WorldVLA: Towards Autoregressive Action World Model
Paper • 2506.21539 • Published • 40
World model
-
-
LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation
Paper • 2509.05263 • Published • 11 -
VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators
Paper • 2510.00406 • Published • 69 -
GigaBrain-0: A World Model-Powered Vision-Language-Action Model
Paper • 2510.19430 • Published • 55 -
WMPO: World Model-based Policy Optimization for Vision-Language-Action Models
Paper • 2511.09515 • Published • 21 -
Can World Simulators Reason? Gen-ViRe: A Generative Visual Reasoning Benchmark
Paper • 2511.13853 • Published • 37 -
Rethinking Video Generation Model for the Embodied World
Paper • 2601.15282 • Published • 46 -
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
Paper • 2601.15876 • Published • 92 -
WorldCompass: Reinforcement Learning for Long-Horizon World Models
Paper • 2602.09022 • Published • 21 -
When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning
Paper • 2602.08236 • Published • 9 -
K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model
Paper • 2602.19128 • Published • 7 -
Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models
Paper • 2603.15557 • Published • 30 -
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
Paper • 2604.04707 • Published • 198 -
Zero-shot World Models Are Developmentally Efficient Learners
Paper • 2604.10333 • Published • 6 -
MultiWorld: Scalable Multi-Agent Multi-View Video World Models
Paper • 2604.18564 • Published • 49 -
A Benchmark for Interactive World Models with a Unified Action Generation Framework
Paper • 2605.03941 • Published • 4 -
When to Trust Imagination: Adaptive Action Execution for World Action Models
Paper • 2605.06222 • Published • 41 -
Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics
Paper • 2605.12178 • Published • 65 -
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors
Paper • 2605.10434 • Published • 30 -
World Model for Robot Learning: A Comprehensive Survey
Paper • 2605.00080 • Published • 16 -
World Action Models: The Next Frontier in Embodied AI
Paper • 2605.12090 • Published • 73 -
YoCausal: How Far is Video Generation from World Model? A Causality Perspective
Paper • 2605.30346 • Published • 51 -
World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning
Paper • 2606.03603 • Published • 28 -
Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators
Paper • 2606.06476 • Published • 16 -
Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning
Paper • 2606.05645 • Published • 2 -
Latent Spatial Memory for Video World Models
Paper • 2606.09828 • Published • 71 -
AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing
Paper • 2606.09811 • Published • 15 -
World Model Self-Distillation: Training World Models to Solve General Tasks
Paper • 2606.12072 • Published • 15 -
Geometric Action Model for Robot Policy Learning
Paper • 2606.17046 • Published • 117 -
Looped World Models
Paper • 2606.18208 • Published • 466 -
WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents
Paper • 2606.18847 • Published • 7 -
World Action Models: A Survey
Paper • 2606.20781 • Published • 59 -
Qwen-AgentWorld: Language World Models for General Agents
Paper • 2606.24597 • Published • 167 -
World Value Models for Robotic Manipulation
Paper • 2606.24742 • Published • 8 -
In-Context World Modeling for Robotic Control
Paper • 2606.26025 • Published • 61 -
Orca: The World is in Your Mind
Paper • 2606.30534 • Published • 438 -
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
Paper • 2607.00248 • Published • 30 -
Infinite Worlds with Versatile Interactions
Paper • 2607.07534 • Published • 46 -
GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch
Paper • 2607.13960 • Published • 25 -
BadWAM: When World-Action Models Dream Right but Act Wrong
Paper • 2607.15207 • Published • 44 -
From Pixels to States: Rethinking Interactive World Models as Game Engines
Paper • 2607.14076 • Published • 31 -
AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report
Paper • 2607.18367 • Published • 63 -
Generative World Renderer at the Speed of Play
Paper • 2607.18703 • Published • 86 -
StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation
Paper • 2607.26754 • Published • 19 -
QQWorld: Quantile-Quantile Matching for World Model Regularization
Paper • 2607.28415 • Published • 31 -
WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity
Paper • 2608.02603 • Published • 34 -
SimWAM: A Simple World Action Model for End-to-End Autonomous Driving
Paper • 2608.07468 • Published • 106 -
Addressable Memory for Video World Models
Paper • 2608.07408 • Published • 17 -
PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives
Paper • 2608.13552 • Published • 49 -
Marionette: Predicting World States, Rendering Geometry, Painting Appearance
Paper • 2608.14530 • Published • 34 -
EnvHarness: Awakening Static Worlds for Agent Learning
Paper • 2608.19880 • Published • 220 -
τ_0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation
Paper • 2608.16885 • Published • 17 -
ReWorld: An Interactive World Model with Long-Horizon Memory
Paper • 2608.23565 • Published • 25 -
Code World Model: Coding Agent as World Brain
Paper • 2608.25927 • Published • 41 -
GameWAM: A World Action Model for Video Games
Paper • 2608.26200 • Published • 36 -
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models
Paper • 2608.25518 • Published • 138 -
Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning
Paper • 2608.27549 • Published • 48 -
H3-World: Turning Language Understanding into World Control
Paper • 2609.01560 • Published • 54 -
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
Paper • 2609.02886 • Published • 114 -
WorldReward: Reward Modeling for Camera-Conditioned World Models
Paper • 2609.03952 • Published • 28 -
OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining
Paper • 2609.07398 • Published • 81 -
Scaling Automatic Research Agents via World Models
Paper • 2608.12564 • Published • 482 -
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
Paper • 2609.14858 • Published • 334 -
Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents
Paper • 2609.29892 • Published • 34 -
CompoWorld: Compositional Environment Scaling for General Agents
Paper • 2609.33665 • Published • 42 -
Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence
Paper • 2609.35432 • Published • 113 -
WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents
Paper • 2609.40325 • Published • 106 -
EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making
Paper • 2609.38334 • Published • 75 -
Long-WAM: Scaling the Context of World-Action Models
Paper • 2610.10528 • Published • 113 -
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
Paper • 2610.08215 • Published • 62 -
AnyGoal: On World Model Generalization Beyond Expert Rollouts
Paper • 2610.26844 • Published • 44 -
State World Models: Execute the Rules, Generate the Pixels
Paper • 2610.26811 • Published • 17