Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems
Paper • 2606.18837 • Published • 58
Sun Haotian
liamth27
AI & ML interests
Open-source multimodal experiment workflows. Mostly focused on experiments.
Recent Activity
liked a dataset 13 days ago
applied-ai-018/pretraining_v1-omega_books liked a dataset 21 days ago
arrow-hf/vla-framework-openad-eval liked a dataset 26 days ago
Open-Orca/OpenOrcaOrganizations
None yet
upvoted a paper 2 months ago
upvoted 4
papers 3 months ago
Colored Noise Diffusion Sampling
Paper • 2605.30332 • Published • 25
SpatialBench: Is Your Spatial Foundation Model an All-Round Player?
Paper • 2605.27367 • Published • 73
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
Paper • 2605.28816 • Published • 433
Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation
Paper • 2605.16003 • Published • 5
upvoted 3
papers 4 months ago
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Paper • 2604.20796 • Published • 243
DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off
Paper • 2604.13902 • Published • 62
CocoaBench: Evaluating Unified Digital Agents in the Wild
Paper • 2604.11201 • Published • 37
upvoted 5
papers 5 months ago
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Paper • 2604.06628 • Published • 330
Learning to Hint for Reinforcement Learning
Paper • 2604.00698 • Published • 9
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
Paper • 2604.02721 • Published • 640
Adam's Law: Textual Frequency Law on Large Language Models
Paper • 2604.02176 • Published • 511
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence
Paper • 2603.28032 • Published • 344