Picture for Junxian He

Junxian He

MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

Add code
Jun 16, 2025
Viaarxiv icon

Pitfalls of Rule- and Model-based Verifiers -- A Case Study on Mathematical Reasoning

Add code
May 28, 2025
Viaarxiv icon

SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond

Add code
May 26, 2025
Viaarxiv icon

Learn to Reason Efficiently with Adaptive Length-based Reward Shaping

Add code
May 21, 2025
Viaarxiv icon

Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging

Add code
May 08, 2025
Viaarxiv icon

Breaking the Data Barrier -- Building GUI Agents Through Task Generalization

Add code
Apr 15, 2025
Viaarxiv icon

Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning

Add code
Apr 11, 2025
Viaarxiv icon

A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond

Add code
Mar 27, 2025
Viaarxiv icon

SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Add code
Mar 24, 2025
Viaarxiv icon

High-Dimensional Interlingual Representations of Large Language Models

Add code
Mar 14, 2025
Viaarxiv icon