AgiWorld: An Agentic Video World Model for Building Persistent Worlds
cs.CV, cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Project page: https://bshfang.github.io/agiworld
Terminology
Sources
- Qwen3-VL Technical Report
- Positional Encoding Field
- PE-Field 4D: Video Generation Models as Canvas
- Mixture of Contexts for Long Video Generation
- WonderVerse: Extendable 3D Scene Generation with Video Generative Models
- Infinite Worlds with Versatile Interactions
- Matrix-game 2.0: An open-source, real-time, and streaming interactive world model
- RELIC: Interactive Video World Model with Long-Horizon Memory
- MagicWorld: Towards Long-Horizon Stability for Interactive Video World Exploration
- Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition
- VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning
- Depth Anything 3: Recovering the Visual Space from Any Views
- Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation
- TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigation
- Lyra 2.0: Explorable Generative 3D Worlds
- WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
- Advancing Open-source World Models
- Wan: Open and Advanced Large-Scale Video Generative Models
- Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
- Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory
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