Closed-loop framework coupling Vision-Language Models with Video Generation Models at step-level granularity. Mitigates long-horizon drift and mid-clip errors in goal-directed video reasoning for robotic planning.

First systematic survey defining World Action Models (WAMs) as embodied foundation models that jointly predict future states and generate actions. Covers architectures, data ecosystems, and evaluation protocols.

Describes end-to-end learning of a foundation model for adaptive whole-body humanoid control via massive simulation variation. Combines proprioceptive perception and policy adaptation across embodiments.

Releases an open-source MuJoCo-based benchmark with 11 dexterous tasks, low-cost teleoperation hardware, and 1.1K human demonstrations. Designed to evaluate and train modern VLA/robotic policies.

Skill library, demonstrations, and dataset for multi-modal robotic skill learning and manipulation tasks.

Introduces dual-brain fusion Vision-Language-Action model with LangForce physics-grounded training methodology.

Vision-Language-Action (VLA) model fine-tuned on the merged LIBERO robotics dataset (1,693 episodes, 273k+ frames) achieving 98.25% success rate on manipulation tasks. Released with both checkpoint and dataset for VLA finetuning.

A 2.6B-parameter open-source world model that generates coherent 720p, minute-long videos with precise 6-DoF camera control on a single GPU using a Hybrid Linear Diffusion Transformer + Gated DeltaNet for long-context efficiency. Targets controllable physics simulation.

New benchmark and dataset for robotic manipulation in unconstrained 'wild' environments. Includes standardized containers, leaderboards, and evaluation protocols for cross-embodiment policies.

Introduces a latent-space world model framework that lets agents simulate state transitions and iteratively refine plans before real-world execution. Evaluated on 20+ MCP-Bench tasks with measurable gains in tool-use success.