Xiangyu's picture

4 5

Xiangyu

xixy

·

https://xixy.github.io/

AI & ML interests

None yet

Recent Activity

authored a paper 6 days ago

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

upvoted a paper 6 days ago

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

commented on a paper 4 months ago

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

View all activity

Organizations

None yet

xixy's activity

upvoted a paper 6 days ago

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

Paper • 2503.01506 • Published 7 days ago • 8

upvoted a paper 6 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 • 26

upvoted 2 papers 10 months ago

Chameleon: Mixed-Modal Early-Fusion Foundation Models

Paper • 2405.09818 • Published May 16, 2024 • 131

CodeShell Technical Report

Paper • 2403.15747 • Published Mar 23, 2024 • 1

upvoted a paper 11 months ago

Rho-1: Not All Tokens Are What You Need

Paper • 2404.07965 • Published Apr 11, 2024 • 90