Poster by Shixuan Liu Papers
2 papers found
Conference
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Shenzhi Wang, Le Yu, Chang Gao et al.
NEURIPS 2025arXiv:2506.01939
305
citations
RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domains
Tianle Pu, Zijie Geng, Haoyang Liu et al.
NEURIPS 2025arXiv:2511.02331
8
citations