21 papers
PAVXploreRL: Physical-Action-Visual World Model Reinforcement Learning with Action Exploration
Han Wang, Zijun Wang, Shuoshuo Xue +6
Action-conditioned world models are a key component of embodied AI, serving as scalable policy evaluators that reduce reliance on expensive real-world rollouts. To accurately captu…
STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning
Zhihao Liu, Qiuyi Gu, Yitao Wang +16
Real-world robot learning increasingly relies on heterogeneous data, but demonstrations and rollouts often mix useful progress with stalls, corrections, and suboptimal behavior. Ef…
World2Act: Latent Action Post-Training from World Model Dynamics
An Dinh Vuong, Tuan Van Vo, Abdullah Sohail +6
World Models (WMs) offer a promising mechanism for post-training Vision-Language-Action (VLA) policies by providing dynamics priors that improve generalization under task and scene…
ArtiSG: Functional 3D Scene Graph Construction via Human-demonstrated Articulated Objects Manipulation
Qiuyi Gu, Yuze Sheng, Jincheng Yu +7
3D scene graphs have empowered robots with semantic understanding for navigation and planning. However, current functional scene graphs primarily focus on static element detection,…
AnyCrowd: Instance-Isolated Identity-Pose Binding for Arbitrary Multi-Character Animation
Zhenyu Xie, Ji Xia, Michael Kampffmeyer +9
Controllable character animation has advanced rapidly in recent years, yet multi-character animation remains underexplored. As the number of characters grows, multi-character refer…
CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning
Yongxin Wang, Zhicheng Yang, Meng Cao +5
Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures. When all rollouts are wrong, gradients stal…