15 papers · 1 filter
4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields
Lishan Yang, Wenxuan Song, Xi Wang +14
Building on recent advances in world models, World Action Models (WAMs) jointly model video prediction and action generation. However, they typically represent videos in 2D pixel s…
Is Forward Prediction Enough? Physical State Grounding for JEPA World Models
Haodong Yan, Jiaguan Zhu, Mingyuan Jia +12
Learning structured and control-relevant latent representations remains a key challenge for world models. Recent JEPA-based world models learn action-conditioned predictive latent…
RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark
Huashuo Lei, Wenxuan Song, Huarui Zhang +10
Memory is a critical component of robotic intelligence, as robots must rely on past observations and actions to accomplish long-horizon tasks in partially observable environments.…
DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching
Jiayi Chen, Wenxuan Song, Jiaxin Fang +13
Vision-Language-Action (VLA) models that encode actions using a discrete tokenization scheme have been widely adopted for robotic manipulation, but existing decoding paradigms rema…
Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance
Wenxuan Song, Jiayi Chen, Shuai Chen +8
This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard s…
Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process
Jiayi Chen, Wenxuan Song, Pengxiang Ding +5
Vision-language-action (VLA) models aim to understand natural language instructions and visual observations and to execute corresponding actions as an embodied agent. Recent work i…