26 citations · 108 across the 31 of their papers we have counts for
35 papers
Can World and Action Modeling Benefit Each Other under Unified Causal Training?
Yue Su, Bokai Lin, Xinkai Wang +9
World and action modeling are closely related, yet their reciprocal benefits under unified causal training remain unclear. We introduce OneWM, a simple framework for unified causal…
ForceWAM: Decoupling Future and Response Learning from Demo and Play Data for Contact-Rich Manipulation
Zijun Xu, Wendi Chen, Xinkai Wang +16
Expert demonstrations show how to complete contact-rich tasks, but provide limited coverage of how interaction forces respond to different actions. Task-agnostic play provides broa…
EgoAfford: Task-Oriented Affordance Grounding via Egocentric Referring Segmentation
Xinyuan Guan, Feifan Chen, Xinyu Zhan +3
Part-level affordance grounding has advanced the localization of functional object regions associated with elemental actions. Extending this capability to complex tasks calls for c…
Track4Action: Distilling World-Centric 3D Tracker into Vision-Language-Action Policies
Chenyi Wang, Xinkai Wang, Bokai Lin +4
Action labels tell a vision-language-action (VLA) policy which robot commands to imitate, but not how those commands change the 3D world. The aligned demonstration clip contains th…
ChronoFlow-Policy: Unifying Past-Current-Future Interaction Flow in Visuomotor Policy Learning
Bokai Lin, Yifu Xu, Xinyu Zhan +6
Visual signals play a crucial role in policy learning by enabling models to capture object motion and interaction dynamics. Just as humans reason about actions using both past expe…
AnyDexRT: Calibration-Free Dexterous Hand Retargeting with Few-Shot Human Guidance
Chenxi Wang, Ying Feng, Hongjie Fang +4
Teleoperation is a key interface for controlling dexterous robotic hands and collecting demonstrations for imitation learning. Its effectiveness largely depends on kinematic retarg…
Revisiting Articulated Parts Perception in Robot Manipulation
Xiaoqian Wu, Yejie Guo, Xiaoyang Chen +3
We are surrounded by various objects with movable, articulated parts, e.g., box, handle, door. An accurate and generalizable perception of articulated parts is essential to enhance…
X-Imitator: Spatial-Aware Imitation Learning via Bidirectional Action-Pose Interaction
Kai Xiong, Hongjie Fang, Lixin Yang +1
Effectively handling the interplay between spatial perception and action generation remains a critical bottleneck in robotic manipulation. Existing methods typically treat spatial…
LIDEA: Human-to-Robot Imitation Learning via Implicit Feature Distillation and Explicit Geometry Alignment
Yifu Xu, Bokai Lin, Xinyu Zhan +4
Scaling up robot learning is hindered by the scarcity of robotic demonstrations, whereas human videos offer a vast, untapped source of interaction data. However, bridging the embod…
From Perception to Planning: Evolving Ego-Centric Task-Oriented Spatiotemporal Reasoning via Curriculum Learning
Xiaoda Yang, Yuxiang Liu, Shenzhou Gao +8
Modern vision-language models achieve strong performance in static perception, but remain limited in the complex spatiotemporal reasoning required for embodied, egocentric tasks. A…
A Progressive Training Strategy for Embodied Vision-Language Models to Mitigate Spatio-Temporal Hallucinations
Xiaoda Yang, Shuai Yang, Can Wang +9
Vision-Language Models (VLMs) have made significant strides in static image understanding but continue to face critical hurdles in spatiotemporal reasoning. A major bottleneck is "…
VFM-Recon: Unlocking Cross-Domain Scene-Level Neural Reconstruction with Scale-Aligned Foundation Priors
Yuhang Ming, Tingkang Xi, Xingrui Yang +4
Scene-level neural volumetric reconstruction from monocular videos remains challenging, especially under severe domain shifts. Although recent advances in vision foundation models…
LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Prior
Xinkai Wang, Chenyi Wang, Yifu Xu +7
We introduce \textbf{LaMP}, a dual-expert Vision-Language-Action framework that embeds dense 3D scene flow as a latent motion prior for robotic manipulation.Existing VLA models reg…
L1 Sample Flow for Efficient Visuomotor Learning
Weixi Song, Zhetao Chen, Tao Xu +6
Denoising-based models, such as diffusion and flow matching, have been a critical component of robotic manipulation for their strong distribution-fitting and scaling capacity. Conc…
TrajBooster: Boosting Humanoid Whole-Body Manipulation via Trajectory-Centric Learning
Jiacheng Liu, Pengxiang Ding, Qihang Zhou +8
Recent Vision-Language-Action models show potential to generalize across embodiments but struggle to quickly align with a new robot's action space when high-quality demonstrations…
OmniCam: Unified Multimodal Video Generation via Camera Control
Xiaoda Yang, Jiayang Xu, Kaixuan Luan +9
Camera control, which achieves diverse visual effects by changing camera position and pose, has attracted widespread attention. However, existing methods face challenges such as co…
Dense Policy: Bidirectional Autoregressive Learning of Actions
Yue Su, Xinyu Zhan, Hongjie Fang +5
Mainstream visuomotor policies predominantly rely on generative models for holistic action prediction, while current autoregressive policies, predicting the next token or chunk, ha…
AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons
Hongjie Fang, Chenxi Wang, Yiming Wang +11
Scaling up robotic imitation learning for real-world applications requires efficient and scalable demonstration collection methods. While teleoperation is effective, it depends on…
Motion Before Action: Diffusing Object Motion as Manipulation Condition
Yue Su, Xinyu Zhan, Hongjie Fang +3
Inferring object motion representations from observations enhances the performance of robotic manipulation tasks. This paper introduces a new paradigm for robot imitation learning…
Multi-view Hand Reconstruction with a Point-Embedded Transformer
Lixin Yang, Licheng Zhong, Pengxiang Zhu +4
This work introduces a novel and generalizable multi-view Hand Mesh Reconstruction (HMR) model, named POEM, designed for practical use in real-world hand motion capture scenarios.…
SemGrasp: Semantic Grasp Generation via Language Aligned Discretization
Kailin Li, Jingbo Wang, Lixin Yang +2
Generating natural human grasps necessitates consideration of not just object geometry but also semantic information. Solely depending on object shape for grasp generation confines…
OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion
Xinyu Zhan, Lixin Yang, Yifei Zhao +5
We present OAKINK2, a dataset of bimanual object manipulation tasks for complex daily activities. In pursuit of constructing the complex tasks into a structured representation, OAK…
CHORD: Category-level Hand-held Object Reconstruction via Shape Deformation
Kailin Li, Lixin Yang, Haoyu Zhen +6
In daily life, humans utilize hands to manipulate objects. Modeling the shape of objects that are manipulated by the hand is essential for AI to comprehend daily tasks and to learn…
Color-NeuS: Reconstructing Neural Implicit Surfaces with Color
Licheng Zhong, Lixin Yang, Kailin Li +3
The reconstruction of object surfaces from multi-view images or monocular video is a fundamental issue in computer vision. However, much of the recent research concentrates on reco…