EvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models
cs.CV, cs.AI
Submitted: 2026-11-04
Updated: 2026-11-05
Project page: https://tommy-bie.github.io/projects/evoworld/Abstract
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Generative World Simulation with DAO and JING
- Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
- Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control
- LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models
- A Survey of World Models for Autonomous Driving
- Infinite Worlds with Versatile Interactions
- LTX-2: Efficient Joint Audio-Visual Foundation Model
- Training Agents Inside of Scalable World Models
- Matrix-game 2.0: An open-source, real-time, and streaming interactive world model
- A Comprehensive Survey on World Models for Embodied AI
- UniFuture: A 4D Driving World Model for Future Generation and Perception
- Current World Models Lack a Persistent State Core
- Closing the Loop: Training-Free Revisit Consistency for Autoregressive Generative Rendering
- Out of Sight, Out of Mind? Evaluating State Evolution in Video World Models
- BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression
- Seedance 2.0: Advancing Video Generation for World Complexity
- AlayaWorld: Long-Horizon and Playable Video World Generation
- Advancing Open-source World Models
- Wan: Open and Advanced Large-Scale Video Generative Models
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