World Models

MessyMem: Learning-from-Doing Memory for Mobile Manipulation

World Models, Robotics, and the Future of 3D AI

Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Models

Write Things Down (Stratechery Article 9-8-2026)

OpenAI Researchers on the Future of Mathematical Reasoning

GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture

Fei Fei Li: The Race to Build World Models For AI

TourPhysics: Bringing Physics to World Models for Exploration and Manipulation from a Single Image

WISE: World-model-guided Imagination Scheduling for Efficient Post-training of Vision-Language-Action Models

Daniel Litt: The Mathematician's Guide to AI

Why 1,200 AI Agents Started Working Together | Ryan Greenblatt

CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators

Riemann-1.0: An Embodied World Action Model for Physical AI

R3: Training Robots to Reason in Natural Language via Reinforcement Learning

TrAct: Bridging Robot Control and Visual Prediction with Visual Tracks

GeniWorld: A Generalizable Interactive World Model for Robotic Manipulation via Visual Actions

DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation

Hydra-0: Action Flow for Generalist World Modeling and Control

Import AI 469: Science AI; RSI simulator; and Zuck's technological pessimism

ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models

H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models

150. 对英伟达研究副总裁刘洺堉的4小时访谈：Cosmos 3、世界模型、武术、黄仁勋影响我的，和你不需要击败所有对手

WorldBagel: Uncovering the Power of Unified Multimodal Models for Vision-Language-Action-World Modeling

Addressable Memory for Video World Models

XEWorld: Can Action-Conditioned World Models Generalize to Unseen Robot Embodiments?

ω-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation

20VC: The Best AI Companies Have Unique Data Acquisition Strategies | Will Simile Kill Kalshi, Polymarkets and NASDAQ | How to Sign Fortune 500 Companies As Customers in Weeks with Joon Sung Park, Simile

Building the Automated AGI Lab: Core Automation's Jerry Tworek and Rohan Anil

ContactFlow: A video action conditioning that transfers across embodiments

Fei-Fei Li on Spatial Intelligence and Robotics

N0-TWAM: Scaling Tactile-Native World-Action Model for Contact-Rich Manipulation

147. 和蚂蚁灵波沈宇军聊：机器人原生基础模型、大脑和本体的关系、预训练与数据scale up、老师汤晓鸥

Masked Visual Actions for Unified World Modeling

World Models, Explained

172: Momenta IPO后再访曹旭东：就是想做没有尽头的AI

Demis Hassabis Says AGI Arrives in 2 to 5 Years. Here Is the Full Picture

VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment

RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation

In-Context World Modeling for Robotic Control

Series B activity: June 2026

170: 【具身季报 26Q2】世界模型大风不停，和不想被贴标签的人

Axios Pro Rata: Remembering Om

AI Is Crossing the Frontier of Human Knowledge | Kevin Weil

SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation

SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors

The data black hole at the center of AI

Kairos: A Native World Model Stack for Physical AI

Biohub: The Future of Biology is Open-Source with Co-Founders Mark Zuckerberg, Priscilla Chan, and Head of Science Alex Rives

MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation

Raj Patel — Inside Human Archive (humanarchive.ai)

NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation

🌎 Nvidia's world move

🚨 Hassabis sounds alarm

165: 英伟达 GEAR 高深远：世界模型、自进化循环、DreamDojo

Eric Jang – Building AlphaGo from scratch

Beyond Bigger Models: Recursion As The Next Scaling Law In AI

Jim Fan — VLAs Are Dead, WAMs Are Next

MotuBrain: An Advanced World Action Model for Robot Control

RopeDreamer: A Kinematic Recurrent State Space Model for Dynamics of Flexible Deformable Linear Objects

Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising

dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model

Cortex 2.0: Grounding World Models in Real-World Industrial Deployment

Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models

20VC: DeepMind's Demis Hassabis on Why AGI is Bigger than the Industrial Revolution | Why LLMs Will Not Commoditise & We Have Not Hit Scaling Laws | Bottlenecks in AI & The Energy Crisis Caused By AI | Whether AI Will Do More to Harm or Help Inequality

Jack Dorsey: Every Company Can Now Be a Mini-AGI

ForeAct: Steering Your VLA with Efficient Visual Foresight Planning

157: 具身季报26Q1：人形再思考、英伟达世界模型、高自由度灵巧手

Sergey Levine - Building LLMs for the Physical World - [Invest Like the Best, EP.465]

DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA

Import AI 451: Political superintelligence; Google's society of minds, and a robot drummer

Scaling World Model for Hierarchical Manipulation Policies

VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model

Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining

👋 Sora sunsets

DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos

Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models

OmniVTA: Visuo-Tactile World Modeling for Contact-Rich Robotic Manipulation

133. 对谢赛宁的7小时马拉松访谈：世界模型、逃出硅谷、AMI Labs、两次拒绝Ilya、杨立昆、李飞飞和42

Building The Chip That Could Unlock AGI | Naveen Rao

Fei-Fei Li (World Labs) — On Creating Large World Models

Michael Levin: Reality is an Illusion - Alien Intelligence, Biology, Life | Lex Fridman Podcast #486

Interview with DeepMind's Jie Tan: Robotics, Cross-Embodiment, World Models, Gemini Robotics 1.5, and Google

Fei-Fei Li & Justin Johnson (World Labs) — After LLMs: Spatial Intelligence and World Models

The Godmother of AI on jobs, robots & why world models are next | Dr. Fei-Fei Li

OpenAI Sora 2 Team: How Generative Video Will Unlock Creativity and World Models

#38 Karol Hausman & Kevin Black: Building A Brain For Any Robot | AI Eating The Physical World

【BAAI2025】 Building Physical Intelligence | Karol Hausman

The Race to Create General-Purpose Robots | Karol Hausman & Lachy Groom on TBPN