Zhongyuan Wang

From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance

Robobench: A Comprehensive Evaluation Benchmark For Multimodal Large Language Models as Embodied Brain

Rethinking Supervised Fine-Tuning: Emphasizing Key Answer Tokens for Improved LLM Accuracy

RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics

Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models

AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation