World In-Context Learning for Agentic Robot Manipulation
cs.CV, cs.RO
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/ArcheOne-AI/RoboScript
Project page: https://archeone-ai.github.io/RoboScript
Terminology
Sources
- 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
- GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
- FlowWAM: Optical Flow as a Unified Action Representation for World Action Models
- EBench: Elemental Diagnosis of Generalist Mobile Manipulation Policies
- HarnessWAM: Bridging Prediction and Deliberation in World Action Models
- Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising
- RoboHarness: Memory-Driven Orchestration of Heterogeneous Robot Policies for Long-Horizon Planning
- WorldEval: World Model as Real-World Robot Policies Evaluator
- Guava: Distilling Frontier VLMs into a Compact Agent through a Robotic Manipulation Harness
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
- Demonstration-Free Robotic Control via LLM Agents
- Towards the Harness of Embodied Agents
- A Pragmatic VLA Foundation Model
- TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM
- StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models
- 4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields
- ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs