---
title: "AlphaSignal Video: World Models News"
url: "https://alphasignal.ai/topic/video/world-models"
description: "Latest AI and machine learning news about World Models (Video) on AlphaSignal."
---

# AlphaSignal Video: World Models News

Latest AI and machine learning news about World Models (Video) on AlphaSignal.

## Articles

- [Runway's Project Continuum Turns Your Desktop Into Live AI-Generated Video](https://alphasignal.ai/news/runway-s-project-continuum-turns-your-desktop-into-live-ai-generated-video.md) (2026-10-01)
- [Runway's Solaris Ditches Code to Build Apps as Live Video](https://alphasignal.ai/news/runway-s-solaris-ditches-code-to-build-apps-as-live-video.md) (2026-09-30)
- [Robotic World Models Break Down After Just 10 Planning Steps](https://alphasignal.ai/news/robotic-world-models-break-down-after-just-10-planning-steps.md) (2026-09-30)
- [NVIDIA's Physis-Lang Teaches Video AI Real Physics, Beats Google's Veo 3.1](https://alphasignal.ai/news/nvidia-s-physis-lang-teaches-video-ai-real-physics-beats-google-s-veo-3-1.md) (2026-09-29)
- [Microsoft's Quine Ranked Pancreatic Cancer Compounds in One Weekend](https://alphasignal.ai/news/microsoft-s-quine-ranked-pancreatic-cancer-compounds-in-one-weekend.md) (2026-09-29)
- [Yann LeCun's AD-E2E-JEPA Plans Driving Trajectories 100x Faster Without Policy Training](https://alphasignal.ai/news/yann-lecun-s-ad-e2e-jepa-plans-driving-trajectories-100x-faster-without-policy.md) (2026-09-28)
- [Pablo Dawson's MiniMax-H3 LoRA Spins a Full 360 Orbit From One Photo](https://alphasignal.ai/news/pablo-dawson-s-minimax-h3-lora-spins-a-full-360-orbit-from-one-photo.md) (2026-09-27)
- [Google's Gemini and Veo Team Up to Generate Coherent 10-Minute Videos](https://alphasignal.ai/news/google-s-gemini-and-veo-team-up-to-generate-coherent-10-minute-videos.md) (2026-09-24)
- [Odyssey's Agora-2 Lets 20 Players Share One AI-Generated World](https://alphasignal.ai/news/odyssey-s-agora-2-lets-20-players-share-one-ai-generated-world.md) (2026-09-24)
- [Tencent's WorldCrafter Remembers Generated Worlds 47.6% Better on Revisit](https://alphasignal.ai/news/tencent-s-worldcrafter-remembers-generated-worlds-47-6-better-on-revisit.md) (2026-09-21)
- [Odyssey Builds One AI Backbone to Control Robots, Cars, Drones, and Games](https://alphasignal.ai/news/odyssey-builds-one-ai-backbone-to-control-robots-cars-drones-and-games.md) (2026-09-15)
- [CMU's ModAR Beats a 6B Robot Model Using 200 Times Fewer Parameters](https://alphasignal.ai/news/cmu-s-modar-beats-a-6b-robot-model-using-200-times-fewer-parameters.md) (2026-09-15)
- [Runway Rebuilds Gen-4.5 to Stream Video Frames in Real Time](https://alphasignal.ai/news/runway-rebuilds-gen-4-5-to-stream-video-frames-in-real-time.md) (2026-09-10)
- [World Labs' Atlas Unifies 3D Reconstruction and Video Generation in One Model](https://alphasignal.ai/news/world-labs-atlas-unifies-3d-reconstruction-and-video-generation-in-one-model.md) (2026-09-08)
- [Unitree's UnifoLM-X2-1.0 Lets Humanoid Robots Fight With No Human Control](https://alphasignal.ai/news/unitree-s-unifolm-x2-1-0-lets-humanoid-robots-fight-with-no-human-control.md) (2026-09-07)
- [Runway's GWM Worlds 2 Streams Interactive AI Worlds at 720p in Real Time](https://alphasignal.ai/news/runway-s-gwm-worlds-2-streams-interactive-ai-worlds-at-720p-in-real-time.md) (2026-09-03)
- [Utopia Gives Open-Source RAG a Memory of What Was True When](https://alphasignal.ai/news/utopia-gives-open-source-rag-a-memory-of-what-was-true-when.md) (2026-09-02)
- [World Labs' Atlas Beats Specialized 3D Models With One Omni Model](https://alphasignal.ai/news/world-labs-atlas-beats-specialized-3d-models-with-one-omni-model.md) (2026-09-01)
- [Runway's Solaris Renders Interactive Apps as Live Video, No Code Needed](https://alphasignal.ai/news/runway-s-solaris-renders-interactive-apps-as-live-video-no-code-needed.md) (2026-08-31)
- [Oxford and MIT Researchers Argue Vision Alone Could Unlock General AI](https://alphasignal.ai/news/oxford-and-mit-researchers-argue-vision-alone-could-unlock-general-ai.md) (2026-08-26)
- [Odyssey's CaliBench Catches Top Video AI Models Failing as Stochastic Simulators](https://alphasignal.ai/news/odyssey-s-calibench-catches-top-video-ai-models-failing-as-stochastic-simulators.md) (2026-08-19)
- [NVIDIA's Hydra-0 Teaches Any Robot by Watching Human Hands Move](https://alphasignal.ai/news/nvidia-s-hydra-0-teaches-any-robot-by-watching-human-hands-move.md) (2026-08-18)
- [Abiray Brings MiniMax H3 Video AI to Consumer GPUs With 1M Downloads](https://alphasignal.ai/news/abiray-brings-minimax-h3-video-ai-to-consumer-gpus-with-1m-downloads.md) (2026-08-03)
- [Sakana AI's Dream-Cubed Beats Real Minecraft Terrain 67% of the Time](https://alphasignal.ai/news/sakana-ai-s-dream-cubed-beats-real-minecraft-terrain-67-of-the-time.md) (2026-07-29)
- [Reka's WMGym Judges World Models on Decision-Making, Not Pretty Pixels](https://alphasignal.ai/news/reka-s-wmgym-judges-world-models-on-decision-making-not-pretty-pixels.md) (2026-07-28)
- [Lightricks Ships LTX-2.5, a 22B Open Video Model With Native Audio](https://alphasignal.ai/news/lightricks-ships-ltx-2-5-a-22b-open-video-model-with-native-audio.md) (2026-07-23)
- [Google DeepMind's Genie Now Turns Real Street View Into Interactive AI Worlds](https://alphasignal.ai/news/google-deepmind-s-genie-now-turns-real-street-view-into-interactive-ai-worlds.md) (2026-07-10)
- [Ant Group's LingBot-World 2.0 Runs Open-Source World Models for a Full Hour](https://alphasignal.ai/news/ant-group-s-lingbot-world-2-0-runs-open-source-world-models-for-a-full-hour.md) (2026-07-09)
- [Ant Group's LingBot-VA Teaches Robots to Imagine Before Acting](https://alphasignal.ai/news/ant-group-s-lingbot-va-teaches-robots-to-imagine-before-acting.md) (2026-07-09)
- [Ant Group's LingBot-World Turns a Single Image Into a Playable Open-Source World](https://alphasignal.ai/news/ant-group-s-lingbot-world-turns-a-single-image-into-a-playable-open-source-world.md) (2026-07-08)
- [Kyutai's MIRA Runs Playable Rocket League Inside a 5B Neural Network](https://alphasignal.ai/news/kyutai-s-mira-runs-playable-rocket-league-inside-a-5b-neural-network.md) (2026-07-06)
- [NVIDIA's Cosmos3-Edge Squeezes a Robot Brain Into a 4B On-Device Model](https://alphasignal.ai/news/nvidia-s-cosmos3-edge-squeezes-a-robot-brain-into-a-4b-on-device-model.md) (2026-07-01)
- [Runway's GWM-1 Cuts MIXI's 21-Day Video Production Down to Three](https://alphasignal.ai/news/runway-s-gwm-1-cuts-mixi-s-21-day-video-production-down-to-three.md) (2026-06-30)
- [World Labs Brings Marble Pro Free to Developers at SIGGRAPH 2026](https://alphasignal.ai/news/world-labs-brings-marble-pro-free-to-developers-at-siggraph-2026.md) (2026-06-25)
- [General Intuition Raises $320M Turning 2.5B Gaming Clips Into Robot Brains](https://alphasignal.ai/news/general-intuition-raises-320m-turning-2-5b-gaming-clips-into-robot-brains.md) (2026-06-25)
- [Physical Intelligence and NVIDIA's SC3-Eval Replaces Real Robot Testing With AI](https://alphasignal.ai/news/physical-intelligence-and-nvidia-s-sc3-eval-replaces-real-robot-testing-with-ai.md) (2026-06-18)
- [Odyssey Raises $310M to Build the GPT-3 Moment for World Models](https://alphasignal.ai/news/odyssey-raises-310m-to-build-the-gpt-3-moment-for-world-models.md) (2026-06-17)
- [NVIDIA's Cosmos 3 Unifies Robot Reasoning, Video, and Action in One Open Model](https://alphasignal.ai/news/nvidia-s-cosmos-3-unifies-robot-reasoning-video-and-action-in-one-open-model.md) (2026-06-17)
- [Tencent's HY-World 1.5 Open-Sources Real-Time AI World Generation at 24 FPS](https://alphasignal.ai/news/tencent-s-hy-world-1-5-open-sources-real-time-ai-world-generation-at-24-fps.md) (2026-06-10)
- [World Labs' ICARE Runs a Full 3D Browser Game on 100 Million Splats](https://alphasignal.ai/news/world-labs-icare-runs-a-full-3d-browser-game-on-100-million-splats.md) (2026-06-09)
- [xAI's Grok Imagine Video 1.5 Tops Leaderboard and Beats Google Veo](https://alphasignal.ai/news/xai-s-grok-imagine-video-1-5-tops-leaderboard-and-beats-google-veo.md) (2026-06-08)
- [Tsinghua's WorldFly Teaches Drones to Imagine Around Corners Before Flying](https://alphasignal.ai/news/tsinghua-s-worldfly-teaches-drones-to-imagine-around-corners-before-flying.md) (2026-06-04)
- [A 22-Author Team Argues AI Must Simulate Biology, Not Just Read It](https://alphasignal.ai/news/a-22-author-team-argues-ai-must-simulate-biology-not-just-read-it.md) (2026-06-04)
- [Microsoft Research Finds Hidden Physics Inside Video Diffusion Models](https://alphasignal.ai/news/microsoft-research-finds-hidden-physics-inside-video-diffusion-models.md) (2026-06-03)
- [NVIDIA's Cosmos 3 Collapses Four Robot AI Models Into One Open Architecture](https://alphasignal.ai/news/nvidia-s-cosmos-3-collapses-four-robot-ai-models-into-one-open-architecture.md) (2026-06-02)
- [Brown and NYU Researchers Map 3D Vision's Chaotic Evolution Into One Unified Guide](https://alphasignal.ai/news/brown-and-nyu-researchers-map-3d-vision-s-chaotic-evolution-into-one-unified.md) (2026-06-02)
- [AirDreamer Teaches Drones to Navigate Unknown Rooms Without Human Engineering](https://alphasignal.ai/news/airdreamer-teaches-drones-to-navigate-unknown-rooms-without-human-engineering.md) (2026-06-02)
- [NVIDIA's Cosmos 3 Merges Robot Reasoning and Video Into One Open Model](https://alphasignal.ai/news/nvidia-s-cosmos-3-merges-robot-reasoning-and-video-into-one-open-model.md) (2026-06-01)
- [Runway Bets $200M on London to Build World Models Beyond Video](https://alphasignal.ai/news/runway-bets-200m-on-london-to-build-world-models-beyond-video.md) (2026-06-01)
- [Runway Joins NVIDIA's Cosmos 3 Coalition to Build Open World Models for Robots](https://alphasignal.ai/news/runway-joins-nvidia-s-cosmos-3-coalition-to-build-open-world-models-for-robots.md) (2026-06-01)