#world-models
- NVIDIA Releases Cosmos 3: Open Omnimodal World Foundation Model for Physical AI NVIDIA research
- Kairos: A Native World Model Stack for Physical AI ACE Robotics research
- Orca: BAAI's General World Foundation Model Trained on 125K Hours of Video BAAI research
- Alaya-EVOKE: From Linear-Scaling Supervision to Endless World research
- Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds research
- Training Object Permanence in World Models research
- GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture GigaAI research
- World Action Models: A Survey National University of Singapore research
- Qwen-AgentWorld: Language World Models for General Agents across Seven Environments Alibaba/Qwen research
- GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation GigaAI research
- AlayaWorld: Long-Horizon and Playable Video World Generation (Open-Source) AlayaWorld Team research
- Alibaba Amap Launches ABot-World Studio: Infinite Interactive Video and 3D World Generation on a Single GPU Alibaba video
- DreamX-Phi 1.0 wins WorldArena 2.0 Track 1 with action-conditioned video world model for robotic manipulation Alibaba research
- Alaya-EVOKE: From Linear-Scaling Supervision to Endless World Zhejiang University research
- τ₀-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation Shanghai Innovation Institute research
- EchoWM: Open and Enterable Omnimodal World Models JD.com research
- VGI-Bench: Probing Visual Intelligence in Video Generation Models research
- Runway introduces Solaris, its first Interface World Model Runway video
- Runway previews real-time video generation: streaming video steered as it is described Runway video
- Black Forest Labs ships FLUX 3 Action, an open-weights 7B world-action model for robot control Black Forest Labs video
- InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization InternRobotics research
- Multiplayer Interactive World Models with Representation Autoencoders research
- ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Alibaba AMAP CV Lab research
- Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models NUS research
- WMRL: scaling automatic research agents via world models University of Illinois / NVIDIA research
- Vidu S2: real-time interactive, editable, and spatial video generation ShengShu Intelligence research
- WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory Tencent ARC Lab research
- Causal Forcing++: 2-Step Distillation Enables Real-Time Interactive Video Generation Tsinghua University research
- SANA-WM: Minute-Scale 720p World Modeling on a Single GPU NVIDIA research
- DreamX-World 1.0: General-Purpose Interactive World Model with 6DoF Camera Control AMAP-ML (Alibaba Maps AI Lab) research
- From Pixels to States: Rethinking Interactive World Models as Game Engines research
- N0-TWAM: Scaling Tactile-Native World-Action Model for Contact-Rich Manipulation NeoteAI / Fudan TEAI research
- WorldClaw: Agentic 3D Open-World Generation at Scale Tencent Hunyuan research
- Runway introduces GWM Worlds 2, a real-time interactive world model Runway video
- Programmable World Model: agent-programmed persistent state for interactive video Alaya Lab research
- Can MiniMax-H3 Reason About the Physical World? research
- Google Project Genie World Model Now Simulates Real Places Using Street View Google DeepMind research
- Astra: RL-Trained VLM Queries World Simulator for Spatial Reasoning research
- Hallucination in World Models is Predictable and Preventable UC San Diego research
- WorldDirector: Controllable World Simulator with Persistent Dynamic Object Memory research
- HarnessEval-W: Agentifying the Evaluation of Visual Worlds NTU / MirroS-Lab consortium research
- ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models research
- ReWorld: An Interactive World Model with Long-Horizon Memory TongyiLab (Alibaba) research
- PAWBench: How Far Are We from Probabilistically Aligned World Modeling? research
- Echo-Memory: Controlled Study of Memory Mechanisms in Action-Conditioned Video World Models Microsoft Research research
- PhysisForcing: Physics-Reinforced World Models Improve Robot Manipulation Success by 50% Peking University / NVIDIA research
- Quo Vadis, World Modeling? Towards Interactive World Proxies for Continually Improving Agents Shanghai AI Laboratory research
- WorldClaw generates agentic 3D open worlds at scale Tencent Hunyuan research
- EnvACE internalizes environment dynamics via world rehearsal for agentic RL research
- DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation Alibaba Group research
- ByteDance founder personally leads real-time spatial-video world model, launch possible as soon as October ByteDance video