Devol-ONE: One Autoregressive Mixture of Transformers to Unify Vision-Language-Action and Latent World Modeling

arXiv:2609.32193 · cs.CV · Submitted 2026-09-26 · Read on arXiv

cs.CV

Submitted: 2026-09-26

Updated: 2026-10-01

Project page: https://robotwin-platform.github.io/leaderboard

Terminology

• Transformer — 14× in this paper · explained in 2 episodes
• World Model — 13× in this paper · explained in 7 episodes
• Fine-Tuning — 11× in this paper · explained in 5 episodes
• Latent Dynamics — 11× in this paper · explained in 2 episodes
• Joint Attention — 7× in this paper · explained in 2 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• Foundation Model — 6× in this paper · explained in 3 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Generative AI — 4× in this paper · explained in 2 episodes
• World Action Models — 4× in this paper
• Ablation Studies — 3× in this paper · explained in 1 episode
• Autoregressive Latent Rollout Training — 3× in this paper
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Diffusion Models — 3× in this paper · explained in 6 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Decode — 2× in this paper · explained in 2 episodes
• Exposure Bias — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• VLA Models — 2× in this paper · explained in 3 episodes
• Vision-Language-Action (VLA) Models — 2× in this paper · explained in 2 episodes
• Action Flow — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Digital Twin — 1× in this paper · explained in 5 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Hysteresis — 1× in this paper · explained in 3 episodes
• Imitation Learning (IL) — 1× in this paper · explained in 2 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Latent World Models — 1× in this paper · explained in 2 episodes
• Optical Flow — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Vision Language Action — 1× in this paper

Sources

• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• Motus: A Unified Latent Action World Model
• LAOF: Robust Latent Action Learning with Optical Flow Constraints
• AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing
• Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution
• RynnVLA-002: A Unified Vision-Language-Action and World Model
• IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI
• LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
• Learning Latent Action World Models In The Wild
• Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising
• Object-Centric Latent Action Learning
• Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
• VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators
• Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding
• Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment
• Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model
• StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation
• World Action Models: A Survey
• StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
• VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models