Open-HumanWAM: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models
cs.CV, cs.RO
Submitted: 2026-11-04
Updated: 2026-11-10
Code: https://github.com/DAGroup-PKU/HumanNet
Project page: https://dagroup-pku.github.io/open-humanwam
Terminology
Sources
- AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
- Scalable Behavior Cloning with Open Data, Training, and Evaluation
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing
- InternW0: A Foundational Physical World Model for Efficient Real-World Interactions
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
- HumanNet: Scaling Human-centric Video Learning to One Million Hours
- Pelican-VLA 0.5: Attending Before Acting Benefits Generalization
- Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation
- Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising
- EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- EgoMimic: Scaling Imitation Learning via Egocentric Video
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
- ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining
- Causal World Modeling for Robot Control
- RoboICL: Embodied In-Context Learning with GPT-6 Astra
- G0.5: One Autoregressive Stream for Robot Reasoning and Action
- Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos
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