← Back to datasets

VideoWorldmodel/Evaluation

2026 Datasets

Preview for VideoWorldmodel/Evaluation

Dataset Analysis

Matrix-Game 2.0 Self-Consistency Reproduction This README explains how to reproduce the Matrix-Game 2.0 self-consistency (SC) row in Reasoning-Structured Videos: A Stratified Diagnostic Suite for Compositional Consistency in World Models. All experimental data, generated videos, and evaluation files required for this reproduction are available on the current dataset page under Files and versions: https://huggingface.co/datasets/VideoWorldmodel/Evaluation No external dataset or… See the full description on the dataset page: https://huggingface.co/datasets/VideoWorldmodel/Evaluation.

Provenance

Collected from huggingface-datasets.

downloads=0, likes=0

Related papers

$τ_0$-WM: A Unified Video-Action World Model for Robotic Manipulation $ω$-EVA: Envision, Verify, and Act with Latent Interactive World Models A 3D Isovist World Model -- Revealing a City's Unseen Geometry and Its Emergent Cross-City Signature A Mechanistic View on Video Generation as World Models: State and Dynamics ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment AGEL-Comp: A Neuro-Symbolic Framework for Compositional Generalization in Interactive Agents ARB4WM: An Adversarial Robustness Benchmark for World Models in Continuous Control Advancing Open-source World Models Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond AlignUSER: Human-Aligned LLM Agents via World Models for Recommender System Evaluation Attacking the Trusted Imagination: Oracle-Level Integrity Attacks on Imagine-then-Act World Models Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents BRo-JEPA: Learning Modular Arithmetic in Latent Space Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning Beyond Pixel Histories: World Models with Persistent 3D State BridgeV2W: Bridging Video Generation Models to Embodied World Models via Embodiment Masks CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines Causal Object-Centric Models for Planning with Monte Carlo Tree Search CausalDrive: Real-time Causal World Models for Autonomous Driving ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care Data Conformal Orbit-Valid Trust Horizons for Equivariant World Models Current World Models Lack a Persistent State Core Data-Asymmetric Latent Imagination and Reranking for 3D Robotic Imitation Learning DeTrack: A Benchmark and Altitude-Aware Dual World Model for Drone-embodied Tracking DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving Diffusion Transformer World-Action Model for AV Scene Prediction 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 Do World Action Models Generalize Better than VLAs? A Robustness Study DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos DreamWorld: Unified World Modeling in Video Generation 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 DriveCtrl: Conditioned Sim-to-Real Driving Video Generation Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving DynaWM: Dynamics-Aware Distillation with World Model and Momentum Targets for Smooth Locomotion over Continuous Stairs Echo-Memory: A Controlled Study of Memory in Action World Models EgoCS-400K: An Egocentric Gameplay Dataset for World Models Embody4D: A Generalist Data Engine for Embodied 4D World Modeling FAR-Drive: Frame-AutoRegressive Video Generation in Closed-Loop Autonomous Driving From Generative Engines to Actionable Simulators: The Imperative of Physical Grounding in World Models GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation GEM: Generating LiDAR World Model via Deformable Mamba Generalization of World Models under Environmental Variability for Vision-based Quadrotor Navigation GeoWorld: Geometric 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 HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training How Should World Models Be Evaluated? A Decision-Making-Centric Position IOI: Decoupling Kinematics and Physics for Interactive World Models InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models Is Your Driving World Model an All-Around Player?JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning LaST-HD: Learning Latent Physical Reasoning from Scalable Human Data for Robot Manipulation LaWM: Least Action World Models for Long-Horizon Physical Consistency from Visual Observations Latent State Design for World Models under Sufficiency Constraints 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 Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models LoViF 2026 The First Challenge on Holistic Quality Assessment for 4D World Model (PhyScore)MBench: A Comprehensive Benchmark on Memory Capability for Video World Models MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments MIND: Benchmarking Memory Consistency and Action Control in World Models 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 Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent Manifolds MobileDreamer: Generative Sketch World Model for GUI Agent Monte Carlo Pass Search: Using Trajectory Generation for 3D Counterfactual Pass Evaluation in Football 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 Network-Efficient World Model Token Streaming NeuroHex: Highly-Efficient Hex Coordinate System for Creating World Models to Enable Adaptive AI 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 Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation On Memory: A comparison of memory mechanisms in world models One Image is All You Need: Agentic One-Shot Image Generation via Text-Based World Models for Long-Tail Spatial Perception Orchestrated Reality: From Role-Play to Living, Playable Game Worlds -- LLM-Driven World Simulation as a Parameterized-Action POMDP PLUME: Probabilistic Latent Unified World Modeling and Parameter Estimation for Multi-Finger Manipulation 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 PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs 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 PhysicsMind: Sim and Real Mechanics Benchmarking for Physical Reasoning and Prediction in Foundational VLMs and World Models PiL-World: A Chunk-Wise World Model for VLA Policy-in-the-Loop Evaluation Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model Planning with an Ensemble of World Models Prisma-World: Camera-Controllable Multi-Agent Video World Model Probabilistic Dreaming for World Models Probing the effectiveness of World Models for Spatial Reasoning through Test-time Scaling Quantitative Video World Model Evaluation for Geometric-Consistency Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation 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 ReactSim-Bench: Benchmarking Reactive Behavior World Model Simulation in Autonomous Driving ReactiveGWM: Steering NPC in Reactive Game World Models 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 Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer SCAR: Self-Supervised Continuous Action Representation Learning ST-Gen4D: Embedding 4D Spatiotemporal Cognition into World Model for 4D Generation SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution Self-Supervised JEPA-based World Models for LiDAR Occupancy Completion and Forecasting Self-Supervised Multi-Modal World Model with 4D Space-Time Embedding Solaris: Building a Multiplayer Video World Model in Minecraft SparseWorld: Enhancing End-to-End Autonomous Driving via World Models with Sparse Scene Representation Stealthy World Model Manipulation via Data Poisoning Stereo World Model: Camera-Guided Stereo Video Generation StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement SurgVista: Long-Horizon Surgical World Modeling with Plausible Instrument-Tissue Dynamics TRAP: Tail-aware Ranking Attack for World-Model Planning 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 The Trinity of Consistency as a Defining Principle for General World Models ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators Thinking with Patterns: Breaking the Perceptual Bottleneck in Visual Planning via Pattern Induction Toward World Modeling of Physiological Signals with Chaos-Theoretic Balancing and Latent Dynamics Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends Trimming the Long-Tail of Visual World Modeling Evaluation 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 Driving Tokens: Representation- and Geometry-Guided Discrete Tokenizer for Driving World Models and Planning VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models Value-guided action planning with JEPA world models Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models 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 What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction What-If World: A Causal Benchmark for General World Models in Embodied Scenarios 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-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks World-R1: Reinforcing 3D Constraints for Text-to-Video Generation WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models WorldBench: Disambiguating Physics for Diagnostic Evaluation of World Modelsl WorldCache: Content-Aware Caching for Accelerated Video World Models 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?WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors WorldVLM: Combining World Model Forecasting and Vision-Language Reasoning Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Testl 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 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 YoCausal: How Far is Video Generation from World Model? A Causality Perspective dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation 3D and 4D World Modeling: A Survey 3D4D: An Interactive, Editable, 4D World Model via 3D Video Generation 4D Driving Scene Generation With Stereo Forcing 4DWorldBench: A Comprehensive Evaluation Framework for 3D/4D World Generation Models A Comprehensive Survey on World Models for Embodied AI A Survey on Future Physical World Generation for Autonomous Driving A Survey: Learning Embodied Intelligence from Physical Simulators and World Models A Unified Definition of Hallucination, Or: It's the World Model, Stupid AVD2: Accident Video Diffusion for Accident Video Description 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 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 Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI Benchmarking World-Model Learning Beyond Generative AI: World Models for Clinical Prediction, Counterfactuals, and Planning Bootstrapping World Models from Dynamics Models in Multimodal Foundation Models CLARITY: Medical World Model for Guiding Treatment Decisions by Modeling Context-Aware Disease Trajectories in Latent Space 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 Consistent World Models via Foresight Diffusion Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models Cosmos-Transfer1 Counterfactual World Models via Digital Twin-conditioned Video Diffusion Ctrl-World: A Controllable Generative World Model for Robot Manipulation DMWM: Dual-Mind World Model with Long-Term Imagination 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 Dexterous World Models DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformer Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning DreamerV3-XP: Optimizing exploration through uncertainty estimation Dreamland: Controllable World Creation with Simulator and Generative Models Drive&Gen: Co-Evaluating End-to-End Driving and Video Generation Models 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 Emu3.5: Native Multimodal Models are World Learners End-to-End Driving with Online Trajectory Evaluation via BEV World Model EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation Evaluating Gemini Robotics Policies in a Veo World Simulator Evaluating Robot Policies in a World Model Exploring the Evolution of Physics Cognition in Video Generation: A Survey From 2D to 3D Cognition: A Brief Survey of General 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 GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving 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 GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction Generating Multimodal Driving Scenes via Next-Scene Prediction Generating Symbolic World Models via Test-time Scaling of Large Language Models Generative Physical AI in Vision: A Survey GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation GigaWorld-0: World Models as Data Engine to Empower Embodied AI GrndCtrl: Grounding World Models via Self-Supervised Reward Alignment How Far Are Surgeons from Surgical World Models? A Pilot Study on Zero-shot Surgical Video Generation with Expert Assessment Hunyuan-GameCraft-2: Instruction-following Interactive Game World Model IPR-1: Interactive Physical Reasoner KAN-Dreamer: Benchmarking Kolmogorov-Arnold Networks as Function Approximators in World Models KeyWorld: Key Frame Reasoning Enables Effective and Efficient World Models LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures LUMOS: Language-Conditioned Imitation Learning with World Models LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation Learning Abstract World Models with a Group-Structured Latent Space Learning Real-World Action-Video Dynamics with Heterogeneous Masked Autoregression 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 Long-Context State-Space Video World Models LongLive: Real-time Interactive Long Video Generation LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE ManipDreamer: Boosting Robotic Manipulation World Model with Action Tree and Visual Guidance 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 MiLA: Multi-view Intensive-fidelity Long-term Video Generation World Model for Autonomous Driving MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft MoWM: Mixture-of-World-Models for Embodied Planning via Latent-to-Pixel Feature Modulation MorphoSim: An Interactive, Controllable, and Editable Language-guided 4D World Simulator NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards Navigation World Models Occ-LLM: Enhancing Autonomous Driving with Occupancy-Based Large Language Models OccTENS: 3D Occupancy World Model via Temporal Next-Scale Prediction Occupancy World Model for Robots OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving 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 PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulation Planning with Reasoning using Vision Language World Model ProTerrain: Probabilistic Physics-Informed Rough Terrain World Modeling ProphetDWM: ProphetDWM: A Driving World Model for Rolling Out Future Actions and Videos RELIC: Interactive Video World Model with Long-Horizon Memory RadarGen: Automotive Radar Point Cloud Generation from Cameras ReSim: Reliable World Simulation for Autonomous Driving Remote Sensing-Oriented World Model Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks RoboScape: Physics-informed Embodied World Model SAMPO: Scale-wise Autoregression with Motion PrOmpt for generative world models STORM: Search-Guided Generative World Models for Robotic Manipulation 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 Sekai: A Video Dataset towards World Exploration 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 SmallWorlds: Assessing Dynamics Understanding of World Models in Isolated Environments 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 TeraSim-World: Worldwide Safety-Critical Data Synthesis for End-to-End Autonomous Driving Terra: Explorable Native 3D World Model with Point Latents 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 Safety Challenge of World Models for Embodied AI Agents: A Review Think Before You Drive: World Model-Inspired Multimodal Grounding for Autonomous Vehicles Thinking Ahead: Foresight Intelligence in MLLMs and World Models 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 UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving VFMF: World Modeling by Forecasting Vision Foundation Model Features VL-SAFE: Vision-Language Guided Safety-Aware Reinforcement Learning with World Models for Autonomous Driving VaViM and VaVAM: Autonomous Driving through Video Generative Modeling 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 Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation 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 Whole-Body Conditioned Egocentric Video Prediction WoW: Towards a World omniscient World model Through Embodied Interaction World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning World Models That Know When They Don't Know: Controllable Video Generation with Calibrated Uncertainty World Models as Reference Trajectories for Rapid Motor Adaptation 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 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 WorldVLA: Towards Autoregressive Action World Model Xray2Xray: World Model from Chest X-rays with Volumetric Context Yume-1.5: A Text-Controlled Interactive World Generation Model Zero-Splat TeleAssist: A Zero-Shot Pose Estimation Framework for Semantic Teleoperation BWArea Model: Learning World Model, Inverse Dynamics, and Policy for Controllable Language Generation Cam4DOCC: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications Can Language Models Serve as Text-Based World Simulators?CityBench: Evaluating the Capabilities of Large Language Model as World Model DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning DOME: Taming Diffusion Model into High-Fidelity Controllable Occupancy World Model Diffusion for World Modeling: Visual Details Matter in Atari Doe-1: Closed-Loop Autonomous Driving with Large World Model Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization DriveGenVLM: Real-world Video Generation for Vision Language Model based Autonomous Driving Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving DrivingDiffusion: Layout-Guided multi-view driving scene video generation with latent diffusion model DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT 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 Genie: Generative Interactive Environments How Far is Video Generation from World Model: A Physical Law Perspective Imagine-2-Drive: High-Fidelity World Modeling in CARLA for Autonomous Vehicles Improving Token-Based World Models with Parallel Observation Prediction Language Agents Meet Causality -- Bridging LLMs and Causal World Models Learning Latent Dynamic Robust Representations for World Models Making Large Language Models into World Models with Precondition and Effect Knowledge 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 OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving Owl-1: Omni World Model for Consistent Long Video Generation Panacea: Panoramic and Controllable Video Generation for Autonomous Driving Planning with Adaptive World Models for Autonomous Driving Probing Multimodal LLMs as World Models for Driving SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control Terra ACT-Bench: Towards Action Controllable World Models for Autonomous Driving Think2Drive: Efficient Reinforcement Learning by Thinking in Latent World Model for Quasi-Realistic Autonomous Driving Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability WHALE: Towards Generalizable and Scalable World Models for Embodied Decision-making WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation World Models for Autonomous Driving: An Initial Survey World Models: The Safety Perspective WorldSimBench: Towards Video Generation Models as World Simulator STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction Transformers are Sample Efficient World Models DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving PerceptUI: PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluation MemoBench: Benchmarking World Modeling in Dynamically Changing Environments Fast LeWorldModel Orca: The World is in Your Mind OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning 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 WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory WorldOdysseyBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models From World Models to World Action Models: A Concise Tutorial for Robotics OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration Bridge-WA: Predicting Where and How the World Changes for Robotic Action LWDrive: Layer-Wise World-Model-Guided Vision-Language Model Planning for Autonomous Driving Long-term Traffic Simulation via Structured Autoregressive Modeling ForgeDrive: Bidirectional Cross-Conditioning for Unified Visual-Action Generation in Autonomous Driving One Video, One World: Turning Monocular Video into Physical 4D Scenes WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots 3D Point World Models: Point Completion Enables More Accurate Dynamics Learning RetailSMV: Exocentric vs. Egocentric Adaptation of Foundation Video World Models in Retail AGI Maze as a Benchmark Framework for World-Modeling Agents 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 EnerVerse-AC: Envisioning Embodied Environments with Action Condition GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics Last-Meter Precision Navigation for UAVs: A Diffusion-Refined Aerial Visual Servoing Approach Operator-on-F complements value-equivalence: a planning-time diagnostic for latent world models CRISP: A Spatiotemporal Camera-Radar Backbone for Driving via Forecasting-Based World-Model Pretraining Mask2Real-WM: Segmentation Masks as a Sim-to-Real Bridge for Controllable Dexterous World Models DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation MoP-JEPA: Hard-Assigned Predictor Mixtures for Stochastic JEPA World Models Multiplayer Interactive World Models with Representation Autoencoders AlayaWorld: Long-Horizon and Playable Video World Generation Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models Infinite Worlds with Versatile Interactions Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model Versatile Behavior Diffusion for Generalized Traffic Agent Simulation Learning to drive from a world on rails Video = World + Event Stream BadWAM: When World-Action Models Dream Right but Act Wrong Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence Collision Avoidance Detour for Multi-Agent Trajectory Forecasting From Pixels to States: Rethinking Interactive World Models as Game Engines 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 Orbis 2: A Hierarchical World Model for Driving 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 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 SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction 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 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 Playable Video Generation Playable Environments: Video Manipulation in Space and Time VideoPhy: Evaluating Physical Commonsense for Video Generation Video Generation Models in Robotics - Applications, Research Challenges, Future Directions OSCBench: Benchmarking Object State Change in Text-to-Video Generation 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 StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation Curiosity-Driven Exploration by Self-Supervised Prediction Planning from Pixels using Inverse Dynamics Models 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 DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation WorldClaw: Agentic 3D Open-World Generation at Scale

Resources

Hugging Face Paper

Tags

region:usworld-modelvideo-generationbenchmarkreproducibility