add code
Feb 13, 2025
Viaarxiv icon

QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation

Add code
Feb 07, 2025
Viaarxiv icon

StreamChat: Chatting with Streaming Video

Add code
Dec 11, 2024
Viaarxiv icon