The paper proposes VERA, a decoupled policy that uses an action-free video world model combined with an embodiment-specific Inverse Dynamics Model (IDM) to achieve generalizable, zero-shot robot contr…

The paper introduces MiraBench, a new benchmark that evaluates the action-conditioned reliability of robotic world models, finding that visual fidelity is insufficient and that optimism bias is a perv…

The paper introduces a diagnostic framework to determine if World-Action Models (WAMs) provide genuinely actionable behavioral improvements beyond simply achieving task success, finding that WAMs ofte…

RoboDream introduces an embodiment-centric world model that synthesizes photorealistic, physically feasible robot demonstrations by decoupling motion generation from environment synthesis, significant…

The paper argues that for embodied AI to be safe and effective, world models must be physically viable, requiring a structural shift from mere observation prediction to representing the underlying phy…

The paper introduces SpatialAct, a challenging benchmark that reveals a significant 'reasoning-to-action gap,' showing that current VLMs struggle to maintain coherent spatial understanding and perform…

The paper introduces WorldDirector, a framework for creating controllable video worlds with persistent dynamic object memory and exact visual identities.

This paper introduces BadWAM, a framework for modeling and evaluating World-Action Drift Attacks, a new class of adversarial attacks that break the alignment between a World-Action Model's (WAM's) ima…

Proposed G$^3$VLA, a camera-aware geometric module for pretrained vision-language-action models, injecting calibrated structure into visual tokens using intrinsic-conditioned ray embeddings, projectiv…

This paper organizes embodied data sources for multimodal foundation models into a pyramid, focusing on real-robot, UMI-style, egocentric and exocentric, simulation, and general vision-language data.

The paper formally addresses the challenging question of cross-domain transferability of latent predictive models by proposing a structured framework that quantifies the relationship between source an…

This paper introduces DriftWorld, an action-conditioned world model based on drifting generative models, which generates future frames from the current observation and a candidate action sequence in a…

Qwen-VLA introduces a unified embodied foundation model that extends vision-language understanding to continuous action generation, enabling robust, multi-task generalization across diverse robotic ta…

This paper investigates the robustness of world models in vision-based quadrotor navigation and identifies factors governing their quality.