Runxuan Liu
RunxuanLiu
AI & ML interests
None yet
Recent Activity
updated a collection 7 days ago
World Model commentedon a paper 9 days ago
EvolvingBrain: An Adaptive Skill System for Multi-modal Agents Self-Evolution in Open WorldsOrganizations
None yet
Open World Agent
-
Harness^2: Recursive Agent Harnessing for an Open World
Paper • 2610.14224 • Published • 68 -
S-Space: Exploring Spatial Workspace in Multimodal Language Models
Paper • 2610.13527 • Published • 52 -
Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence
Paper • 2609.34563 • Published • 23 -
Player-1: Learning to Play from Synthetic Experience
Paper • 2610.20584 • Published • 56
Visual Coding
-
RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement
Paper • 2609.39045 • Published • 45 -
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness
Paper • 2610.08621 • Published • 68 -
AgentGarten: Code Worlds for Evolving Agents
Paper • 2610.12374 • Published • 58
Model Architecture
Diffusion Model
World Model
-
World Action Modeling with Progressive Visual Planning
Paper • 2610.02508 • Published • 83 -
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 • 61 -
Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds
Paper • 2610.27999 • Published • 98
On-Policy Distillation
Recursive Self-improvement
Diffusion Model
Open World Agent
-
Harness^2: Recursive Agent Harnessing for an Open World
Paper • 2610.14224 • Published • 68 -
S-Space: Exploring Spatial Workspace in Multimodal Language Models
Paper • 2610.13527 • Published • 52 -
Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence
Paper • 2609.34563 • Published • 23 -
Player-1: Learning to Play from Synthetic Experience
Paper • 2610.20584 • Published • 56
World Model
-
World Action Modeling with Progressive Visual Planning
Paper • 2610.02508 • Published • 83 -
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 • 61 -
Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds
Paper • 2610.27999 • Published • 98
Visual Coding
-
RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement
Paper • 2609.39045 • Published • 45 -
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness
Paper • 2610.08621 • Published • 68 -
AgentGarten: Code Worlds for Evolving Agents
Paper • 2610.12374 • Published • 58
On-Policy Distillation
Model Architecture