Yilei Tu

yileitu

·

https://yileitu.github.io/

AI & ML interests

NLP; LLM

Recent Activity

updated a collection 16 days ago

QAonly_Specialist_Distillation

authored a paper 17 days ago

Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models

authored a paper 17 days ago

Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation

View all activity

Organizations

upvoted 2 papers 17 days ago

Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models

Paper • 2609.13680 • Published 21 days ago • 13

Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation

Paper • 2609.13770 • Published 21 days ago • 9

upvoted a collection 25 days ago

QAonly_Specialist_Distillation

Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation • 67 items • Updated 16 days ago • 1

upvoted 2 collections 3 months ago

🧠 SmolLM3

Smol, multilingual, long-context reasoner • 14 items • Updated Oct 9, 2025 • 111

SmolLM3 pretraining datasets

datasets used in SmolLM3 pretraining • 15 items • Updated Aug 12, 2025 • 58

upvoted a paper over 1 year ago

Could Thinking Multilingually Empower LLM Reasoning?

Paper • 2504.11833 • Published Apr 16, 2025 • 29