24 citations · 47 across the 39 of their papers we have counts for
48 papers
Hand2Robot: Object-Centric 4D Hand Reconstruction from Human Demonstrations for Robotics
Zetao Du, Weiqing Wang, Hanbing Zhang +4
Human demonstrations can capture task-relevant manipulation without using the target robot, but the recorded hand motions cannot directly serve as robot action supervision. Hand re…
CFG-Policy: Unified Diffusion Policy Learning Framework via Classifier-free Guidance
Shutong Ding, Zhaoyang Liu, Yimiao Zhou +3
Diffusion policies are increasingly used in robotic control and manipulation, vision-language-action models, and world-model-based agents. Their ability to represent multimodal act…
From Social Reasoning to Embodied Interaction: An Agentic Framework for Social Robots
Ziyu Cheng, Yuewen Guo, Zhirui Liu +5
Natural face-to-face human--robot interaction requires a robot to understand an evolving social situation, decide when to engage, and express its intent through coordinated physica…
FASTER: Fast Adjoint Stochastic Transport for Endpoint Refinement in Reward-Guided Image Editing
Yimiao Zhou, Zejia Zhong, Jingya Wang +1
Reward-guided image editing at test time seeks to improve a specified reward while preserving source content and visual plausibility. Many existing approaches optimize candidates t…
EmbodiRSI: Recursive Self-Improvement for Data-Efficient Robot Adaptation
Haoran Lang, Haotao Lu, Shiyu Sang +6
Adapting robot manipulation policies to new tasks and environments remains highly data-intensive, while the data needed for further improvement depends on the policy's current capa…
In-Context Forcing: Uncovering Context Effects in Autoregressive Video Diffusion
Lingxiao Yang, Liu Liu, Moran Li +4
Current few-step autoregressive video diffusion models depend on previous fully denoised clean frames as context for all denoising steps of the current frame. However, these clean…
ViTacWorld: Scaling Visuo-Tactile World Models for Contact-Rich Robot Manipulation
Yunao Huang, Shiyu Sang, Haotao Lu +6
Contact-rich robot manipulation requires physical interaction cues that are often invisible to cameras, making tactile sensing essential for robust control. However, scaling visuo-…
Super Star: Towards Streaming Real-time Interactive Agents for Digital Humans
Wentao Jiang, Youchen Xie, Haidi Fan +4
Existing co-speech gesture generation methods are predominantly studied in offline settings, where gestures are synthesized from complete speech segments. However, interactive digi…
TactiDex: A Real-World Tactile-Guided Benchmark for Human-Like Dexterous Manipulation
Suting Ni, Hanbing Zhang, Zhenyu Wei +4
Tactile feedback is fundamental to Hand-Object Interaction (HOI), governing contact formation, force regulation, and stable manipulation, making it essential for achieving true hum…
Steering Generative Reinforcement Learning into Stable Robotic Controller
Yixuan Wang, Shutong Ding, Ke Hu +3
Diffusion and flow-based generative policies provide a powerful policy class for reinforcement learning by inducing rich stochastic exploration through iterative action generation.…
GenPO++: Generative Policy Optimization with Jacobian-free Likelihood Ratios
Ke Hu, Shutong Ding, Panxin Tao +2
Generative policies provide expressive and multimodal action distributions, making them attractive for reinforcement learning (RL) in complex continuous-control tasks. Among them,…
Conformal Reliability: A New Evaluation Metric for Conditional Generation
Yachen Gao, Xinwei Sun, Yikai Wang +4
Conditional generative models have recently achieved remarkable success in various applications. However, a suitable metric for evaluating the reliability of these models, which ta…
DiscoForcing: A Unified Framework for Real-Time Audio-Driven Character Control with Diffusion Forcing
Kaiyang Ji, Bingsheng Qian, Binghuan Wu +3
We study real-time audio-responsive character control as a deployment-faithful problem: strictly causal, bounded-latency streaming that must generate coherent full-body motion at i…
UniHM: Unified Dexterous Hand Manipulation with Vision Language Model
Zhenhao Zhang, Jiaxin Liu, Ye Shi +1
Planning physically feasible dexterous hand manipulation is a central challenge in robotic manipulation and Embodied AI. Prior work typically relies on object-centric cues or preci…
Learning Semantic Atomic Skills for Multi-Task Robotic Manipulation
Yihang Zhu, Weiqing Wang, Shijie Wu +2
Scaling imitation learning to diverse multi-task robot manipulation remains challenging due to suboptimal demonstrations, behavioral multi-modality, and destructive interference ac…
Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation
Zhaoyang Liu, Mokai Pan, Zhongyi Wang +5
Imitation learning with diffusion models has advanced robotic control by capturing the multi-modal action distributions. However, existing methods typically treat observations only…
Commanding Humanoid by Free-form Language: A Large Language Action Model with Unified Motion Vocabulary
Zhirui Liu, Kaiyang Ji, Ke Yang +4
Enabling humanoid robots to follow free-form natural language commands is a critical step toward seamless human-robot interaction and general-purpose embodied AI. However, existing…
Diffusion Bridge or Flow Matching? A Unifying Framework and Comparative Analysis
Kaizhen Zhu, Mokai Pan, Zhechuan Yu +3
Diffusion Bridge and Flow Matching have both demonstrated compelling empirical performance in transformation between arbitrary distributions. However, there remains confusion about…
Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis
Kaiyang Ji, Ye Shi, Zichen Jin +5
Real-time synthesis of physically plausible human interactions remains a critical challenge for immersive VR/AR systems and humanoid robotics. While existing methods demonstrate pr…
A Unified and Fast-Sampling Diffusion Bridge Framework via Stochastic Optimal Control
Mokai Pan, Kaizhen Zhu, Yuexin Ma +4
Recent advances in diffusion bridge models leverage Doob's -transform to establish fixed endpoints between distributions, demonstrating promising results in image translation an…
OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model
Zhenhao Zhang, Ye Shi, Lingxiao Yang +3
Understanding and synthesizing realistic 3D hand-object interactions (HOI) is critical for applications ranging from immersive AR/VR to dexterous robotics. Existing methods struggl…
DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion
Yahao Fan, Tianxiang Gui, Kaiyang Ji +8
Achieving versatile humanoid locomotion with a single policy presents a critical scalability challenge. Prevailing methods often rely on distilling multiple terrain-specific teache…
GenPO: Generative Diffusion Models Meet On-Policy Reinforcement Learning
Shutong Ding, Ke Hu, Shan Zhong +5
Recent advances in reinforcement learning (RL) have demonstrated the powerful exploration capabilities and multimodality of generative diffusion-based policies. While substantial p…
Human-Object Interaction via Automatically Designed VLM-Guided Motion Policy
Zekai Deng, Ye Shi, Kaiyang Ji +3
Human-object interaction (HOI) synthesis is crucial for applications in animation, simulation, and robotics. However, existing approaches either rely on expensive motion capture da…