WAM-Sim0.1: World Anchored Memory Meets Online RL for Consistent and Realistic Driving Simulation
cs.CV
Submitted: 2026-11-05
Updated: 2026-11-05
Project page: https://fudan-generative-vision.github.io/WAM-Sim
Terminology
Sources
- VideoPhy: Evaluating Physical Commonsense for Video Generation
- NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
- Training Diffusion Models with Reinforcement Learning
- SkyReels-V2: Infinite-length Film Generative Model
- UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving
- M$^\text{4}$World: A Multi-view Multimodal Driving World Model for Interactive Object Manipulation and Minute-long Streaming
- MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control
- DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation
- InfinityDrive: Breaking Time Limits in Driving World Models
- GAIA-1: A Generative World Model for Autonomous Driving
- DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT
- Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft
- ADriver-I: A General World Model for Autonomous Driving
- Spatial Retrieval Augmented Autonomous Driving
- DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformer
- WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World
- Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning
- Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
- DreamForge: Motion-Aware Autoregressive Video Generation for Multi-View Driving Scenes
- Cosmos World Foundation Model Platform for Physical AI
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs