← Back to datasets

qsun2001/world_model

2026 Datasets

Preview for qsun2001/world_model

Dataset Analysis

Hugging Face dataset: qsun2001/world_model

Provenance

Collected from huggingface-datasets.

downloads=3152, likes=0

Related papers

$μ_0$: A Scalable 3D Interaction-Trace World Model $τ_0$-WM: A Unified Video-Action World Model for Robotic Manipulation $ω$-EVA: Envision, Verify, and Act with Latent Interactive World Models 3D-Belief: Embodied Belief Inference via Generative 3D World Modeling A 3D Isovist World Model -- Revealing a City's Unseen Geometry and Its Emergent Cross-City Signature A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners A geometric relation of the error introduced by sampling a language model's output distribution to its internal state AGEL-Comp: A Neuro-Symbolic Framework for Compositional Generalization in Interactive Agents AGWM: Affordance-Grounded World Models for Environments with Compositional Prerequisites AR Forcing: Towards Long-Horizon Robot Navigation World Model ARB4WM: An Adversarial Robustness Benchmark for World Models in Continuous Control ARIS: Agentic and Relationship Intelligence System for Social Robots ActWorld: From Explorable to Interactive World Model via Action-Aware Memory Active Inference as the Test-Time Scaling Law for Physical AI Agents Active Inference: A method for Phenotyping Agency in AI systems?AdaReP:Adaptive Re-Planning under Model Mismatch for Neural World-Model Predictive Control AdaptiveLoad: Towards Efficient Video Diffusion Transformer Training AffectVerse: Emotional World Models for Multimodal Affective Computing Affective Music Recommendation: A Rollout-Based World Model for Offline Preference Optimization Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model Attacking the Trusted Imagination: Oracle-Level Integrity Attacks on Imagine-then-Act World Models Autonomous Video Generation with Counterfactual Controllability for Self-Evolving World Models Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents BRo-JEPA: Learning Modular Arithmetic in Latent Space BadDreamer: Transferable Backdoor Attacks against Video World Models for Autonomous Driving Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression Business World Model CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization COMAP: Co-Evolving World Models and Agent Policies for LLM Agents Can In-Context Learning Support Intrinsic Curiosity?Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation Causal Object-Centric Models for Planning with Monte Carlo Tree Search Causal Reward World Models: Zero-shot Reward Design for Automated Skill Generation Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models CausalDrive: Real-time Causal World Models for Autonomous Driving Certified World Models: Predictability Across Configuration, Horizon, and Resolution Chreode: A Cell World Model for One-Step Temporal Dynamics and Perturbation Prediction ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care Data Closing the Motion Execution Gap: From Semantic Motion Task Constraints to Kinematic Control CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving Coding Agent Is Good As World Simulator Conformal Orbit-Valid Trust Horizons for Equivariant World Models Current World Models Lack a Persistent State Core DREAM-Chunk: Reactive Action Chunking with Latent World Model Data-Asymmetric Latent Imagination and Reranking for 3D Robotic Imitation Learning DeTrack: A Benchmark and Altitude-Aware Dual World Model for Drone-embodied Tracking DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation Demo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation DexFuture: Hierarchical Future-State Visuomotor Targeting for Bimanual Dexterous Tool Use DiLA: Disentangled Latent Action World Models Diffusion Transformer World-Action Model for AV Scene Prediction DisCo: World Models with Discrete Camera Motion Control Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving Distilling Game Code World Model Generation into Lightweight Large Language Models Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models Do multimodal models imagine electric sheep?Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination DreamX-World 1.0: A General-Purpose Interactive World Model Dreaming Of Others: Latent Teammate Modeling In World Models For Multi-Agent Reinforcement Learning Dreaming Smoothly and Sample Efficiently with Gradient Penalized Latent Dynamics Drift-Resistant Navigation World Model with Anchored Epipolar Guidance Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout Dual-Channel Grounded World Modeling (DCGWM): Structural Prevention of Objective Interference Collapse via Heterogeneous External Grounding with Inward-Only Gradient Flow DynaWM: Dynamics-Aware Distillation with World Model and Momentum Targets for Smooth Locomotion over Continuous Stairs DynoSLAM: Dynamic SLAM with Generative Graph Neural Networks for Real-World Social Navigation EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields EV-WM: Event-Verified World Models for Long-Horizon Robotic Manipulation Echo-Memory: A Controlled Study of Memory in Action World Models Efficient Agentic Reasoning Through Self-Regulated Simulative Planning EgoCS-400K: An Egocentric Gameplay Dataset for World Models EgoExo-WM: Unlocking Exo Video for Ego World Models Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue Embody4D: A Generalist Data Engine for Embodied 4D World Modeling Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision Emotion-Conditioned Short-Horizon Human Pose Forecasting with a Lightweight Predictive World Model EponaV2: Driving World Model with Comprehensive Future Reasoning Exact equivariance, kept through training, buys zero-shot generalisation across the symmetry group Executable World Models for ARC-AGI-3 in the Era of Coding Agents Explainably Safe Reinforcement Learning Feat2Go: Visual Feature-Grounded Value Estimation for Embodied Reinforcement Learning Feedback World Model Enables Precise Guidance of Diffusion Policy FlowMPC: Improving Flow Matching policies with World Models FlowMo-WM: A World Model with Object Momentum and Hidden Ambient Drift FlyMirage: A Fully Automated Generation Pipeline for Diverse and Scalable UAV Flight Data via Generative World Model Flying by Inference: Active Inference World Models for Adaptive UAV Swarms Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents From Pixels to Concepts: Growing Rich 3D Semantic Scene Graph Forests utilizing Foundation Models From Zero to Hero: Training-Free Custom Concept Spawning in World Models Future Dynamic 3D Reconstruction: A 3D World Model with Disentangled Ego-Motion GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation GEM: Gaussian Evolution Model for Occupancy Forecasting and Motion Planning GEM: Generating LiDAR World Model via Deformable Mamba Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players GaussianDream: A Feed-Forward 3D Gaussian World Model for Robotic Manipulation Generalization of World Models under Environmental Variability for Vision-based Quadrotor Navigation GeoSem-WAM: Geometry- and Semantic-Aware World Action Models GeoStream: Toward Precise Camera Controlled Streaming Video Generation GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs HEAT: Heterogeneous End-to-End Autonomous Driving via Trajectory-Guided World Models HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation HOLO-MPPI: Multi-Scenario Motion Planning via Hierarchical Policy Optimization HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training Holo-World: Unified Camera, Object and Weather Control for Video World Model HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation How Mobile World Model Guides GUI Agents?How Should World Models Be Evaluated? A Decision-Making-Centric Position IDOL: Inverse-Dynamics-Guided Future Prediction for End-to-End Autonomous Driving IFPV: An Integrated Multi-Agent Framework for Generative Operational Planning and High-Fidelity Plan Verification IMWM: Intuition Models Complement World Models for Latent Planning IOI: Decoupling Kinematics and Physics for Interactive World Models Identifiability Without Gaussianity: Symbolic World Models and Near-Infinite Temporal Consistency ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?Imagine to Ensure Safety in Hierarchical Reinforcement Learning Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World Models Imperfect World Models are Exploitable Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models Inference-time Policy Steering via Vision and Touch Intercepting the Future: Latent-Space Predictive World Model for Dynamic VLA Manipulation Inverting the Bellman Equation: From $Q$-Values to World Models Is Your Driving World Model an All-Around Player?JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning Kairos: A Native World Model Stack for Physical AI LASER: Learning Active Sensing for Continuum Field Reconstruction LEIA: Learned Environment for Interactive Architected Materials LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation LaST-HD: Learning Latent Physical Reasoning from Scalable Human Data for Robot Manipulation LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies LaWM: Least Action World Models for Long-Horizon Physical Consistency from Visual Observations Latent Geometry Beyond Search: Amortizing Planning in World Models Latent Spatial Memory for Video World Models Latent State Design for World Models under Sufficiency Constraints Learning Action-Conditional and Object-Centric Gaussian Splatting World Models for Rigid Objects Learning Multi-Timescale Abstractions for Hierarchical Combinatorial Planning Learning Visual Feature-Based World Models via Residual Latent Action Learning a Particle Dynamics Model with Real-world Videos Lifting Embodied World Models for Planning and Control Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models LoViF 2026 The First Challenge on Holistic Quality Assessment for 4D World Model (PhyScore)MAD: Mapping-Aware World Models for Agile Quadrotor Flight MBench: A Comprehensive Benchmark on Memory Capability for Video World Models MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments MODIP: Efficient Model-Based Optimization for Diffusion Policies MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model Making Foresight Actionable: Repurposing Representation Alignment in World Action Models Mask World Model: Predicting What Matters for Robust Robot Policy Learning Mem-World: Memory-Augmented Action-Conditioned World Models for Persistent Robot Manipulation MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent Manifolds MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold Monte Carlo Pass Search: Using Trajectory Generation for 3D Counterfactual Pass Evaluation in Football MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation MotuBrain: An Advanced World Action Model for Robot Control NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation Nano World Models: A Minimalist Implementation of Future Video Prediction NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Horizon Co-Creative Audio Drama NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigation NavWM: A Unified Navigation World Model for Foresight-Driven Planning Network-Efficient World Model Token Streaming Next Forcing: Causal World Modeling with Multi-Chunk Prediction Nous: A Predictive World Model for Long-Term Agent Memory OSCAR: Omni-Embodiment Action-Conditioned World Model for Robotics OccDirector: Language-Guided Behavior and Interaction Generation in 4D Occupancy Space OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation One Image is All You Need: Agentic One-Shot Image Generation via Text-Based World Models for Long-Tail Spatial Perception One Lens, Many Worlds : A Capability-Typed Interface for World-Model Interpretability One Transit Is All You Need: Detecting Exoplanets Through Learned Stellar Behaviour with EXOVEIL OptiWorld: Optimal Control for Video World Generation under Physical Constraints OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence PEACE: A Planner-Executor Agent with Constraint Enforcement for UAVs PH-Dreamer: A Physics-Driven World Model via Port-Hamiltonian Generative Dynamics PLUME: Probabilistic Latent Unified World Modeling and Parameter Estimation for Multi-Finger Manipulation PRISM: PRior-guided Imagination Sampling in world Models PROWL: Prioritized Regret-Driven Optimization for World Model Learning PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesis PanoWorld: Geometry-Consistent Panoramic Video World Modeling PatchWorld: Gradient-Free Optimization of Executable World Models PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space PhyGround: Benchmarking Physical Reasoning in Generative World Models PhyWorld: Physics-Faithful World Model for Video Generation Phys-JEPA: Physics-Informed Latent World Models for Multivariate Time-Series Forecasting Physical Object Understanding with a Physically Controllable World Model Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling Physics-Aware Sparse Learning and Selective Online Adaptation for Euler-Lagrange Robot Dynamics Physics-IQ Verified PiL-World: A Chunk-Wise World Model for VLA Policy-in-the-Loop Evaluation Pixels to Proofs: Probabilistically-Safe Latent World Model Control via Parallel Conformal Robust MPC Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts Predictive but Not Plannable: RC-aux for Latent World Models PriorZero: Bridging Language Priors and World Models for Decision Making Prisma-World: Camera-Controllable Multi-Agent Video World Model ProDrive: Proactive Planning for Autonomous Driving via Ego-Environment Co-Evolution ProPlay: Procedural World Models for Self-Evolving LLM Agents Probing the Impact of Scale on Data-Efficient, Generalist Transformer World Models for Atari Quantitative Video World Model Evaluation for Geometric-Consistency Quantum Cinema: An Interactive Cinematic Exploration of Quantum Computing Hardware via Generative World Models Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation ReactSim-Bench: Benchmarking Reactive Behavior World Model Simulation in Autonomous Driving ReactiveGWM: Steering NPC in Reactive Game World Models Reason--Imagine--Act: Closed-Loop LLM Decision Making with World Models for Autonomous Driving Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models Reference-Free Assessment of Physical Consistency in World Model-based Video Generation ReflectiChain: Epistemic Grounding in LLM-Driven World Models for Supply Chain Resilience Reinforcing VLAs in Task-Agnostic World Models Render, Don't Decode: Weight-Space World Models with Latent Structural Disentanglement Riding the Shifting Potential: When Reactive Control Suffices for Multi-Goal Behavior RoboDream: Compositional World Models for Scalable Robot Data Synthesis RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation SCAR: Self-Supervised Continuous Action Representation Learning SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model ST-Gen4D: Embedding 4D Spatiotemporal Cognition into World Model for 4D Generation SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate SWAP: Symmetric Equivariant World-Model for Agile Robot Parkour SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution SWoMo: Neuro-Symbolic World Model for Cataract Surgery Simulation SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Model SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning Scaling World-Model Reinforcement Learning Through Diffusion Policy Optimization See Tomorrow, Act Today: Foresight-Driven Autonomous Driving Self-Evolving Cognitive Framework via Causal World Modeling for Embodied Scientific Intelligence Self-supervised Hierarchical Visual Reasoning with World Model Sensorimotor World Models: Perception for Action via Inverse Dynamics Shadow-Loom: Causal Reasoning over Graphical World Models of Narratives Signed Compression Progress on a Sealed Audit is Goodhart-Resistant Simulating clinical interventions with a generative multimodal model of human physiology SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors Slot-MPC: Goal-Conditioned Model Predictive Control with Object-Centric Representations Social World Model for Lifelong Social Intelligence SparseWorld: Enhancing End-to-End Autonomous Driving via World Models with Sparse Scene Representation Stealthy World Model Manipulation via Data Poisoning StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement Structure Abstraction and Generalization in a Hippocampal-Entorhinal Inspired World Model Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models SurgVista: Long-Horizon Surgical World Modeling with Plausible Instrument-Tissue Dynamics Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training TRAP: Tail-aware Ranking Attack for World-Model Planning TacForeSight: Force-Guided Tactile World Model for Contact-Rich Manipulation Targeting World Models to Compromise Robot Learning Pipelines Teaching Video Generators to Remember: Eliciting Dynamic Memory for Out-of-Sight State Evolution Temporal Logic Guidance for Action-Only Diffusion Policies with World Models Thinking with Patterns: Breaking the Perceptual Bottleneck in Visual Planning via Pattern Induction Thoughts-as-Planning: Latent World Models for Chain-of-Thoughts Optimization via Reinforcement Planning Three-in-One World Model: Energy-Based Consistency, Prediction, and Counterfactual Inference for Marketing Intervention Toward AI That Understands Self and Others: A World-Model Theory of Cognitive Diversity and Alignment Toward Compiler World Models: Learning Latent Dynamics for Efficient Tensor Program Search Toward Safe Autonomous Robotic Endovascular Interventions using World Models Toward World Modeling of Physiological Signals with Chaos-Theoretic Balancing and Latent Dynamics Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends Transformers Linearly Represent Highly Structured World Models Trimming the Long-Tail of Visual World Modeling Evaluation Turning Video Models into Generalist Robot Policies USS: Unified Spatial-Semantic Prompts for Embodied Visual Tracking with Latent Dynamics Learning UWM-JEPA: Predictive World Models That Imagine in Belief Space UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling Unified 3D Scene Understanding Through Physical World Modeling Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising Unified Driving Tokens: Representation- and Geometry-Guided Discrete Tokenizer for Driving World Models and Planning Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks UniviewVLA: A Unified Multiview Vision-Language-Action Model with World Modeling VANDERER: Map-Free Exploration using Future-Aware and Visual-Curiosity-Guided Diffusion Policy VegSim: A Geospatial World Model for Scenario-Conditioned Vegetation Simulation Video Generation with Predictive Latents WAM-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFT WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation WEAVER, Better, Faster, Longer: An Effective World Model for Robotic Manipulation Wh0: Generative World Models as Scalable Sources of Egocentric Human Hand Manipulation Data What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction What You Think is What You See: Driving Exploration in VLM Agents via Visual-Linguistic Curiosity What-If World: A Causal Benchmark for General World Models in Embodied Scenarios When Does LeJEPA Learn a World Model?Why Conclusions Diverge from the Same Observations: Formalizing World-Model Non-Identifiability via an Inference Words as Difference Makers: How Large Language Models Determine Causal Structure in Text World Action Models: A Survey World Action Models: The Next Frontier in Embodied AI World Model Self-Distillation: Training World Models to Solve General Tasks World Model for Robot Learning: A Comprehensive Survey World Model-Enabled Causal Digital Twins for Semantic Communications in Physical AI Systems World Models for Robotic Manipulation: A Survey World Models in Pieces: Structural Certification for General Agents World Pilot: Steering Vision-Language-Action Models with World-Action Priors World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks World-Task Factorization for Robot Learning World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Models WorldFly: A World-Model-Based Vision-Language-Action Model for UAV Navigation WorldKernel: A World Model is the Coupling Kernel of Admissible Possible Worlds WorldMark: A Unified Benchmark Suite for Interactive Video World Models WorldOlympiad: Can Your World Model Survive a Triathlon?WorldString: Actionable World Representation X-Cache: Cross-Chunk Block Caching for Few-Step Autoregressive World Models Inference X-Foresight: A Joint Vision-Action Causal Forecasting Network via Predictive World Modeling Xiaomi Auto World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous Driving YoCausal: How Far is Video Generation from World Model? A Causality Perspective dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation Paper - Voyager: An Open-Ended Embodied Agent with Large Language Models A Mechanistic View on Video Generation as World Models: State and Dynamics A formal theory on problem space as a semantic world model in systems engineering ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment AcceRL: A Distributed Asynchronous Reinforcement Learning and World Model Framework for Vision-Language-Action Models Action Shapley: A Training Data Selection Metric for World Model in Reinforcement Learning Advancing Open-source World Models Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning AlignUSER: Human-Aligned LLM Agents via World Models for Recommender System Evaluation Aligning Agentic World Models via Knowledgeable Experience Learning An Efficient and Multi-Modal Navigation System with One-Step World Model Beyond Pixel Histories: World Models with Persistent 3D State Boltzmann-GPT: Bridging Energy-Based World Models and Language Generation BridgeV2W: Bridging Video Generation Models to Embodied World Models via Embodiment Masks Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representation CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines Causal World Modeling for Robot Control Cross-View World Models Current Agents Fail to Leverage World Model as Tool for Foresight DCARL: A Divide-and-Conquer Framework for Autoregressive Long-Trajectory Video Generation Describe-Then-Act: Proactive Agent Steering via Distilled Language-Action World Models Do World Action Models Generalize Better than VLAs? A Robustness Study DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos DreamPlan: Efficient Reinforcement Fine-Tuning of Vision-Language Planners via Video World Models DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration DreamWorld: Unified World Modeling in Video Generation DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving DriveCtrl: Conditioned Sim-to-Real Driving Video Generation DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model Explicit World Models for Reliable Human-Robot Collaboration Factored Latent Action World Models Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments Foundation World Models for Agents that Learn, Verify, and Adapt Reliably Beyond Static Environments From Generative Engines to Actionable Simulators: The Imperative of Physical Grounding in World Models From Observations to Events: Event-Aware World Model for Reinforcement Learning From Part to Whole: 3D Generative World Model with an Adaptive Structural Hierarchy GeoWorld: Geometric World Models GigaBrain-0.5M: a VLA That Learns From World Model-Based Reinforcement Learning Hand2World: Autoregressive Egocentric Interaction Generation via Free-Space Hand Gestures Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model Inference-time Physics Alignment of Video Generative Models with Latent World Models Interpreting Physics in Video World Models Kinematics-Aware Latent World Models for Data-Efficient Autonomous Driving LIVE: Long-horizon Interactive Video World Modeling Latent World Models for Automated Driving: A Unified Taxonomy, Evaluation Framework, and Open Challenges Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving Learning Invariant Visual Representations for Planning with Joint-Embedding Predictive World Models Learning Latent Action World Models In The Wild LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models MAD: Motion Appearance Decoupling for efficient Driving World Models MIND: Benchmarking Memory Consistency and Action Control in World Models MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation MWM: Mobile World Models for Action-Conditioned Consistent Prediction MetaOthello: A Controlled Study of Multiple World Models in Transformers MetaWorld: Skill Transfer and Composition in a Hierarchical World Model for Grounding High-Level Instructions MobileDreamer: Generative Sketch World Model for GUI Agent Model Predictive Control with Differentiable World Models for Offline Reinforcement Learning MosaicMem: Hybrid Spatial Memory for Controllable Video World Models NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos NeuroHex: Highly-Efficient Hex Coordinate System for Creating World Models to Enable Adaptive AI OCCVAR: Scalable 4D Occupancy Prediction via Next-Scale Prediction Object-Centric World Models Meet Monte Carlo Tree Search Object-Centric World Models for Causality-Aware Reinforcement Learning Olaf-World: Orienting Latent Actions for Video World Modeling Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models On Memory: A comparison of memory mechanisms in world models Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning PhysicsMind: Sim and Real Mechanics Benchmarking for Physical Reasoning and Prediction in Foundational VLMs and World Models Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model Planning with an Ensemble of World Models PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation Probabilistic Dreaming for World Models Probing the effectiveness of World Models for Spatial Reasoning through Test-time Scaling Puzzle it Out: Local-to-Global World Model for Offline Multi-Agent Reinforcement Learning R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation RAE-NWM: Navigation World Model in Dense Visual Representation Space RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space ReWorld: Multi-Dimensional Reward Modeling for Embodied World Models Real Real-Time Long Video Generation Model ResWM: Residual-Action World Model for Visual RL ResWorld: Temporal Residual World Model for End-to-End Autonomous Driving Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving Say, Dream, and Act: Learning Video World Models for Instruction-Driven Robot Manipulation Scaling World Model for Hierarchical Manipulation Policies Self-Improving World Modelling with Latent Actions Self-Supervised JEPA-based World Models for LiDAR Occupancy Completion and Forecasting Self-Supervised Multi-Modal World Model with 4D Space-Time Embedding Semantic Belief-State World Model for 3D Human Motion Prediction ShareVerse: Multi-Agent Consistent Video Generation for Shared World Modeling Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation Solaris: Building a Multiplayer Video World Model in Minecraft Stereo World Model: Camera-Guided Stereo Video Generation The Trinity of Consistency as a Defining Principle for General World Models ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model Toward Physically Consistent Driving Video World Models under Challenging Trajectories UCM: Unifying Camera Control and Memory with Time-aware Positional Encoding Warping for World Models UniDrive-WM: Unified Understanding, Planning and Generation World Model For Autonomous Driving UniFuture: A 4D Driving World Model for Future Generation and Perception VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model VLM-DEWM: Dynamic External World Model for Verifiable and Resilient Vision-Language Planning in Manufacturing Value-guided action planning with JEPA world models Vega: Learning to Drive with Natural Language Instructions VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models Walk through Paintings: Egocentric World Models from Internet Priors What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Models World Action Models are Zero-shot Policies World Properties without World Models: Recovering Spatial and Temporal Structure from Co-occurrence Statistics in Static Word Embeddings World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy World2Act: Latent Action Post-Training via Skill-Compositional World Models WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models WorldBench: Disambiguating Physics for Diagnostic Evaluation of World Modelsl WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching WorldCache: Content-Aware Caching for Accelerated Video World Models WorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous Driving WorldVLM: Combining World Model Forecasting and Vision-Language Reasoning Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Testl X-World: Controllable Ego-Centric Multi-Camera World Models for Scalable End-to-End Driving Xiaomi EV World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous Driving 3D and 4D World Modeling: A Survey 3D4D: An Interactive, Editable, 4D World Model via 3D Video Generation 3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model 4DWorldBench: A Comprehensive Evaluation Framework for 3D/4D World Generation Models A "Good" Regulator May Provide a World Model for Intelligent Systems A Comprehensive Survey on World Models for Embodied AI A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models A Step Toward World Models: A Survey on Robotic Manipulation A Survey of World Models for Autonomous Driving A Survey on Future Physical World Generation for Autonomous Driving A Survey on World Models Grounded in Acoustic Physical Information A Survey: Learning Embodied Intelligence from Physical Simulators and World Models A Unified Definition of Hallucination, Or: It's the World Model, Stupid AD-L-JEPA: Self-Supervised Spatial World Models with Joint Embedding Predictive Architecture for Autonomous Driving with LiDAR Data AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models AVD2: Accident Video Diffusion for Accident Video Description Act2Goal: From World Model To General Goal-conditioned Policy Active Confusion Expression in Large Language Models: Leveraging World Models toward Better Social Reasoning Active Intelligence in Video Avatars via Closed-loop World Modeling AdaPower: Specializing World Foundation Models for Predictive Manipulation AdaWM: Adaptive World Model based Planning for Autonomous Driving Adapting Vision-Language Models for Evaluating World Models Adapting a World Model for Trajectory Following in a 3D Game Advancing Off-Road Autonomous Driving: The Large-Scale ORAD-3D Dataset and Comprehensive Benchmarks Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Space Aether: Geometric-Aware Unified World Modeling Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI Astra: General Interactive World Model with Autoregressive Denoising AstraNav-World: World Model for Foresight Control and Consistency Audio-Visual World Models: Towards Multisensory Imagination in Sight and Sound Back to the Features: DINO as a Foundation for Video World Models Benchmarking World-Model Learning Better World Models Can Lead to Better Post-Training Performance Beyond Generative AI: World Models for Clinical Prediction, Counterfactuals, and Planning BiTAgent: A Task-Aware Modular Framework for Bidirectional Coupling between Multimodal Large Language Models and World Models Bootstrapping World Models from Dynamics Models in Multimodal Foundation Models Bridging the Gap Between Multimodal Foundation Models and World Models CLARITY: Medical World Model for Guiding Treatment Decisions by Modeling Context-Aware Disease Trajectories in Latent Space CVD-STORM: Cross-View Video Diffusion with Spatial-Temporal Reconstruction Model for Autonomous Driving CWM: An Open-Weights LLM for Research on Code Generation with World Models Causal Cartographer: From Mapping to Reasoning Over Counterfactual Worlds CausalARC: Abstract Reasoning with Causal World Models ChronoDreamer: Action-Conditioned World Model as an Online Simulator for Robotic Planning Clone Deterministic 3D Worlds with Geometrically-Regularized World Models Closing the Train-Test Gap in World Models for Gradient-Based Planning Co-Evolving Latent Action World Models CoEx -- Co-evolving World-model and Exploration CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models Code World Models for General Game Playing Consistent World Models via Foresight Diffusion Context and Diversity Matter: The Emergence of In-Context Learning in World Models Continual Reinforcement Learning by Planning with Online World Models CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous Driving Counterfactual World Models via Digital Twin-conditioned Video Diffusion Critiques of World Models Ctrl-World: A Controllable Generative World Model for Robot Manipulation DC-MPC: Discrete Codebook World Models for Continuous Control DINO-Foresight: Looking into the Future with DINO DIO: Decomposable Implicit 4D Occupancy-Flow World Model DMWM: Dual-Mind World Model with Long-Term Imagination DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration DREAMer-VXS: A Latent World Model for Sample-Efficient AGV Exploration in Stochastic, Unobserved Environments DSG-World: Learning a 3D Gaussian World Model from Dual State Videos Deductive Chain-of-Thought Augmented Socially-aware Robot Navigation World Model Deep Active Inference with Diffusion Policy and Multiple Timescale World Model for Real-World Exploration and Navigation Deep SPI: Safe Policy Improvement via World Models DeepVerse: 4D Autoregressive Video Generation as a World Model Design and Optimization of Reinforcement Learning-Based Agents in Text-Based Games Deterministic World Models for Verification of Closed-loop Vision-based Systems Dexterous World Models DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformer DiWA: Diffusion Policy Adaptation with World Models Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning Does End-to-End Autonomous Driving Really Need Perception Tasks?Dream to Drive with Predictive Individual World Model Dream to Drive: Model-Based Vehicle Control Using Analytic World Models DreamerV3-XP: Optimizing exploration through uncertainty estimation DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment Drive&Gen: Co-Evaluating End-to-End Driving and Video Generation Models DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation DriveLaW: Unifying Planning and Video Generation in a Latent Driving World DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers Dual-Mind World Models: A General Framework for Learning in Dynamic Wireless Networks Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation Dyn-O: Building Structured World Models with Object-Centric Representations Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents Dynamic Sparsity: Challenging Common Sparsity Assumptions for Learning World Models in Robotic Reinforcement Learning Benchmarks DynamicCity: Large-Scale LiDAR Generation from Dynamic Scenes Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalization EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models EchoWorld: Learning Motion-Aware World Models for Echocardiography Probe Guidance Edge General Intelligence Through World Models and Agentic AI: Fundamentals, Solutions, and Challenges Efficient Generation of Diverse Cooperative Agents with World Models Ego-Vision World Model for Humanoid Contact Planning Embodied AI Agents: Modeling the World Embodied Tree of Thoughts: Deliberate Manipulation Planning with Embodied World Model Embodied World Models Emerge from Navigational Task in Open-Ended Environments Emu3.5: Native Multimodal Models are World Learners End-to-End Driving with Online Trajectory Evaluation via BEV World Model Enhancing Physical Consistency in Lightweight World Models Epona: Autoregressive Diffusion World Model for Autonomous Driving Evaluating Gemini Robotics Policies in a Veo World Simulator Evaluating Robot Policies in a World Model EvoAgent: Agent Autonomous Evolution with Continual World Model for Long-Horizon Tasks FASTopoWM: Fast-Slow Lane Segment Topology Reasoning with Latent World Models FLARE: Robot Learning with Implicit World Modeling FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making FUTURIST: Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction FieldSeer I: Physics-Guided World Models for Long-Horizon Electromagnetic Dynamics under Partial Observability FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulation Foundation Models as World Models: A Foundational Study in Text-Based GridWorlds From 2D to 3D Cognition: A Brief Survey of General World Models From Curiosity to Competence: How World Models Interact with the Dynamics of Exploration From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction From Imitation to Exploration: End-to-end Autonomous Driving based on World Model From Masks to Worlds: A Hitchhiker's Guide to World Models From Word to World: Can Large Language Models be Implicit Text-based World Models?FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving GAF: Gaussian Action Field as a Dynamic World Model for Robotic Manipulation GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving GAWM: Global-Aware World Model for Multi-Agent Reinforcement Learning GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control GLAM: Global-Local Variation Awareness in Mamba-based World Model GWM: Towards Scalable Gaussian World Models for Robotic Manipulation GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction General agents need world models Generating Symbolic World Models via Test-time Scaling of Large Language Models Generative World Modelling for Humanoids: 1X World Model Challenge Technical Report GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control GigaBrain-0: A World Model-Powered Vision-Language-Action Model GigaWorld-0: World Models as Data Engine to Empower Embodied AI Graph World Model GrndCtrl: Grounding World Models via Self-Supervised Reward Alignment HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation HERO: Hierarchical Extrapolation and Refresh for Efficient World Models Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task How Far Are Surgeons from Surgical World Models? A Pilot Study on Zero-shot Surgical Video Generation with Expert Assessment How Hard is it to Confuse a World Model?Hunyuan-GameCraft-2: Instruction-following Interactive Game World Model I2 -World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting IPR-1: Interactive Physical Reasoner ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving InDRiVE: Reward-Free World-Model Pretraining for Autonomous Driving via Latent Disagreement Inter-environmental world modeling for continuous and compositional dynamics Internal World Models as Imagination Networks in Cognitive Agents JEDI: Latent End-to-end Diffusion Mitigates Agent-Human Performance Asymmetry in Model-Based Reinforcement Learning KAN-Dreamer: Benchmarking Kolmogorov-Arnold Networks as Function Approximators in World Models KeyWorld: Key Frame Reasoning Enables Effective and Efficient World Models LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures LLM-as-a-Judge: Toward World Models for Slate Recommendation Systems LS-Imagine: Open-World Reinforcement Learning over Long Short-Term Imagination LUMOS: Language-Conditioned Imitation Learning with World Models LaGen: Towards Autoregressive LiDAR Scene Generation Language-Driven Hierarchical Task Structures as Explicit World Models for Multi-Agent Learning Language-conditioned world model improves policy generalization by reading environmental descriptions Large Emotional World Model Latent Action World Models for Control with Unlabeled Trajectories Latent Chain-of-Thought World Modeling for End-to-End Driving Latent Policy Steering with Embodiment-Agnostic Pretrained World Models Latent-Space Autoregressive World Model for Efficient and Robust Image-Goal Navigation LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation Learning Abstract World Models with a Group-Structured Latent Space Learning Primitive Embodied World Models: Towards Scalable Robotic Learning Learning Real-World Action-Video Dynamics with Heterogeneous Masked Autoregression Learning Robot Manipulation from Audio World Models Learning To Explore With Predictive World Model Via Self-Supervised Learning Learning World Models for Interactive Video Generation Learning an Adversarial World Model for Automated Curriculum Generation in MARL Learning to Generate 4D LiDAR Sequences LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences LiSTAR: Ray-Centric World Models for 4D LiDAR Sequences in Autonomous Driving Long-Context State-Space Video World Models LongDWM: Cross-Granularity Distillation for Building a Long-Term Driving World Model LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE LongVie 2: Multimodal Controllable Ultra-Long Video World Model M^3 : A Modular World Model over Streams of Tokens MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control ManiGaussian++: General Robotic Bimanual Manipulation with Hierarchical Gaussian World Model ManipDreamer: Boosting Robotic Manipulation World Model with Action Tree and Visual Guidance Martian World Models: Controllable Video Synthesis with Physically Accurate 3D Reconstructions MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model Measuring (a Sufficient) World Model in LLMs: A Variance Decomposition Framework Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft Meta-Reinforcement Learning with Discrete World Models for Adaptive Load Balancing MiLA: Multi-view Intensive-fidelity Long-term Video Generation World Model for Autonomous Driving MinD: Unified Visual Imagination and Control via Hierarchical World Models MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving MindJourney: Test-Time Scaling with World Models for Spatial Reasoning MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval MoVieDrive: Multi-Modal Multi-View Urban Scene Video Generation MoWM: Mixture-of-World-Models for Embodied Planning via Latent-to-Pixel Feature Modulation MobiWorld: World Models for Mobile Wireless Network MorphoSim: An Interactive, Controllable, and Editable Language-guided 4D World Simulator Motus: A Unified Latent Action World Model Multimodal Dreaming: A Global Workspace Approach to World Model-Based Reinforcement Learning NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards NRSeg: Noise-Resilient Learning for BEV Semantic Segmentation via Driving World Models Natural Building Blocks for Structured World Models: Theory, Evidence, and Scaling NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Prediction NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments Navigation World Models Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning OccProphet: Pushing Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with Observer-Forecaster-Refiner Framework OccTENS: 3D Occupancy World Model via Temporal Next-Scale Prediction Occupancy World Model for Robots Offline Robotic World Model: Learning Robotic Policies without a Physics Simulator OmniNWM: Omniscient Driving Navigation World Models OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning OpenTwinMap: An Open-Source Digital Twin Generator for Urban Autonomous Driving Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models Other Vehicle Trajectories Are Also Needed: A Driving World Model Unifies Ego-Other Vehicle Trajectories in Video Latant Space PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulation ParticleFormer: A 3D Point Cloud World Model for Multi-Object, Multi-Material Robotic Manipulation PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesis PhysicalAgent: Towards General Cognitive Robotics with Foundation World Models Planning with Reasoning using Vision Language World Model PlayerOne: Egocentric World Simulator PragWorld: A Benchmark Evaluating LLMs' Local World Model under Minimal Linguistic Alterations and Conversational Dynamics Prismatic World Model: Learning Compositional Dynamics for Planning in Hybrid Systems ProTerrain: Probabilistic Physics-Informed Rough Terrain World Modeling ProphetDWM: ProphetDWM: A Driving World Model for Rolling Out Future Actions and Videos R-WoM: Retrieval-augmented World Model For Computer-use Agents RELIC: Interactive Video World Model with Long-Horizon Memory RLVR-World: Training World Models with Reinforcement Learning RadarGen: Automotive Radar Point Cloud Generation from Cameras Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)ReSim: Reliable World Simulation for Autonomous Driving ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration Reimagination with Test-time Observation Interventions: Distractor-Robust World Model Predictions for Visual Model Predictive Control Remote Sensing-Oriented World Model Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks Rethinking the Simulation vs. Rendering Dichotomy: No Free Lunch in Spatial World Modelling RoboHorizon: An LLM-Assisted Multi-View World Model for Long-Horizon Robotic Manipulation RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL RoboScape: Physics-informed Embodied World Model Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics RynnVLA-002: A Unified Vision-Language-Action and World Model SAMPO: Scale-wise Autoregression with Motion PrOmpt for generative world models SCMA: Self-Consistent Model-based Adaptation for Visual Reinforcement Learning STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation STORM: Search-Guided Generative World Models for Robotic Manipulation Safe Planning and Policy Optimization via World Model Learning Scalable Policy Evaluation with Video World Models Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model Seeing Clearly, Forgetting Deeply: Revisiting Fine-Tuned Video Generators for Driving Simulation Sekai: A Video Dataset towards World Exploration Semantic Communications with World Models Semantic World Models Semi-SD: Semi-Supervised Metric Depth Estimation via Surrounding Cameras for Autonomous Driving Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving SimWorld: A Unified Benchmark for Simulator-Conditioned Scene Generation via World Model Simple, Good, Fast: Self-Supervised World Models Free of Baggage SimuRA: Towards General Goal-Oriented Agent via Simulative Reasoning Architecture with LLM-Based World Model Simulating Before Planning: Constructing Intrinsic User World Model for User-Tailored Dialogue Policy Planning Simulating the Visual World with Artificial Intelligence: A Roadmap SmallWorlds: Assessing Dynamics Understanding of World Models in Isolated Environments Social World Model-Augmented Mechanism Design Policy Learning Social World Models Sparse Imagination for Efficient Visual World Model Planning SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model SparseWorld: A Flexible, Adaptive, and Efficient 4D Occupancy World Model Powered by Sparse and Dynamic Queries Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models Speech World Model: Causal State-Action Planning with Explicit Reasoning for Speech StateSpaceDiffuser: Bringing Long Context to Diffusion World Models Surfer: A World Model-Based Framework for Vision-Language Robot Manipulation Synthesizing world models for bilevel planning TeleWorld: Towards Dynamic Multimodal Synthesis with a 4D World Model Temporal Triplane Transformers as Occupancy World Models Terra: Explorable Native 3D World Model with Point Latents TesserAct: Learning 4D Embodied World Models Text2World: Benchmarking Large Language Models for Symbolic World Model Generation The Double Life of Code World Models: Provably Unmasking Malicious Behavior Through Execution Traces The Role of World Models in Shaping Autonomous Driving: A Comprehensive Survey The Safety Challenge of World Models for Embodied AI Agents: A Review The brain-AI convergence: Predictive and generative world models for general-purpose computation Think Before You Drive: World Model-Inspired Multimodal Grounding for Autonomous Vehicles Thinking Ahead: Foresight Intelligence in MLLMs and World Models Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction Time-Aware World Model for Adaptive Prediction and Control Toward Memory-Aided World Models: Benchmarking via Spatial Consistency Toward Stable World Models: Measuring and Addressing World Instability in Generative Environments Towards High-Consistency Embodied World Model with Multi-View Trajectory Videos Towards foundational LiDAR world models with efficient latent flow matching TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos TransDreamerV3: Implanting Transformer In DreamerV3 Transformer World Model for Sample Efficient Multi-Agent Reinforcement Learning U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving Unified Vision-Language-Action Model Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets Unified World Models: Memory-Augmented Planning and Foresight for Visual Navigation Unlocking Smarter Device Control: Foresighted Planning with a World Model-Driven Code Execution Approach V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents VCWorld: A Biological World Model for Virtual Cell Simulation VDAWorld: World Modelling via VLM-Directed Abstraction and Simulation VFMF: World Modeling by Forecasting Vision Foundation Model Features VISTAv2: World Imagination for Indoor Vision-and-Language Navigation VL-SAFE: Vision-Language Guided Safety-Aware Reinforcement Learning with World Models for Autonomous Driving VaViM and VaVAM: Autonomous Driving through Video Generative Modeling Vector Quantization in the Brain: Grid-like Codes in World Models Vehicle Dynamics Embedded World Models for Autonomous Driving ViPRA: Video Prediction for Robot Actions Vid2World: Crafting Video Diffusion Models to Interactive World Models Video World Models with Long-term Spatial Memory VideoVerse: How Far is Your T2V Generator from a World Model?Vision-Centric 4D Occupancy Forecasting and Planning via Implicit Residual World Models Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform Visuomotor Grasping with World Models for Surgical Robots WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation WMPO: World Model-based Policy Optimization for Vision-Language-Action Models Web World Models What Does it Mean for a Neural Network to Learn a "World Model"?What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models What You Don't Know Can Hurt You: How Well do Latent Safety Filters Understand Partially Observable Safety Constraints?When do Neural Networks Learn World Models?WoMAP: World Models For Embodied Open-Vocabulary Object Localization WoW: Towards a World omniscient World model Through Embodied Interaction World Model Implanting for Test-time Adaptation of Embodied Agents World Model-Based End-to-End Scene Generation for Accident Anticipation in Autonomous Driving World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning World Models Can Leverage Human Videos for Dexterous Manipulation World Models Should Prioritize the Unification of Physical and Social Dynamics World Models That Know When They Don't Know: Controllable Video Generation with Calibrated Uncertainty World Models Unlock Optimal Foraging Strategies in Reinforcement Learning Agents World Models as Reference Trajectories for Rapid Motor Adaptation World Models for Autonomous Navigation of Terrestrial Robots from LIDAR Observations World Models for Cognitive Agents: Transforming Edge Intelligence in Future Networks World model inspired sarcasm reasoning with large language model agents World-in-World: World Models in a Closed-Loop World World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model World4Omni: A Zero-Shot Framework from Image Generation World Model to Robotic Manipulation World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World WorldModelBench: Judging Video Generation Models As World Models WorldPack: Compressed Memory Improves Spatial Consistency in Video World Modeling WorldPlanner: Monte Carlo Tree Search and MPC with Action-Conditioned Visual World Models WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling WorldVLA: Towards Autoregressive Action World Model WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation X-WIN: Building Chest Radiograph World Model via Predictive Sensing Xray2Xray: World Model from Chest X-rays with Volumetric Context Zero-Splat TeleAssist: A Zero-Shot Pose Estimation Framework for Semantic Teleoperation Zero-shot World Models via Search in Memory seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models 3D-VLA: A 3D Vision-Language-Action Generative World Model AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractors AVID: Adapting Video Diffusion Models to World Models Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning Agent Planning with World Knowledge Model An Efficient Occupancy World Model via Decoupled Dynamic Flow and Image-assisted Training BEVWorld: A Multimodal World Model for Autonomous Driving via Unified BEV Latent Space BWArea Model: Learning World Model, Inverse Dynamics, and Policy for Controllable Language Generation Bounded Exploration with World Model Uncertainty in Soft Actor-Critic Reinforcement Learning Algorithm CarDreamer: Open-Source Learning Platform for World Model based Autonomous Driving CarFormer: Self-Driving with Learned Object-Centric Representations Causal World Representation in the GPT Model CityBench: Evaluating the Capabilities of Large Language Model as World Model CoDreamer: Communication-Based Decentralised World Models Cognitive Map for Language Models: Optimal Planning via Verbally Representing the World Model Cognitively Inspired Energy-Based World Models Compete and Compose: Learning Independent Mechanisms for Modular World Models Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning DOME: Taming Diffusion Model into High-Fidelity Controllable Occupancy World Model DexSim2Real$^2$: Building Explicit World Model for Precise Articulated Object Dexterous Manipulation Diffusion for World Modeling: Visual Details Matter in Atari Do Transformer World Models Give Better Policy Gradients?Doe-1: Closed-Loop Autonomous Driving with Large World Model Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving DriveGenVLM: Real-world Video Generation for Vision Language Model based Autonomous Driving DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT EVA: An Embodied World Model for Future Video Anticipation Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction Efficient World Models with Context-Aware Tokenization Emergence of Implicit World Models from Mortal Agents Enhancing End-to-End Autonomous Driving with Latent World Model Evaluating the World Model Implicit in a Generative Model Exploring the Interplay Between Video Generation and World Models in Autonomous Driving: A Survey Generalized Predictive Model for Autonomous Driving Generative Emergent Communication: Large Language Model is a Collective World Model Genie: Generative Interactive Environments Grounded Answers for Multi-agent Decision-making Problem through Generative World Model Grounding Large Language Models In Embodied Environment With Imperfect World Models HarmonyDream: Task Harmonization Inside World Models Hierarchical World Models as Visual Whole-Body Humanoid Controllers Hieros: Hierarchical Imagination on Structured State Space Sequence World Models HoloDrive: Holistic 2D-3D Multi-Modal Street Scene Generation for Autonomous Driving How Far is Video Generation from World Model: A Physical Law Perspective IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI Imagine-2-Drive: High-Fidelity World Modeling in CARLA for Autonomous Vehicles Improving Token-Based World Models with Parallel Observation Prediction InfinityDrive: Breaking Time Limits in Driving World Models Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents Language Agents Meet Causality -- Bridging LLMs and Causal World Models Learning Latent Dynamic Robust Representations for World Models Learning Multiple Probabilistic Decisions from Latent World Model in Autonomous Driving Learning World Models for Unconstrained Goal Navigation Learning and Leveraging World Models in Visual Representation Learning LidarDM: Generative LiDAR Simulation in a Generated World MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning MagicDrive: Street View Generation with Diverse 3D Geometry Control MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators Making Large Language Models into World Models with Precondition and Effect Knowledge Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation Mastering Memory Tasks with World Models Mitigating Covariate Shift in Imitation Learning for Autonomous Vehicles Using Latent Space Generative World Models Motion Prompting: Controlling Video Generation with Motion Trajectories Multi-Task Interactive Robot Fleet Learning with Visual World Models Multimodal foundation world models for generalist embodied agents OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving One-shot World Models Using a Transformer Trained on a Synthetic Prior Owl-1: Omni World Model for Consistent Long Video Generation PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation PWM: Policy Learning with Large World Models Physical Informed Driving World Model Planning with Adaptive World Models for Autonomous Driving Predicting vs. Acting: A Trade-off Between World Modeling & Agent Modeling Probing Multimodal LLMs as World Models for Driving R-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Models RenderWorld: World Model with Self-Supervised 3D Label Representing Positional Information in Generative World Models for Object Manipulation Reward-free World Models for Online Imitation Learning RoboDreamer: Learning Compositional World Models for Robot Imagination SafeDreamer: Safe Reinforcement Learning with World Models Scaling Laws for Pre-training Agents and World Models SimuDICE: Offline Policy Optimization Through World Model Updates and DICE Estimation StoryWeaver: A Unified World Model for Knowledge-Enhanced Story Character Customization TD-MPC2: Scalable, Robust World Models for Continuous Control Terra ACT-Bench: Towards Action Controllable World Models for Autonomous Driving The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control Think2Drive: Efficient Reinforcement Learning by Thinking in Latent World Model for Quasi-Realistic Autonomous Driving Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Driving Towards Physically Interpretable World Models: Meaningful Weakly Supervised Representations for Visual Trajectory Prediction Towards Unraveling and Improving Generalization in World Models Transformers Use Causal World Models in Maze-Solving Tasks Transformers and Slot Encoding for Sample Efficient Physical World Modelling UnO: Unsupervised Occupancy Fields for Perception and Forecasting Understanding World or Predicting Future? A Comprehensive Survey of World Models UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving Unleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generation UrbanWorld: An Urban World Model for 3D City Generation VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulation Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning WHALE: Towards Generalizable and Scalable World Models for Embodied Decision-making Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation World Model on Million-Length Video And Language With RingAttention World Model-based Perception for Visual Legged Locomotion World Models Increase Autonomy in Reinforcement Learning World Models for Autonomous Driving: An Initial Survey World Models with Hints of Large Language Models for Goal Achieving World Models: The Safety Perspective WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens ADriver-I: A General World Model for Autonomous Driving Categorical Traffic Transformer: Interpretable and Diverse Behavior Prediction with Tokenized Latent FOCUS: Object-Centric World Models for Robotics Manipulation GAIA-1: A Generative World Model for Autonomous Driving Learning to Model the World with Language MUVO: A Multimodal Generative World Model for Autonomous Driving with Geometric Representations STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning Task Aware Dreamer for Task Generalization in Reinforcement Learning TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction Transformer-based World Models Are Happy with 100k Interactions Transformers are Sample Efficient World Models UniWorld: Autonomous Driving Pre-training via World Models DayDreamer: World Models for Physical Robot Learning Deep Hierarchical Planning from Pixels DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation Mastering Atari with Discrete World Models Dream to Control: Learning Behaviors by Latent Imagination Planning to Explore via Self-Supervised World Models World Models PerceptUI: PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluation MemoBench: Benchmarking World Modeling in Dynamically Changing Environments EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting Hallucination in World Models is Predictable and Preventable PhysiFormer: Learning to Simulate Mechanics in World Space Fast LeWorldModel PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning SimVP: Simpler yet Better Video Prediction Diffusion Models for Video Prediction and Infilling Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation MemLearner: Learning to Query Context memory for Video World Models Learning Transferable Dynamics Priors from Action to World Modeling DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model Valdi: Value Diffusion World Models ABot-M0.5: Unified Mobility-and-Manipulation World Action Model WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory WorldOdysseyBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation From World Models to World Action Models: A Concise Tutorial for Robotics OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration Certified World Models as Sensing Clocks: Drift-Aware Deadlines for Active Perception Safe and Adaptive Cloud Healing: Verifying LLM-Generated Recovery Plans with a Neural-Symbolic World Model Predicting Closed-Loop Performance of Latent World Models: Offline Checkpoint Selection for MPC and Model-Based RL Under Non-Markovian Rewards in LunarLander PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation PWM-ArtGen: Part World Model for Articulated Object Generation Bridge-WA: Predicting Where and How the World Changes for Robotic Action ACID: Action Consistency via Inverse Dynamics for Planning with World Models WorldSample: Closed-loop Real-robot RL with World Modelling OWMDrive: Causality-Aware End-to-End Autonomous Driving via 4D Occupancy World Model Self-Evolving World Models for LLM Agent Planning Long-term Traffic Simulation via Structured Autoregressive Modeling Delta-JEPA: Learning Action-Sensitive World Models via Latent Difference Decoding One Video, One World: Turning Monocular Video into Physical 4D Scenes World-Model Collapse as a Phase Transition Ask the World Before Acting: Budgeted Environment Probing for World-Model Calibration WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models AdaJEPA: An Adaptive Latent World Model 3D Point World Models: Point Completion Enables More Accurate Dynamics Learning RetailSMV: Exocentric vs. Egocentric Adaptation of Foundation Video World Models in Retail Multi-scale Mixture of World Models for Embodied Agents in Evolving Environments Path Planning in Physically Viable World Models RoboWorld: Fast and Reliable Neural Simulators for Generalist Robot Policy Evaluation IRASim: A Fine-Grained World Model for Robot Manipulation Unified Video Action Model EnerVerse-AC: Envisioning Embodied Environments with Action Condition VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Control DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics Last-Meter Precision Navigation for UAVs: A Diffusion-Refined Aerial Visual Servoing Approach Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling Operator-on-F complements value-equivalence: a planning-time diagnostic for latent world models Geographic Diversity Beats Data Volume for Cross-Domain Generalization in Zero-Label JEPA Driving World Models Mask2Real-WM: Segmentation Masks as a Sim-to-Real Bridge for Controllable Dexterous World Models KAM-WM: Kinematic Affordance Maps from Latent World Models for Robot Manipulation DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Control MoP-JEPA: Hard-Assigned Predictor Mixtures for Stochastic JEPA World Models Multiplayer Interactive World Models with Representation Autoencoders Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models LongCat-Video Technical Report RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation AlayaWorld: Long-Horizon and Playable Video World Generation Imagined Rollouts are Kinematic, Not Dynamic: A Diagnosis of Long-Horizon World-Model Failure WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence Infinite Worlds with Versatile Interactions PanoWorld: Real-World Panoramic Generation Flow-ERD: Agent-type Aware Flow Matching with Entropy-Regularized Distillation for Diverse Traffic Simulation Pathdreamer: A World Model for Indoor Navigation V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model Improving Multi-Step Prediction of Learned Time Series Models Versatile Behavior Diffusion for Generalized Traffic Agent Simulation BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction Learning to drive from a world on rails Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch Collision Avoidance Detour for Multi-Agent Trajectory Forecasting Hierarchical Denoising For Multi-Step Visual Reasoning RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination From Pixels to States: Rethinking Interactive World Models as Game Engines Can World Models Benefit VLMs for World Dynamics?LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion Rethinking Video Generation Model for the Embodied World Mixture of Contexts for Long Video Generation Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention E3DGS: Unified Geometric-Photometric Equivariance for 3D Gaussian Splatting via Color-as-Geometry Embedding SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction Orbis 2: A Hierarchical World Model for Driving DSWorld: A Data Science World Model for Efficient Autonomous Agents Learning from World Feedback: Why Model Uncertainty Fails as a Risk Signal in Model-Based RL PAVXploreRL: Physical-Action-Visual World Model Reinforcement Learning with Action Exploration GeoWorldAD: Geometry World Action Model for Autonomous Driving Thinking in Video: Can Video Generators Really Reason About the Real World?Reinforcement Learning: From Algorithms To Foundation Models Planning with Transformers: Chain of Computation and Structured Context Windows Mobile Network Control with a World Model SAGE: Subgoal-Conditioned Action Generation for Latent World Model Planning Masked Visual Actions for Unified World Modeling Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report Generative World Renderer at the Speed of Play ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers Stable Video Infinity: Infinite-Length Video Generation with Error Recycling GameFactorly: Creating New Games with Generative Interactive Videos LoViC: Efficient Long Video Generation with Context Compression Playable Video Generation Generative Pre-trained Autoregressive Diffusion Transformer Video-GPT via Next Clip Diffusion RoboTrustBench: Benchmarking the Trustworthiness of Video World Models for Robotic Manipulation Video Generation Models in Robotics - Applications, Research Challenges, Future Directions Wonder: Video World Model Done Better WorldDiT: A Unified Diffusion Architecture for World and Action Modeling Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control VisualPatchWorld: Code World Models as Latent Structured Representations for Planning ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine PhiZero: A World Model Built Around Physical Language StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow MultiWorld: Scalable Multi-Agent Multi-View Video World Models Planning from Pixels using Inverse Dynamics Models SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation QQWorld: Quantile-Quantile Matching for World Model Regularization World Action Planner: Generalizable Decision-Making with Action-Conditioned World Models ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space HelloWorld: Enabling Socially Interactive Characters in Video World Models MiniWorld: Democratizing the Training of Video World Models from Scratch Quo Vadis, World Modeling?WorldClaw: Agentic 3D Open-World Generation at Scale WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models Mirage 2: Ai-native ugc game engine powered by real-time world models Scaling Agent Learning via Experience Synthesis

Resources

Hugging Face Paper

Tags

size_categories:1K<n<10Kmodality:imagemodality:videolibrary:datasetslibrary:mlcroissantregion:us