4 citations · 7 across the 22 of their papers we have counts for
24 papers
Video Prediction Policy 2: Predict Better, Act Better
Yanjiang Guo, Haodong Yan, Zhide Zhong +15
World action models (WAMs) have emerged as an important class of generalist robot policies, aiming to transfer video prediction priors to action learning. However, we find that exi…
GALA: Geometry-Aware Latent Action Modeling for Vision-Language-Action Model Pretraining across Embodiments
Yichen Liu, Puzhen Yuan, Xiang Zhu +2
Learning large-scale vision-language-action (VLA) models from multi-embodiment datasets remains challenging due to heterogeneous action spaces across end effectors. Although latent…
HEFT: Heavy-Payload Full-size Humanoid Teleoperation with Privileged Motion Guidance and Windowed Payload Curriculum
Chenxin Liu, Qingzhou Lu, Guangxiao Yang +4
General motion tracking and teleoperation offer a promising path to scalable humanoid skill acquisition, yet most existing frameworks are validated on compact platforms or without…
UAM: A Dual-Stream Perspective on Forgetting in VLA Training
Jianke Zhang, Yuanfei Luo, Yucheng Hu +6
Vision--language--action (VLA) models are typically built by fine-tuning a pretrained vision--language model (VLM) on action data. However, we show that this standard recipe system…
Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training
Yaxuan Li, Zhongyi Zhou, Yefei Chen +5
Post-training is essential for turning pretrained generalist robot policies into reliable task-specific controllers, but existing human-in-the-loop pipelines remain tied to physica…
Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training
Suning Huang, Jiaqi Shao, Ke Wang +5
Have you ever post-trained a generalist vision-language-action (VLA) policy on a small demonstration dataset, only to find that it stops responding to new instructions and is limit…
Veo-Act: Enhancing VLA Policies with Frontier Video Models
Zhongru Zhang, Chenghan Yang, Qingzhou Lu +4
Video generation models can produce coherent vi- sual sequences depicting object motion and interactions. We in- vestigate how frontier video generation models can complement visio…
ProCeedRL: Process Critic with Exploratory Demonstration Reinforcement Learning for LLM Agentic Reasoning
Jingyue Gao, Yanjiang Guo, Xiaoshuai Chen +1
Reinforcement Learning (RL) significantly enhances the reasoning abilities of large language models (LLMs), yet applying it to multi-turn agentic tasks remains challenging due to t…
VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model
Yanjiang Guo, Tony Lee, Lucy Xiaoyang Shi +3
The goal of this paper is to improve the performance and reliability of vision-language-action (VLA) models through iterative online interaction. Since collecting policy rollouts i…
BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation
Yucheng Hu, Jianke Zhang, Yuanfei Luo +9
Equipping embodied agents with the ability to reason about tasks, foresee physical outcomes, and generate precise actions is essential for general-purpose manipulation. While recen…
VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models
Jianke Zhang, Xiaoyu Chen, Qiuyue Wang +7
Vision-Language-Action (VLA) models, which integrate pretrained large Vision-Language Models (VLM) into their policy backbone, are gaining significant attention for their promising…
UniJEPA: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning
Jianke Zhang, Yucheng Hu, Yanjiang Guo +5
Building generalist robot policies that can handle diverse tasks in open-ended environments is a central challenge in robotics. To leverage knowledge from large-scale pretraining,…
Ctrl-World: A Controllable Generative World Model for Robot Manipulation
Yanjiang Guo, Lucy Xiaoyang Shi, Jianyu Chen +1
Generalist robot policies can now perform a wide range of manipulation skills, but evaluating and improving their ability with unfamiliar objects and instructions remains a signifi…
villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models
Xiaoyu Chen, Hangxing Wei, Pushi Zhang +9
Vision-Language-Action (VLA) models have emerged as a popular paradigm for learning robot manipulation policies that can follow language instructions and generalize to novel scenar…
Improving Vision-Language-Action Model with Online Reinforcement Learning
Yanjiang Guo, Jianke Zhang, Xiaoyu Chen +4
Recent studies have successfully integrated large vision-language models (VLMs) into low-level robotic control by supervised fine-tuning (SFT) with expert robotic datasets, resulti…
UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent
Jianke Zhang, Yanjiang Guo, Yucheng Hu +3
Recent advancements in Vision-Language-Action (VLA) models have leveraged pre-trained Vision-Language Models (VLMs) to improve the generalization capabilities. VLMs, typically pre-…
Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations
Yucheng Hu, Yanjiang Guo, Pengchao Wang +6
Visual representations play a crucial role in developing generalist robotic policies. Previous vision encoders, typically pre-trained with single-image reconstruction or two-image…
Prediction with Action: Visual Policy Learning via Joint Denoising Process
Yanjiang Guo, Yucheng Hu, Jianke Zhang +4
Diffusion models have demonstrated remarkable capabilities in image generation tasks, including image editing and video creation, representing a good understanding of the physical…
HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers
Jianke Zhang, Yanjiang Guo, Xiaoyu Chen +4
Large Vision-Language-Action (VLA) models, leveraging powerful pre trained Vision-Language Models (VLMs) backends, have shown promise in robotic control due to their impressive gen…
Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning
Xinyang Gu, Yen-Jen Wang, Xiang Zhu +4
Humanoid robots, with their human-like skeletal structure, are especially suited for tasks in human-centric environments. However, this structure is accompanied by additional chall…
DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment
Yanjiang Guo, Yen-Jen Wang, Lihan Zha +1
Large language models (LLMs) encode a vast amount of semantic knowledge and possess remarkable understanding and reasoning capabilities. Previous work has explored how to ground LL…
Decentralized Motor Skill Learning for Complex Robotic Systems
Yanjiang Guo, Zheyuan Jiang, Yen-Jen Wang +2
Reinforcement learning (RL) has achieved remarkable success in complex robotic systems (eg. quadruped locomotion). In previous works, the RL-based controller was typically implemen…
Reinforcement learning with Demonstrations from Mismatched Task under Sparse Reward
Yanjiang Guo, Jingyue Gao, Zheng Wu +2
Reinforcement learning often suffer from the sparse reward issue in real-world robotics problems. Learning from demonstration (LfD) is an effective way to eliminate this problem, w…
Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning
Zheng Wu, Yichen Xie, Wenzhao Lian +5
Humans are capable of abstracting various tasks as different combinations of multiple attributes. This perspective of compositionality is vital for human rapid learning and adaptio…