Yeyun Gong's picture

Yeyun Gong

yegong

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 21 hours ago

Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts

authored a paper 9 months ago

Behind RoPE: How Does Causal Mask Encode Positional Information?

authored a paper about 1 year ago

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

View all activity

Organizations

None yet

upvoted a paper about 21 hours ago

Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts

Paper • 2606.05922 • Published 7 days ago • 48

upvoted 2 papers over 1 year ago

Optimizing Large Language Model Training Using FP4 Quantization

Paper • 2501.17116 • Published Jan 28, 2025 • 37

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

Paper • 2501.13629 • Published Jan 23, 2025 • 48

upvoted a paper about 2 years ago

Rho-1: Not All Tokens Are What You Need

Paper • 2404.07965 • Published Apr 11, 2024 • 95