arXiv Computer Vision
What Matters for World Modeling in Vision-Language-Action Models?
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Sep 10
WorldAgen: Unified State-Action Prediction with Test-Time World Model Training
WorldAgen is a unified framework that jointly learns world modeling and action prediction using a shared Transformer backbone with two specialized heads. It introduces a Mixed Unidirectional Attention Mask to separate the world model and agent model, and enables Test-Time Training (TTT) by sampling exploratory actions and updating the world model with real state transitions. Experiments on CALVIN and LIBERO show that WorldAgen matches or surpasses state‑of‑the‑art methods, especially when TTT is applied to a few samples.
arXiv AI
Jun 6
World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis
arXiv:2606. 05979v1 Announce Type: cross Abstract: We propose world-language-action (WLA) models as a new class of embodied foundation models.
arXiv Machine Learning
Jul 7
WorldBagel: Uncovering the Power of Unified Multimodal Models for Vision-Language-Action-World Modeling
arXiv:2607. 03461v1 Announce Type: cross Abstract: World models aim to capture environment dynamics in ways that support perception, reasoning, and action, and have recently become a central direction in Vision-Language-Action-World (VLAW) modeling.
arXiv Computer Vision
Sep 24
AWM-VLA: AlignedWorld Modeling for Efficient and Explainable Vision-Language-Action Policies
AWM‑VLA introduces a unified framework that embeds aligned world modeling directly into a diffusion‑transformer vision‑language‑action policy. By adding learnable future tokens aligned with vision‑language embeddings of future observations, the policy can anticipate long‑term consequences while generating actions. The method extends this with an object‑centric alignment objective and a principled weighting scheme, achieving up to 21% higher success rates on RoboCasa and humanoid tabletop benchmarks and producing object‑centric rationales preferred by human raters in 83% of cases.
arXiv Computer Vision
Oct 2
Devol-ONE: One Autoregressive Mixture of Transformers to Unify Vision-Language-Action and Latent World Modeling
arXiv:2609.32193v2 Announce Type: replace Abstract: Vision Language Action (VLA) models condition actions directly on current visual and language context, without an explicit account of how the scene...
arXiv Computer Vision
6d ago
Vision-Language-Action or World-Action? Just Action Models
The paper introduces the Just Action Model (JAM), a framework that decouples backbone initialization, future observation objectives, and inference machinery to unify vision-language-action (VLA) and world-action model (WAM) approaches. JAM employs a pretrained visual backbone, an action expert, an action loss, and a foresight loss that predicts future encodings without visual generation, discarding the prediction head after training. Experiments show JAM outperforms FastWAM and ImageWAM on LIBERO, LIBERO-Plus, and RoboTwin, while reducing online training FLOPs by 73%.