18 papers
MaskVLA: Visual Masking Against Trajectory Overfitting of Vision-Language-Action Model
Yuxuan Jiang, Jiaying Huang, Ge Wang +9
Vision-Language-Action (VLA) models integrate vision-language understanding with executable robot actions, enabling end-to-end learning for robot control. However, our empirical an…
Decoupling Policy Extraction for Offline Reinforcement Learning
Xuyao Lin, Yixiang Shan, Jinru Duan +7
Offline RL methods commonly jointly train the actor and critic, where the critic is used to guide the actor toward higher-value actions. This coupled learning process is well motiv…
Rethink Before You Execute: Adaptive Execution for World Action Models
Feng Ye, Yiming Zhao, Yong Yu +5
World Action Models (WAMs) jointly predict future actions and the evolution of the environment. At each inference, a WAM generates a chunk of actions and the robot executes a fixed…
Interleaved POMDP Planning for Multi-Object Search in Unknown Multi-Room Household Environments
Ruochu Yang, Ziyi Xia, Huibo Zhang +6
Multi-object search in unknown household environments requires planning under extensive uncertainty - from unknown object locations to cluttered spaces with unobserved obstacles. P…
TSD: A Physics-Inspired Trajectory Saliency Detector for Efficient Imitation Learning
Yiming Zhao, Gongrui Ma, Qingkai Li +1
For imitation learning in robotic manipulation, high data collection costs result in the scarcity of high quality data. In this paper, we leverage the inherent heterogeneity of tra…
ReFPO: Reflow Regularization for Flow Matching Policy Gradients
Ge Wang, Yibo Peng, Fan Feng +10
We present Reflow-regularized Flow Matching Policy Gradients (ReFPO), a simple online RL method that adds explicit Reflow regularization to FPO for efficient flow-based control. We…
MimicIK: Real-Time Generative Inverse Kinematics from Teleoperation with FK Consistency
Jiahao Yang, Shenhao Yan, Fan Feng +5
Inverse kinematics (IK) remains a critical bottleneck for real-time robot manipulation. Classical numerical solvers achieve high geometric precision but often suffer from discontin…
Acting While Understanding: Asynchronous Semantic-Action Decoupling for Real-Time Vision-Language-Action Models
Shenhao Yan, Ge Wang, Qi Liu +7
Vision-Language-Action models (VLAs) have demonstrated strong task understanding and generalization in robotic manipulation, yet the high computational cost of full-model inference…
ConSteer-RL: Steering Reasoning Capabilities in Large Language Models via Confidence-Aware Reinforcement Learning
Qing Miao, Yiming Zhao, Jing Yang +5
Reinforcement Learning from Verifiable Rewards (RLVR) has recently become a key paradigm for improving the reasoning abilities of Large Language Models (LLMs), yet it remains limit…
Internalizing Agency from Reflective Experience
Rui Ge, Yichao Fu, Yuyang Qian +4
Large language models are increasingly deployed as autonomous agents that must plan, act, and recover from mistakes through long-horizon interaction with environments that provide…
KoopmanFlow: Spectrally Decoupled Generative Control Policy via Koopman Structural Bias
Chengsi Yao, Ge Wang, Kai Kang +9
Generative Control Policies (GCPs) show immense promise in robotic manipulation but struggle to simultaneously model stable global motions and high-frequency local corrections. Whi…
SVLL: Staged Vision-Language Learning for Physically Grounded Embodied Task Planning
Yuyuan Yang, Junkun Hong, Hongrong Wang +11
Embodied task planning demands vision-language models to generate action sequences that are both visually grounded and causally coherent over time. However, existing training parad…
Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces
Jiayuan Du, Yuebing Song, Yiming Zhao +6
End-to-End autonomous driving (E2E-AD) systems face challenges in lifelong learning, including catastrophic forgetting, difficulty in knowledge transfer across diverse scenarios, a…
RoboSeek: You Need to Interact with Your Objects
Yibo Peng, Jiahao Yang, Shenhao Yan +5
Optimizing and refining action execution through exploration and interaction is a promising way for robotic manipulation. However, practical approaches to interaction-driven roboti…
RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systems
Mingcong Lei, Honghao Cai, Yuyuan Yang +16
Embodied intelligence aims to enable robots to learn, reason, and generalize robustly across complex real-world environments. However, existing approaches often struggle with parti…
SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents
Wanxin Tian, Shijie Zhang, Kevin Zhang +12
Self-evolution, the ability of agents to autonomously improve their reasoning and behavior, is essential for the embodied domain with long-horizon, real-world tasks. Despite curren…
CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic Environments
Mingcong Lei, Ge Wang, Yiming Zhao +7
Large Language Models (LLMs) exhibit remarkable capabilities in the hierarchical decomposition of complex tasks through semantic reasoning. However, their application in embodied s…
STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planning
Mingcong Lei, Yiming Zhao, Ge Wang +4
A key objective of embodied intelligence is enabling agents to perform long-horizon tasks in dynamic environments while maintaining robust decision-making and adaptability. To achi…