15 papers
MOSS: Mode-Oriented Source Shaping for Robot Flow Matching Policies
Zirun Ma, Jindou Jia, Tuo An +3
In robotic manipulation, the same observation often admits multiple feasible actions. Generative policies such as diffusion and flow matching naturally capture such multimodal beha…
Flow Matching for Robot Foundation Models
Kuangji Zuo, Tuo An, Xinying Guo +9
Flow matching is a common generative recipe for robot foundation models. Vision-language-action models (VLAs) generate action chunks, while world-action models (WAMs) additionally…
TUCO: Curating Simulation Demonstrations for Sim-to-Real Robot Policy Co-Training
Ning Zhu, Mengfei Zhao, Yikai Tang +5
Simulation demonstrations can supplement scarce real-world data for robot policy co-training. However, the value of using data curation to actively select these demonstrations for…
F4R: Failure-Driven Recognition, Reconstruction, Refinement, and Redeployment for Continual Robot Self-Improvement
Zhuoyuan Yu, Jiacheng Wang, Tianle Liu +13
The real-world performance of current vision-language-action models is fundamentally constrained by the limited coverage of expert demonstrations and their insufficient understandi…
ADAPT: Analytical Disturbance-Aware Policy Training for Humanoid Locomotion
Bofan Lyu, Jindou Jia, Kuangji Zuo +7
Humanoids deployed in human-centered environments must handle force-interactive tasks, where external contacts introduce unexpected disturbances that disrupt locomotion accuracy an…
APEX: Adaptive Policy Execution for Precise Manipulation
Mengfei Zhao, Chenxi Jiang, Tuo An +2
Modern imitation learning methods, including visuomotor and Vision-Language-Action (VLA) policies, typically output high-level action references that are executed by low-level cont…
GIVE: Grounding Human Gestures in Vision-Language-Action Models
Pengfei Liu, Gen Li, Junqiao Fan +4
Human communication is inherently multimodal, where language is often accompanied by non-verbal cues such as gestures to convey intentions. However, current Vision-Language-Action…
MARS Policy: Multimodality Only When It Matters
Jindou Jia, Tuo An, Yuxuan Hu +7
Imitation learning has become a cornerstone for solving complex robotic manipulation tasks. In particular, multimodality, which enables robots to capture diverse yet valid behavior…
CompassAD: Intent-Driven 3D Affordance Grounding in Functionally Competing Objects
Jingliang Li, Jindou Jia, Tuo An +7
When told to "cut the cake," a robot must choose the knife over nearby scissors, despite both objects affording the same cutting function. In real-world scenes, multiple objects ma…
Feedback World Model Enables Precise Guidance of Diffusion Policy
Tuo An, Jindou Jia, Gen Li +8
World models aim to improve robotic decision making by predicting the consequences of actions. However, in practice, their predictions often become unreliable once the robot encoun…
FLASH: Efficient Visuomotor Policy via Sparse Sampling
Jiaqi Bai, Jindou Jia, Yuxuan Hu +5
Generative models such as diffusion and flow matching have become dominant paradigms for visuomotor policy learning, yet their reliance on iterative denoising incurs high inference…
World Model for Robot Learning: A Comprehensive Survey
Bohan Hou, Gen Li, Jindou Jia +15
World models, which are predictive representations of how environments evolve under actions, have become a central component of robot learning. They support policy learning, planni…
Trace-Focused Diffusion Policy for Multi-Modal Action Disambiguation in Long-Horizon Robotic Manipulation
Yuxuan Hu, Xiangyu Chen, Chuhao Zhou +4
Generative model-based policies have shown strong performance in imitation-based robotic manipulation by learning action distributions from demonstrations. However, in long-horizon…
Action-to-Action Flow Matching
Jindou Jia, Gen Li, Xiangyu Chen +5
Diffusion-based policies have recently achieved remarkable success in robotics by formulating action prediction as a conditional denoising process. However, the standard practice o…
DIPOLE: Fusing Vision and Geometry for Robust Visuomotor Generalization
Yikai Tang, Haoran Geng, Jindou Jia +5
Imitation learning has emerged as a crucial approach for acquiring visuomotor skills from demonstrations, where designing effective observation encoders is essential for policy gen…