#World Models

51개의 포스트

[논문리뷰] OpenWorldLib: A Unified Codebase and Definition of Advanced World Models

arXiv에 게시된 'OpenWorldLib: A Unified Codebase and Definition of Advanced World Models' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Unified Inference Framework #Multimodal Reasoning #Vision-Language-Action #3D Generation #Interactive Video Generation

2026년 4월 6일

[논문리뷰] Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models

arXiv에 게시된 'Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #4D Generation #Interactive Response #Evaluation Benchmark #Omni-WorldSuite #Omni-Metrics #AgenticScore #Causal Consistency

2026년 3월 23일

[논문리뷰] MosaicMem: Hybrid Spatial Memory for Controllable Video World Models

Songheng Yin이 arXiv에 게시한 'MosaicMem: Hybrid Spatial Memory for Controllable Video World Models' 논문에 대한 자세한 리뷰입니다.

#Review #Spatial Memory #World Models #Video Diffusion Models #Hybrid Memory #Controllable Video Generation #Long-horizon Consistency #Patch-and-Compose

2026년 3월 18일

[논문리뷰] Reward Prediction with Factorized World States

Hongbo Zhao이 arXiv에 게시한 'Reward Prediction with Factorized World States' 논문에 대한 자세한 리뷰입니다.

#Review #Reward Prediction #World Models #State Representation #Large Language Models #Zero-shot Learning #Reinforcement Learning #Planning #Factorization

2026년 3월 10일

[논문리뷰] WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching

Mingqiang Wu이 arXiv에 게시한 'WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Diffusion Models #Inference Acceleration #Feature Caching #Heterogeneous Tokens #Curvature Prediction #Adaptive Skipping

2026년 3월 8일

[논문리뷰] Next Embedding Prediction Makes World Models Stronger

arXiv에 게시된 'Next Embedding Prediction Makes World Models Stronger' 논문에 대한 자세한 리뷰입니다.

#Review #Model-Based Reinforcement Learning #World Models #Decoder-Free #Temporal Transformer #Next-Embedding Prediction #Latent Representation #Partial Observability #Barlow Twins

2026년 3월 3일

[논문리뷰] Chain of World: World Model Thinking in Latent Motion

Lei Fan이 arXiv에 게시한 'Chain of World: World Model Thinking in Latent Motion' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #World Models #Latent Motion #Embodied Intelligence #Temporal Reasoning #Disentangled Representation #Robotics #Pretraining

2026년 3월 3일

[논문리뷰] The Trinity of Consistency as a Defining Principle for General World Models

arXiv에 게시된 'The Trinity of Consistency as a Defining Principle for General World Models' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Multimodal Generative AI #Consistency Theory #Spatial-Temporal Reasoning #Causal Simulation #AI Benchmarking #Artificial General Intelligence

2026년 2월 26일

[논문리뷰] Causal-JEPA: Learning World Models through Object-Level Latent Interventions

arXiv에 게시된 'Causal-JEPA: Learning World Models through Object-Level Latent Interventions' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Object-Centric Representations #Latent Interventions #Masked Prediction #Causal Inductive Bias #Joint Embedding Predictive Architecture (JEPA)#Visual Question Answering (VQA)#Model Predictive Control (MPC)

2026년 2월 17일

[논문리뷰] RISE: Self-Improving Robot Policy with Compositional World Model

arXiv에 게시된 'RISE: Self-Improving Robot Policy with Compositional World Model' 논문에 대한 자세한 리뷰입니다.

#Review #Robot Learning #Reinforcement Learning #World Models #Compositional Models #Robotic Manipulation #Self-Improving #Vision-Language-Action (VLA)

2026년 2월 12일

[논문리뷰] GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning

arXiv에 게시된 'GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #VLA Models #World Models #Reinforcement Learning #Robotic Manipulation #Long-Horizon Control #Human-in-the-Loop #Continual Learning

2026년 2월 12일

[논문리뷰] WorldCompass: Reinforcement Learning for Long-Horizon World Models

arXiv에 게시된 'WorldCompass: Reinforcement Learning for Long-Horizon World Models' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #World Models #Video Generation #Autoregressive Generation #Long-Horizon #Post-training #Diffusion Models #Reward Functions

2026년 2월 9일

[논문리뷰] OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions

heroding77이 arXiv에 게시한 'OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Benchmarking #Inductive Reasoning #Long-Horizon Tasks #Active Exploration #World Models #Autonomous Discovery

2026년 2월 8일

[논문리뷰] Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks

arXiv에 게시된 'Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Unified Framework #Multimodal AI #Embodied AI #Physical Understanding #Long-term Consistency #AI Agents #Generative Models

2026년 2월 3일

[논문리뷰] Advancing Open-source World Models

arXiv에 게시된 'Advancing Open-source World Models' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Open-source AI #Video Generation #Real-time Simulation #Long-term Memory #Action-Conditioned Learning #Generative Models #Embodied AI

2026년 1월 28일

[논문리뷰] Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models

arXiv에 게시된 'Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal AI #World Models #Visual Generation #Chain-of-Thought (CoT)#Multimodal Reasoning #Unified Multimodal Models #Spatial-Physical Reasoning

2026년 1월 27일

[논문리뷰] Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning

arXiv에 게시된 'Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning' 논문에 대한 자세한 리뷰입니다.

#Review #Video Models #Visuomotor Control #Robot Policy #Fine-tuning #Diffusion Models #World Models #Model-based Planning #Imitation Learning

2026년 1월 22일

[논문리뷰] Aligning Agentic World Models via Knowledgeable Experience Learning

arXiv에 게시된 'Aligning Agentic World Models via Knowledgeable Experience Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic AI #World Models #Experience Learning #LLMs #Physical Hallucinations #Embodied AI #Predictive Coding #Knowledge Repository

2026년 1월 20일

[논문리뷰] Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models

Wenjie Li이 arXiv에 게시한 'Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #World Models #Adaptive Planning #Lookahead #Reinforcement Learning #POMDP #Task Planning #Reasoning

2026년 1월 14일

[논문리뷰] Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals

Arjan Chakravarthy이 arXiv에 게시한 'Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #World Models #Physics-Conditioned Goals #Causal Planning #Force Vectors #Zero-Shot Generalization #Diffusion Models #Robotics Planning

2026년 1월 11일

[논문리뷰] SurgWorld: Learning Surgical Robot Policies from Videos via World Modeling

arXiv에 게시된 'SurgWorld: Learning Surgical Robot Policies from Videos via World Modeling' 논문에 대한 자세한 리뷰입니다.

#Review #Surgical Robotics #World Models #Video Generation #Imitation Learning #Inverse Dynamics Model #Synthetic Data #Vision-Language-Action Models #Data Scarcity

2025년 12월 29일

[논문리뷰] Act2Goal: From World Model To General Goal-conditioned Policy

arXiv에 게시된 'Act2Goal: From World Model To General Goal-conditioned Policy' 논문에 대한 자세한 리뷰입니다.

#Review #Goal-Conditioned Policy #World Models #Robotic Manipulation #Multi-Scale Temporal Hashing #Online Adaptation #Hindsight Experience Replay #LoRA Finetuning #Zero-shot Generalization

2025년 12월 29일

[논문리뷰] Active Intelligence in Video Avatars via Closed-loop World Modeling

Cheng Meng이 arXiv에 게시한 'Active Intelligence in Video Avatars via Closed-loop World Modeling' 논문에 대한 자세한 리뷰입니다.

#Review #Video Avatars #Active Intelligence #World Models #Closed-loop Reasoning #POMDP #Generative AI #Hierarchical Planning #Cognitive Architecture

2025년 12월 23일

[논문리뷰] The World is Your Canvas: Painting Promptable Events with Reference Images, Trajectories, and Text

arXiv에 게시된 'The World is Your Canvas: Painting Promptable Events with Reference Images, Trajectories, and Text' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Video Generation #Multimodal Control #Trajectory Guidance #Reference Images #Promptable Events #Cross-Attention #Diffusion Models

2025년 12월 18일

[논문리뷰] MMGR: Multi-Modal Generative Reasoning

Haozhe Zhao이 arXiv에 게시한 'MMGR: Multi-Modal Generative Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-Modal Generative Models #Reasoning Evaluation #World Models #Physical Commonsense #Abstract Reasoning #Embodied Navigation #VLM-based Evaluation #Temporal Consistency

2025년 12월 16일

[논문리뷰] Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform

Muyao Niu이 arXiv에 게시한 'Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform' 논문에 대한 자세한 리뷰입니다.

#Review #Neural Rendering #3D Gaussian Splatting #WebGPU #ONNX Inference #World Models #Real-time Rendering #Browser-based #Dynamic Scenes

2025년 12월 9일

[논문리뷰] MIND-V: Hierarchical Video Generation for Long-Horizon Robotic Manipulation with RL-based Physical Alignment

arXiv에 게시된 'MIND-V: Hierarchical Video Generation for Long-Horizon Robotic Manipulation with RL-based Physical Alignment' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Robotic Manipulation #Hierarchical Framework #Reinforcement Learning #Diffusion Models #World Models #Cognitive Science #Physical Alignment

2025년 12월 9일

[논문리뷰] UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation

arXiv에 게시된 'UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Multi-modal Learning #Multi-task Learning #Zero-shot Generalization #Diffusion Models #World Models #Video Understanding

2025년 12월 8일

[논문리뷰] TV2TV: A Unified Framework for Interleaved Language and Video Generation

arXiv에 게시된 'TV2TV: A Unified Framework for Interleaved Language and Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Language Modeling #Multimodal AI #Interleaved Generation #Flow Matching #Transformer #Controllability #World Models

2025년 12월 4일

[논문리뷰] EgoLCD: Egocentric Video Generation with Long Context Diffusion

arXiv에 게시된 'EgoLCD: Egocentric Video Generation with Long Context Diffusion' 논문에 대한 자세한 리뷰입니다.

#Review #Egocentric Video Generation #Long-Context Diffusion #Long-Short Memory #Sparse KV Cache #Memory Regulation Loss #Structured Narrative Prompting #World Models #Embodied AI

2025년 12월 4일

[논문리뷰] Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation

arXiv에 게시된 'Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Audio-Video Multimodal #Joint Denoising #Diffusion Models #Transformer Architecture #World Models #Physical Commonsense #Multimodal Training

2025년 12월 2일

[논문리뷰] GigaWorld-0: World Models as Data Engine to Empower Embodied AI

Chaojun Ni이 arXiv에 게시한 'GigaWorld-0: World Models as Data Engine to Empower Embodied AI' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Embodied AI #Data Generation #Video Generation #3D Scene Reconstruction #Robotics #Vision-Language-Action

2025년 11월 25일

[논문리뷰] Target-Bench: Can World Models Achieve Mapless Path Planning with Semantic Targets?

Zhaowei Lu이 arXiv에 게시한 'Target-Bench: Can World Models Achieve Mapless Path Planning with Semantic Targets?' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Mapless Navigation #Semantic Path Planning #Robot Learning #Video Prediction #Benchmark #Trajectory Generation

2025년 11월 24일

[논문리뷰] SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models

arXiv에 게시된 'SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Vision-Language-Action Models #Reward Shaping #World Models #Self-Referential Learning #Robotics #Trajectory Optimization

2025년 11월 20일

[논문리뷰] Simulating the Visual World with Artificial Intelligence: A Roadmap

Pengfei Wan이 arXiv에 게시한 'Simulating the Visual World with Artificial Intelligence: A Roadmap' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Video Generation #AI Simulation #Generative AI #Physical Plausibility #Interactive AI #Planning #Roadmap

2025년 11월 16일

[논문리뷰] WMPO: World Model-based Policy Optimization for Vision-Language-Action Models

arXiv에 게시된 'WMPO: World Model-based Policy Optimization for Vision-Language-Action Models' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action (VLA)#Reinforcement Learning (RL)#Model-based RL #World Models #Policy Optimization #Robotics #Sample Efficiency #Self-correction

2025년 11월 12일

[논문리뷰] 10 Open Challenges Steering the Future of Vision-Language-Action Models

arXiv에 게시된 '10 Open Challenges Steering the Future of Vision-Language-Action Models' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #Embodied AI #Robotics #Multimodal Perception #Cross-Robot Generalization #Hierarchical Planning #World Models #Robot Safety

2025년 11월 10일

[논문리뷰] Scaling Agent Learning via Experience Synthesis

arXiv에 게시된 'Scaling Agent Learning via Experience Synthesis' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #LLM Agents #Experience Synthesis #World Models #Curriculum Learning #Sim-to-Real Transfer #Web Agents

2025년 11월 9일

[논문리뷰] How Far Are Surgeons from Surgical World Models? A Pilot Study on Zero-shot Surgical Video Generation with Expert Assessment

Yuhao Zhai이 arXiv에 게시한 'How Far Are Surgeons from Surgical World Models? A Pilot Study on Zero-shot Surgical Video Generation with Expert Assessment' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #World Models #Surgical AI #Zero-shot Prediction #Expert Evaluation #Plausibility Gap #Medical Simulation

2025년 11월 9일

[논문리뷰] Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model

Jinwoo Shin이 arXiv에 게시한 'Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #World Models #Diffusion Models #Multimodal Learning #Robotics #Asynchronous Sampling #Diffusion Transformers

2025년 11월 9일

[논문리뷰] LongCat-Video Technical Report

Hongyu Li이 arXiv에 게시한 'LongCat-Video Technical Report' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Diffusion Transformer #RLHF #Sparse Attention #Long Video Generation #Coarse-to-Fine Generation #Multi-task Learning #World Models

2025년 10월 28일

[논문리뷰] WorldGrow: Generating Infinite 3D World

Jia Lu이 arXiv에 게시한 'WorldGrow: Generating Infinite 3D World' 논문에 대한 자세한 리뷰입니다.

#Review #3D World Generation #Infinite Scene Synthesis #Block-wise Generation #Coarse-to-Fine #3D Inpainting #Structured Latent Representation #Virtual Environments #World Models

2025년 10월 27일

[논문리뷰] PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesis

Hui Li이 arXiv에 게시한 'PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesis' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Deformable Objects #Physics Simulation #GNN #Digital Twin #Data Synthesis #Real-to-Sim #Physics-Aware Learning

2025년 10월 27일

[논문리뷰] From Masks to Worlds: A Hitchhiker's Guide to World Models

Shufan Li이 arXiv에 게시한 'From Masks to Worlds: A Hitchhiker's Guide to World Models' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Generative AI #Multimodal Learning #Masked Modeling #Interactive AI #Memory Systems #Autonomous Agents #AI Roadmap

2025년 10월 24일

[논문리뷰] OmniNWM: Omniscient Driving Navigation World Models

Zhujin Liang이 arXiv에 게시한 'OmniNWM: Omniscient Driving Navigation World Models' 논문에 대한 자세한 리뷰입니다.

#Review #Autonomous Driving #World Models #Multi-modal Generation #3D Occupancy #Plücker Ray-maps #Action Control #Dense Rewards #Long-term Forecasting

2025년 10월 23일

[논문리뷰] World-in-World: World Models in a Closed-Loop World

Arda Uzunoglu이 arXiv에 게시한 'World-in-World: World Models in a Closed-Loop World' 논문에 대한 자세한 리뷰입니다.

#Review #World Models #Embodied AI #Closed-Loop Evaluation #Online Planning #Data Scaling #Controllability #Robotic Manipulation

2025년 10월 22일

[논문리뷰] LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training

arXiv에 게시된 'LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training' 논문에 대한 자세한 리뷰입니다.

#Review #LLM #Digital Agents #UI Simulation #Synthetic Data Generation #Targeted Data Synthesis #World Models

2025년 10월 17일

[논문리뷰] PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning

Hengshuang Zhao이 arXiv에 게시한 'PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Video Generation #Physical Plausibility #Reinforcement Learning #Direct Preference Optimization #Physical Representation #Diffusion Models #World Models #Image-to-Video

2025년 10월 16일

[논문리뷰] CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving

arXiv에 게시된 'CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving' 논문에 대한 자세한 리뷰입니다.

#Review #Autonomous Driving #Imitation Learning #Reinforcement Learning #World Models #Latent Space #Dual-Policy #Competitive Learning

2025년 10월 16일

[논문리뷰] Dyna-Mind: Learning to Simulate from Experience for Better AI Agents

Qianhui Wu이 arXiv에 게시한 'Dyna-Mind: Learning to Simulate from Experience for Better AI Agents' 논문에 대한 자세한 리뷰입니다.

#Review #AI Agents #Reinforcement Learning #World Models #Simulation #Reasoning #Language Models #Planning #Interactive AI

2025년 10월 13일

[논문리뷰] VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators

Zirui Ge이 arXiv에 게시한 'VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #Reinforcement Learning #World Models #Fine-tuning #Embodied AI #Robotics #Reward Design #Distribution Shift

2025년 10월 2일