Zeyu Qin

qqqzzzyyy

https://alan-qin.github.io/

Alan-Qin

AI & ML interests

Trustworthy ML, AI safety

Recent Activity

liked a dataset 7 days ago

allenai/reward-bench

upvoted a collection 8 days ago

DeepSeek-R1

liked a model 11 days ago

TIGER-Lab/Qwen2.5-Math-7B-CFT

View all activity

Organizations

None yet

qqqzzzyyy's activity

upvoted a collection 8 days ago

DeepSeek-R1

Collection

8 items • Updated Jan 21 • 579

upvoted a collection 12 days ago

NuminaMath

Collection

Datasets and models for training SOTA math LLMs. See our GitHub for training & inference code: https://github.com/project-numina/aimo-progress-prize • 7 items • Updated Feb 10 • 76

upvoted a paper 26 days ago

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Paper • 2502.14739 • Published 26 days ago • 97

upvoted a paper 27 days ago

Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?

Paper • 2502.12215 • Published 30 days ago • 16

upvoted 2 papers about 1 month ago

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Paper • 2502.07316 • Published Feb 11 • 47

s1: Simple test-time scaling

Paper • 2501.19393 • Published Jan 31 • 112

upvoted a paper about 2 months ago

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

Paper • 2501.13629 • Published Jan 23 • 44

upvoted a paper 3 months ago

ProcessBench: Identifying Process Errors in Mathematical Reasoning

Paper • 2412.06559 • Published Dec 9, 2024 • 80

upvoted 2 papers 4 months ago

AgentInstruct: Toward Generative Teaching with Agentic Flows

Paper • 2407.03502 • Published Jul 3, 2024 • 50

Adapting Large Language Models via Reading Comprehension

Paper • 2309.09530 • Published Sep 18, 2023 • 77

upvoted a collection 6 months ago

Qwen2.5-Math

Collection

Math-specific model series based on Qwen2.5 • 11 items • Updated Jan 14 • 78

upvoted a paper 7 months ago

Iterative Reasoning Preference Optimization

Paper • 2404.19733 • Published Apr 30, 2024 • 48

upvoted an article 8 months ago

Article

SmolLM - blazingly fast and remarkably powerful

Jul 16, 2024

• 335

upvoted 2 collections 8 months ago

Qwen1.5

Collection

Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. • 55 items • Updated Nov 28, 2024 • 208

Coding Instruction datasets

Collection

4 items • Updated Nov 25, 2024 • 1

upvoted a collection 9 months ago

Awesome SFT datasets

Collection

A curated list of interesting datasets to fine-tune language models with. • 43 items • Updated Apr 12, 2024 • 129

upvoted a paper 9 months ago

Adam-mini: Use Fewer Learning Rates To Gain More

Paper • 2406.16793 • Published Jun 24, 2024 • 68

upvoted a paper 11 months ago

AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

Paper • 2404.16873 • Published Apr 21, 2024 • 29

upvoted a paper 12 months ago

Localizing Paragraph Memorization in Language Models

Paper • 2403.19851 • Published Mar 28, 2024 • 15