@seclink: Robot World Models (New Dimension, 0 Deduplication = New Information) Core Projects: - Awesome-WAM (OpenMOSS): Comprehensive Paper List of World Action Models, including DreamDojo (General-Purpose Robot World Model Learned from Human Videos) - awe…
Summary
Introduces two projects related to robot world models: Awesome-WAM (OpenMOSS) includes papers such as World Action Models and DreamDojo; awesome-physical-ai curates a collection of papers on VLA models, world models, and embodied foundation models (including NVIDIA Cosmos Predict2.5).
View Cached Full Text
Cached at: 05/29/26, 03:37 AM
Robot World Models (New Dimension, 0 Deduplication = Fresh Information)
Core Projects:
- Awesome-WAM (OpenMOSS): A comprehensive paper list on World Action Models, including DreamDojo (a general robot world model learned from human videos)
- awesome-physical-ai: A collection of papers on VLA models, world models, and embodied foundation models, including NVIDIA Cosmos Predict2.5
Similar Articles
@seclink: 5. Open-Source Acceleration of Robot World Models - NVIDIA Cosmos 3 + Isaac GR00T: Physical AI Foundation Models - AGIBOT Genie Sim 3.0: The First Fully Open-Source Robot Simulation Platform (Complete Open Source of Code, Data, and Assets) - VLA (Vision-…
Robot world models and simulation platforms are experiencing open-source acceleration: NVIDIA launched Cosmos 3 and Isaac GR00T physical AI foundation models, AGIBOT released Genie Sim 3.0, a fully open-source simulation platform, VLA models become mainstream for manipulation policies, collectively lowering the entry barrier for the robotics field.
World Models Explained: What Every AI Is Missing
The article explains the concept of world models in detail, comparing them to LLMs, introduces two major camps (pixel prediction and meaning prediction) and representative works such as Dreamer v3, GameNGen, Genie, and JEPA, discusses applications in autonomous driving and robotics, and points out that world models are a key component of physical AI.
@dotey: https://x.com/dotey/status/2053351712149135385
NVIDIA's Jim Fan spoke at Sequoia AI Ascent 2026, declaring the VLA architecture obsolete and proposing World Action Models (WAM) as a new paradigm for robotics. He introduced key technologies including DreamZero, EgoScale, and the neural simulator Dream Dojo.
@seclink: https://x.com/seclink/status/2057093284330430533
NVIDIA's head of robotics, Jim Fan, gave a public talk, advocating that robots should directly replicate the successful path of large language models. He proposed directions such as World Action Model (WAM), a data revolution based on human first-person video, and neural simulation, and predicted a 95% probability of achieving the endgame of general-purpose physical robots by 2040.
GreenWAM: A World Foundation Model for Robotics
GreenWAM 提出一个机器人世界基础模型，通过共享的解剖学动作空间联合训练 20 个机器人家族，使其既能作为世界模型预测动作后果，又能作为策略控制不同形态的机器人，并在多个基准上取得领先表现。