#World Models

Genie 4 adds audio and live Gemini control

Google for Developers debuted Genie 4 with native audio, photorealistic visuals from Gemini Omni Flash and live Gemini steering for real-time worlds.

World Labs Atlas bets on new view prediction

World Labs Atlas predicts new views from a few posed photos, turning three iPhone shots into Matrix-style bullet time and unifying generation with 3D reconstruction.

Today in AI: World Models Have No Recipe Yet

World Labs co-founder Justin Johnson says spatial AI still lacks a recipe as Marble bets on generative 3D worlds.

CLAP cross-embodiment action-conditioned video generation

CLAP trains action-conditioned video world models across human and robot video and matches single-embodiment models on DROID with zero-shot generalization.

Unified Framework for Decision-Informed Future Prediction

DA-WAM unifies predictive representation learning and action-conditioned future modeling for safer autonomous driving, outperforming existing methods on key benchmarks.

Yann LeCun's JEPA Cadence: Four Models in Three Years Across Two Labs

Since leaving Meta in November 2025, Yann LeCun has released V-JEPA 2.1, delivered five keynotes, co-authored two arXiv papers, and closed a $1.03 billion seed round. Here is the full output rate.

World Models: The Next Frontier Beyond LLMs

Odyssey CEO Oliver Cameron discusses the trillion-dollar opportunity in world models, their difference from LLMs, and applications in robotics and beyond.

Reactor's Ahmed Ahres on Real-Time Interactive Video

Ahmed Ahres of Reactor discusses the transformative potential of real-time interactive video, moving beyond static generative models to dynamic, programmable content.

Claude's Corner: Fern - From Sales AI to Robot World Models

Fern (formerly Ishiki Labs) is a YC W2026 startup that pivoted from socially-aware meeting AI to custom robot world models for RL policy training. Here is how they did it, and how you can build a clone.

Fei-Fei Li's $5B World Labs and the Spatial AI Race No One Agrees On

World Labs raised $1B at a $5B valuation in 2026. Here is how Fei-Fei Li's spatial AI approach diverges from LeCun's JEPA, DeepMind's Genie 3, and Nvidia's Cosmos.

Yann LeCun's AMI Labs Papers Give JEPA a Mathematical Foundation

Two arXiv preprints from AMI Labs, posted in May and June 2026, provide the first formal mathematical proof that JEPA-based world models can recover the true hidden structure of an environment, and precisely define the conditions current implementations still fail to meet.

Claude's Corner: One Robot - The Simulation Layer Robotics Has Been Missing

One Robot builds task-specific world model simulations from your robot's own data, letting robotics teams test and train VLA policies without physical hardware bottlenecks. Founded by ex-Tesla Dojo and NASA JPL engineers, they're betting that learned physics beats generic simulators for contact-rich manipulation.

Fei-Fei Li: Robots Need 'Spatial Intelligence' for Real-World Tasks

Fei-Fei Li and Yunus from Scenix discuss World Labs' vision for 'spatial intelligence' in AI and robotics, focusing on world models and the real-to-sim-to-real pipeline.

ABot-World-0: Real-time Video World Models

ABot-World-0 introduces a real-time video world model for long-horizon agent interaction, achieving 16 FPS at 720P with an optimized inference stack.

Fei-Fei Li on Spatial AI: Marble, $1.23B, and the Language Gap

World Labs has raised $1.23 billion and shipped Marble since February 2026. Here is what Fei-Fei Li told Bloomberg Tech about why language models miss half the AI problem.

World Models: The Key to AGI?

Ankit Gupta and Francois Chaubard of Y Combinator discuss world models as a key to solving AI's sample efficiency problem and potentially unlocking AGI.

Yann LeCun's $1B World Model Bet Puts Him Against His Mentors

LeCun raised $1.03B for AMI Labs in March 2026, betting that Hinton and Bengio are wrong: LLMs cannot reach AGI, and JEPA world models are the real path forward.

Baseten tripled to $13B while nobody was watching: inference infrastructure and sovereign AI defined this week's $7.3B in deals

Inference infrastructure and sovereign AI absorbed $2.2B and $500M this week, while total AI deals reached $7.3B across 61 rounds in the week of June 15, 2026.

How Fei-Fei Li Splits ‘World Models’ Into Three Distinct Functions

Fei-Fei Li’s June 2026 taxonomy places every world model into one of three functions: renderer, simulator, or planner. Here is what each one does and where World Labs’ Marble fits at the intersection.

LoopWM: A New Scaling Axis for World Models

Looped World Models (LoopWM) redefine world simulation with iterative refinement, achieving 100x parameter efficiency and establishing latent depth as a new scaling axis.

AWS Trainium Powers Next-Gen World Models

AI startups are increasingly choosing AWS Trainium to train world models, achieving unprecedented efficiency and sustained performance for complex simulations.

Yann LeCun Left Meta to Put $1.03B Behind His LLM Critique

Yann LeCun's position on LLMs hasn't changed since 2022 — but his stakes have. He left Meta in November 2025 after 12 years and, by March 2026, AMI Labs had raised $1.03 billion to build the world-model alternative at a $3.5 billion valuation.

Yann LeCun on World Models and the AI Revolution

AI pioneer Yann LeCun discusses how 'World Models' are key to the next AI revolution, emphasizing prediction, planning, and learning from real-world data.

Fei-Fei Li Clarifies 'World Models'

Fei-Fei Li offers a framework to define AI 'world models', distinguishing them from language models and tracing their roots to agent-environment interaction.

Fei-Fei Li's World Labs: $1.23B Raised, Marble Now Shipping

World Labs has raised $1.23 billion across two rounds since emerging from stealth in September 2024. Here is the full funding arc, investor composition, and product breakdown for Fei-Fei Li's spatial-intelligence venture.

Yann LeCun's AMI Labs Raises $1.03B to Build Beyond LLMs

AMI Labs, Yann LeCun's Paris-based AI company, closed a $1.03 billion seed round in March 2026 at a $3.5 billion pre-money valuation. Here is the full breakdown of why LeCun left Meta, who backed the raise, and what V-JEPA 2 is actually building.

YC Paper Club: Inference, Diffusion, World Models

YC Paper Club event featuring discussions on AI inference, diffusion models, and world models, with insights from Francois Chaubard and Tanishq Kumar.

Four labs, four acquisitions in five days: the consolidation signal hiding in plain sight

Anthropic, Mistral, Google DeepMind, and Meta each acquired an AI startup in the same week. None announced it as a trend. It is.

The Yann LeCun Halo Effect: His Alumni and Researchers Built a $55 Billion Empire. Where Are They Now?

Yann LeCun's alumni and researchers have collectively built companies worth over $55 billion. From AMI Labs ($4.5B) to Mistral AI ($13.7B) to Google DeepMind's CTO, here is where LeCun's network ended up and what they are building now.

LeCun Starts $1B AI Firm

Yann LeCun launches Advanced Machine Intelligence (AMI Labs) with $1.03B seed funding to build AI systems grounded in 'world models'.

New EB-JEPA Library Simplifies AI World Models

Meta AI's new EB-JEPA library offers accessible, single-GPU implementations for advanced AI world models, covering image, video, and planning tasks.

Luma AI Secures $900 Million Series C for Multimodal AGI Development

End-to-End Learning Reshapes Autonomous Driving

Sora 2: The Genesis of World Models and a New Creative Economy