Yucheng Hu

Hi! I am a 2th-year PhD student in Computer Science at Tsinghua University, advised by Prof. Jianyu Chen. I received my bachelor's degree in EE also from Tsinghua University in 2024 . I have previously interned at Seed-Robotics, Robotera, and Shanghai AI Laboratory.

My research focuses on embodied foundation models and generative models , aiming to maximize data utilization toward general-purpose embodied intelligence. To this end, My work includes World Action Model[7,9], UAM (Unified Action Model)[10,14,15] and VLA[3,6,8,13] Model.

Besides research, I enjoy playing video games and traveling. I'm currently preparing to launch a startup. Anyone interested in embodied intelligence is welcome to get in touch with us.

My email: h790762279@gmail.com

Phone and WeChat: 17347316224

Email / Scholar / Github

Selected Research (* indicates equal contribution)

World Action Model:

[9] Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations
Yucheng Hu*, Yanjiang Guo*, Pengchao Wang, Xiaoyu Chen, Yen-Jen Wang, Jianke Zhang, Koushil Sreenath, Chaochao Lu, Jianyu Chen
International Conference on Machine Learning (ICML), 2025 (Spotlight, 2.6%)
project page / code / arXiv / twitter / 机器之心 / 量子位

We finetune a general-purpose video diffusion model into manipulation-focused video prediction model to guide policy learning. VPP was the earliest WAM work.

[7] Prediction with Action: Visual Policy Learning via Joint Denoising Process
Yanjiang Guo*, Yucheng Hu*, Jianke Zhang, Yen-Jen Wang, Xiaoyu Chen, Chaochao Lu, Jianyu Chen
Advances in Neural Information Processing Systems (NeurIPS), 2024
project page / code / arXiv

We jointly predict future images and robot actions in a unified DiT network, transfering physical knowledge from internet video data to robots.

Unified Action Models:

	[14] BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation Yucheng Hu, Jianke Zhang, Yuanfei Luo, Yanjiang Guo, Xiaoyu Chen, Xinshu Sun, Kun Feng, Qingzhou Lu, Sheng Chen, Yangang Zhang, Wei Li, Jianyu Chen Robotics: Science and Systems (RSS), 2026* project page / arXiv We propose a unified VLA framework that integrates understanding, prediction, and execution.
	[15] UniCoD: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning Jianke Zhang, Yucheng Hu, Yanjiang Guo, Xiaoyu Chen, Yichen Liu, Wenna Chen, Chaochao Lu, Jianyu Chen International Conference on Machine Learning (ICML), 2026 arXiv We introduced JEPA into VLA.
	[10] UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent Jianke Zhang, Yanjiang Guo, Yucheng Hu, Xiaoyu Chen, Jianyu Chen International Conference on Machine Learning (ICML), 2025* arXiv / code We incoperate both multi-modal understanding (MMU) and future prediction into VLA model, enhancing both high-level semantic knowledge and low-level visual dynamics.

Other Paper:

	[13] VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models Jianke Zhang, Xiaoyu Chen, Yanjiang Guo, Yucheng Hu, Jianyu Chen International Conference on Learning Representations (ICLR), 2026 project page / arXiv / code We systematically evaluate how the base VLM affect the performance of VLA.
	[8] Improving Vision-Language-Action Model with Online Reinforcement Learning Yanjiang Guo, Jianke Zhang, Xiaoyu Chen, Xiang Ji, Yen-Jen Wang, Yucheng Hu, Jianyu Chen International Conference on Robotics and Automation (ICRA), 2025* arXiv / twitter1 / twitter2 We make some initial exploration on leveraging online RL to improve the VLA model! We notice that online RL for VLA can be extremely unstable and thus we adopted a iterative approach.
	[6] HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers Jianke Zhang, Yanjiang Guo, Xiaoyu Chen, Yen-Jen Wang, Yucheng Hu, Chengming Shi, Jianyu Chen Conference on Robot Learning (CoRL), 2024 arXiv / twitter / 机器之心 We finetune pretrained VLM into VLA models with hierarchical transformers, keeping the generalization ability but also much higher control frequency.
	[3] Robix: A Unified Model for Robot Interaction, Reasoning and Planning Huang Fang, Mengxi Zhang, Heng Dong, Wei Li, Zixuan Wang, Qifeng Zhang, Xueyun Tian, Yucheng Hu, Hang Li arXiv, 2025 arXiv / project page We introduce Robix, a unified model that integrates robot reasoning, task planning, and natural language interaction within a single vision-language architecture.

Source code from Jon Barron.