cs.RONov 26, 2025

E0: Expressive Fine-Grained Discrete Action Prediction for Vision-Language-Action Models via Tweedie Discrete Diffusion

Authors: Zhihao Zhan, Jiaying Zhou, Likui Zhang, Qinhan Lyu, Hao Liu, Weizheng Li, Jusheng Zhang, Ziliang Chen, 

Organizations: Sun Yat-sen University · X-Era AI Lab · Guangdong University of Technology · Guangdong Key Laboratory of Big Data Analysis and Processing

Abstract

Vision-Language-Action (VLA) models offer a unified framework for robotic manipulation by integrating visual perception, language understanding, and control generation. However, existing VLA systems still struggle to generalize across diverse tasks, scenes, and camera viewpoints, and often produce coarse or unstable actions. We argue that these limitations are closely tied to the structural properties of actions in VLA settings, including the inherent multi-peaked nature of action distributions, the token-based symbolic reasoning of pretrained VLM/VLA backbones, and the effective finite resolution imposed by real-world robotic control. Motivated by these properties, we introduce E0, a tweedie discrete diffusion framework that formulates action generation as iterative denoising over quantized action tokens. By operating in a discrete action space with a principled diffusion process, E0 naturally aligns with token-based reasoning, supports fine-grained yet executable action control, and avoids the distributional mismatch of masking-based discrete diffusion. Experiments on LIBERO, VLABench, ManiSkill, and a real-world Franka arm demonstrate that E0 achieves state-of-the-art performance across diverse environments, outperforming strong baselines by 8.1% on average.

Figures & tables

Appendix figures & tables29 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models

    Jun 22, 2026Yuhao Wu, Yitian Liu, Weijie Shen +13Vision-Language-Action ModelsDiffusion-Based VLA Models

  2. Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models

    Jun 5, 2026Jinhao Wu, Shiduo Zhang, Yicheng Liu +9Visuomotor Policy LearningAI Control

  3. Vision-Language Models Are Joint Denoisers in Robotic Action Generation

    Oct 31, 2026Xicheng Gong, Wenxuan Song, Chengze Liu +5Diffusion-Based VLA ModelsVision-Language-Action Models