Skip to content
conftrace_

world model

311 papers

WM

Papers

Empowering World Models with Reflection for Embodied Video Prediction ICML 2025 End-to-End Driving with Online Trajectory Evaluation via BEV World Model ICCV 2025 Enhancing End-to-End Autonomous Driving with Latent World Model ICLR 2025 Epona: Autoregressive Diffusion World Model for Autonomous Driving ICCV 2025 Exploration-Driven Generative Interactive Environments CVPR 2025 FLIP: Flow-Centric Generative Planning as General-Purpose Manipulation World Model ICLR 2025 FOSP: Fine-tuning Offline Safe Policy through World Models ICLR 2025 FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making ICML 2025 Gaussian-based World Model: Gaussian Priors for Voxel-Based Occupancy Prediction and Future Motion Prediction ICCV 2025 GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction CVPR 2025 GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control CVPR 2025 General agents need world models ICML 2025 Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis RSS 2025 GLAM: Global-Local Variation Awareness in Mamba-based World Model AAAI 2025 HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation ICCV 2025 Hierarchical World Models as Visual Whole-Body Humanoid Controllers ICLR 2025 I2-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting ICCV 2025 InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video Generation ICCV 2025 IRASim: A Fine-Grained World Model for Robot Manipulation ICCV 2025 Knowledge Retention in Continual Model-Based Reinforcement Learning ICML 2025 Learning Structured World Models From and For Physical Interactions AAAI 2025 Learning to Search from Demonstration Sequences ICLR 2025 Learning Transformer-based World Models with Contrastive Predictive Coding ICLR 2025 Learning View-invariant World Models for Visual Robotic Manipulation ICLR 2025 LLMs as World Models: Data-Driven and Human-Centered Pre-Event Simulation for Disaster Impact Assessment EMNLP 2025