DeyangKong

DeyangKong

·

DeyangKong

AI & ML interests

Natural Language Processing

Recent Activity

authored a paper 14 days ago

Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models

upvoted a paper 17 days ago

Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models

submitted a paper 17 days ago

Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models

View all activity

Organizations

commented 2 papers over 1 year ago

Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective

Paper • 2505.17652 • Published May 23, 2025 • 6 •

SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity

Paper • 2503.01506 • Published Mar 3, 2025 • 10 •