Kaiwen Yan

linrany

·

lin-rany

AI & ML interests

None yet

Recent Activity

upvoted a paper 9 days ago

TraceForge: Distilling with Your Own Thinking

upvoted a paper about 1 month ago

onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction

authored a paper 9 months ago

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

View all activity

Organizations

Collections 2

Papers 1

arxiv:2602.10604

models 1

linrany/Qwen2.5-1.5B-Open-R1-Distill

Text Generation • 2B • Updated Feb 1, 2025 • 21

datasets 5

linrany/DRQA_Efficient_Reasoning_CoT

Viewer • Updated Jun 30, 2025 • 59.4k • 11

linrany/math_batch_distill_easy_set

Viewer • Updated Jun 29, 2025 • 14.6k • 8

linrany/math_multi_model_distill

Viewer • Updated Jun 16, 2025 • 27.6k • 12

linrany/DeepMath_103K_only_num

Viewer • Updated Jun 2, 2025 • 41.1k • 25

linrany/CodeIF

Viewer • Updated Feb 8, 2025 • 1.2k • 9 • 3