Mingyu Jin

When Evolution Meets Momentum: Orchestrating Goal-oriented and Process-oriented reasoning for LLM Inference Scaling

Do Larger Language Models Generalize Better? A Scaling Law for Implicit Reasoning at Pretraining Time

Exploring the Entropy Mechanism in LLM Agents On-policy Optimization

AIOS: LLM Agent Operating System

Visual Agents as Fast and Slow Thinkers

Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding

From Commands to Prompts: LLM-based Semantic File System for AIOS

Hallucinating LLM Could Be Creative

iAgent: LLM Agent as a Shield between User and Recommender Systems

LLM as GNN: Graph Vocabulary Learning for Graph Foundation Model