6 papers
V-JEPA Policy: Building Effective World-Action Models on Predictive Visual Latents
Yang Zhang, Jiangyuan Zhao, Chenyou Fan +4
World-action models (WAMs) couple future visual-state prediction with action generation. By adapting video generators or image-editing models pretrained at scale, a prominent line…
KineBench: Benchmarking Embodied World Models via IDM-Free Kinematic Grounding
Zeyu Liu, Zhangzhe Zhu, Yang Zhang +3
Evaluating the physical consistency of embodied world models(EWMs) is a critical open challenge. While closed-loop evaluation via simulator rollouts offers a more faithful assessme…
PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations
Yang Zhang, Jiangyuan Zhao, Chenyou Fan +11
Vision-Language-Action (VLA) models advance robotic control via strong visual-linguistic priors. However, existing VLAs predominantly frame pretraining as supervised behavior cloni…
Towards a Generalizable Bimanual Foundation Policy via Flow-based Video Prediction
Chenyou Fan, Fangzheng Yan, Chenjia Bai +4
Learning a generalizable bimanual manipulation policy is extremely challenging for embodied agents due to the large action space and the need for coordinated arm movements. Existin…
Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner
Chenyou Fan, Chenjia Bai, Zhao Shan +3
Diffusion models have demonstrated their capabilities in modeling trajectories of multi-tasks. However, existing multi-task planners or policies typically rely on task-specific dem…
Forward KL Regularized Preference Optimization for Aligning Diffusion Policies
Zhao Shan, Chenyou Fan, Shuang Qiu +2
Diffusion models have achieved remarkable success in sequential decision-making by leveraging the highly expressive model capabilities in policy learning. A central problem for lea…