Yeyun Gong's picture

1 3

Yeyun Gong

yegong

·

AI & ML interests

None yet

Recent Activity

authored a paper about 1 month ago

Behind RoPE: How Does Causal Mask Encode Positional Information?

authored a paper 5 months ago

TL;DR: Too Long, Do Re-weighting for Effcient LLM Reasoning Compression

upvoted a paper 9 months ago

Optimizing Large Language Model Training Using FP4 Quantization

View all activity

Organizations

None yet

upvoted 2 papers 9 months ago

Optimizing Large Language Model Training Using FP4 Quantization

Paper • 2501.17116 • Published Jan 28 • 37

Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models

Paper • 2501.13629 • Published Jan 23 • 48

upvoted a paper over 1 year ago

Rho-1: Not All Tokens Are What You Need

Paper • 2404.07965 • Published Apr 11, 2024 • 93