Shihao Wang

Latest

• PhyCritic: Multimodal Critic Models for Physical AI
• VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding
• Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models
• Hydra-NeXt: Robust Closed-Loop Driving with Open-Loop Training
• OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counter Factual Reasoning
• Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders
• Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation