Xiwei Pan

isPANN

4 1

·

isPANN

AI & ML interests

None yet

Recent Activity

liked a Space 14 days ago

dlouapre/nlp-before-llms

authored a paper 7 months ago

Problem Reductions at Scale: Agentic Integration of Computationally Hard Problems

upvoted a paper about 1 year ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

View all activity

Organizations

Papers 1

arxiv:2604.11535

models 0

None public yet

datasets 0

None public yet