9 8

Xiangyu

xixy

https://xixy.github.io/

AI & ML interests

None yet

Recent Activity

new activity 2 days ago

a-m-team/AM-DeepSeek-R1-0528-Distilled:什么叫中国速度！

commented on a paper 4 days ago

Reinforcement Pre-Training

new activity 6 days ago

a-m-team/AM-DeepSeek-R1-0528-Distilled:请问有code相关的评测结果吗？

View all activity

Organizations

None yet

xixy's activity

New activity in a-m-team/AM-DeepSeek-R1-0528-Distilled 2 days ago

什么叫中国速度！

#1 opened 10 days ago by

reign12

commented a paper 4 days ago

Reinforcement Pre-Training

Paper • 2506.08007 • Published 5 days ago • 199 •

New activity in a-m-team/AM-DeepSeek-R1-0528-Distilled 6 days ago

请问有code相关的评测结果吗？

#2 opened 6 days ago by

xixy

commented a paper 12 days ago

Why Distillation can Outperform Zero-RL: The Role of Flexible Reasoning

Paper • 2505.21067 • Published 19 days ago • 3 •

authored a paper 19 days ago

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

Paper • 2505.17652 • Published 23 days ago • 6

upvoted a paper 19 days ago

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

Paper • 2505.17652 • Published 23 days ago • 6

upvoted a paper 25 days ago

Not All Correct Answers Are Equal: Why Your Distillation Source Matters

Paper • 2505.14464 • Published 26 days ago • 8

commented a paper 26 days ago

Model Merging in Pre-training of Large Language Models

Paper • 2505.12082 • Published 28 days ago • 36 •

upvoted a collection about 2 months ago

Qwen3

Collection

40 items • Updated 25 days ago • 756

authored a paper 3 months ago

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

Paper • 2503.01506 • Published Mar 3 • 9

upvoted a paper 3 months ago

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

Paper • 2503.01506 • Published Mar 3 • 9

commented a paper 7 months ago

IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization

Paper • 2411.06208 • Published Nov 9, 2024 • 21 •

upvoted a paper 10 months ago

Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems

Paper • 2408.16293 • Published Aug 29, 2024 • 27

commented a paper 12 months ago

Scaling Synthetic Data Creation with 1,000,000,000 Personas

Paper • 2406.20094 • Published Jun 28, 2024 • 102 •

upvoted 3 papers about 1 year ago

commented a paper about 1 year ago

Rho-1: Not All Tokens Are What You Need

Paper • 2404.07965 • Published Apr 11, 2024 • 94 •