Runxuan Liu
RunxuanLiu
AI & ML interests
None yet
Recent Activity
updated a collection about 6 hours ago
Open World Agent upvoted a paper 8 days ago
dNaViT: Discrete Codes are General-Purpose Visual Representations updated a collection 8 days ago
Recursive Self-improvementOrganizations
None yet
Diffusion Model
World Model
-
World Action Modeling with Progressive Visual Planning
Paper • 2610.02508 • Published • 84 -
World Observer: Joint Actor-Observer Generation for Persistent World Modeling
Paper • 2610.02162 • Published • 60 -
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation
Paper • 2610.20571 • Published • 60 -
Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds
Paper • 2610.27999 • Published • 96
On-Policy Distillation
Recursive Self-improvement
Open World Agent
-
Harness^2: Recursive Agent Harnessing for an Open World
Paper • 2610.14224 • Published • 69 -
S-Space: Exploring Spatial Workspace in Multimodal Language Models
Paper • 2610.13527 • Published • 51 -
Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence
Paper • 2609.34563 • Published • 22 -
Player-1: Learning to Play from Synthetic Experience
Paper • 2610.20584 • Published • 57
Visual Coding
-
RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement
Paper • 2609.39045 • Published • 42 -
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness
Paper • 2610.08621 • Published • 69 -
AgentGarten: Code Worlds for Evolving Agents
Paper • 2610.12374 • Published • 60
Model Architecture
Native Multimodal Model Architecture
Recursive Self-improvement
Diffusion Model
Open World Agent
-
Harness^2: Recursive Agent Harnessing for an Open World
Paper • 2610.14224 • Published • 69 -
S-Space: Exploring Spatial Workspace in Multimodal Language Models
Paper • 2610.13527 • Published • 51 -
Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence
Paper • 2609.34563 • Published • 22 -
Player-1: Learning to Play from Synthetic Experience
Paper • 2610.20584 • Published • 57
World Model
-
World Action Modeling with Progressive Visual Planning
Paper • 2610.02508 • Published • 84 -
World Observer: Joint Actor-Observer Generation for Persistent World Modeling
Paper • 2610.02162 • Published • 60 -
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation
Paper • 2610.20571 • Published • 60 -
Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds
Paper • 2610.27999 • Published • 96
Visual Coding
-
RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement
Paper • 2609.39045 • Published • 42 -
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness
Paper • 2610.08621 • Published • 69 -
AgentGarten: Code Worlds for Evolving Agents
Paper • 2610.12374 • Published • 60
On-Policy Distillation
Model Architecture