14 papers
-WAM: Repair-and-Reject Post-Training for World Action Models
Ruiyan Xu, Haisheng Su, Sixu Lin +4
World Action Models (WAMs) emerge as a promising foundation for policy refinement by predicting the consequences of sampled actions. However, visually plausible predictions can mis…
RoboSynChallenge: Mastering Real-World Dexterity via Generalizing Synthesized Manipulation Skills
Runyi Zhao, Ruixin Wu, Chengkun Li +15
Achieving generalizable robotic manipulation remains a central challenge in embodied intelligence. Despite rapid advances in model architectures and learning algorithms, progress i…
Vid2WAM: Distilling Video Diffusion Priors into World Action Models
Chenhao Qiu, Ruixiang Wang, Runyi Zhao +7
World Action Models (WAMs) improve robot policy learning by jointly modeling future visual dynamics and actions. However, their scalability and generalization remain constrained by…
LIRA: Local Cross-Layer Information Routing for Vision-Language-Action Decoding
Zhewei Zhang, Puyue Wang, Guanren Qiao +10
Vision-Language-Action (VLA) models transform representations from pretrained vision-language models (VLMs) into robot actions, yet the interface that routes intermediate VLM featu…
RoboReact: Agentic Skill Distillation from Generated Egocentric Videos for Generalizable Whole-Body Manipulation
Shuliang He, Shuai Wang, Bo Yue +3
Humanoid robots have the potential to perform dexterous manipulation in human environments, yet acquiring diverse and generalizable skills remains costly due to expensive hardware…
LoopVLA: cross-subtask event memory for looped task execution
Shoujing Zhu, Zhenyang Liu, Fungmiu Wang +6
Repetitive tasks are common in real-world manipulation, yet current vision-language-action (VLA) policies remain unreliable for repeated actions. We present LoopVLA, a cross-subtas…
RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation
Sixu Lin, Junliang Chen, Huaiyuan Xu +8
Planning and acting in 3D environments is a fundamental capability for robotic manipulation in the real world. Although prior work has explored predictive flow planners to guide 3D…
DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization
Sixu Lin, Yunpeng Qing, Litao Liu +4
Recent progress in Reinforcement Learning (RL) provides a principled approach to optimizing Vision-Language-Action (VLA) models, facilitating a shift from trajectory imitation to a…
From Reaction to Anticipation: Proactive Failure Recovery through Agentic Task Graph for Robotic Manipulation
Sheng Xu, Ruixing Jin, Huayi Zhou +6
Although robotic manipulation has made significant progress, reliable execution remains challenging because task failures are inevitable in dynamic and unstructured environments. T…
TacticGen: Grounding Adaptable and Scalable Generation of Football Tactics
Sheng Xu, Guiliang Liu, Tarak Kharrat +12
Success in association football relies on both individual skill and coordinated tactics. While recent advancements in spatio-temporal data and deep learning have enabled predictive…
DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks
Yueci Deng, Guiliang Liu, Kui Jia
Deploying generative World-Action Models for manipulation is severely bottlenecked by redundant pixel-level reconstruction, memory scaling, and sequential inferenc…
Grounding Sim-to-Real Generalization in Robotic Manipulation: An Empirical Study with Vision-Language-Action Models
Ruixing Jin, Zicheng Zhu, Ruixiang Ouyang +4
Learning a generalist control policy for robotic manipulation typically relies on large-scale datasets. Given the high cost of real-world data collection, a practical alternative i…
Provably Efficient Exploration in Inverse Constrained Reinforcement Learning
Bo Yue, Jian Li, Guiliang Liu
Optimizing objective functions subject to constraints is fundamental in many real-world applications. However, these constraints are often not readily defined and must be inferred…
A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challenges
Guiliang Liu, Sheng Xu, Shicheng Liu +3
Inverse Constrained Reinforcement Learning (ICRL) is the task of inferring the implicit constraints that expert agents adhere to, based on their demonstration data. As an emerging…