Zhangchen Xu's picture

Zhangchen Xu PRO

zhangchenxu

·

https://zhangchenxu.com/

AI & ML interests

LLM Data, Alignment, Post-Training, Safety

Recent Activity

liked a model 1 day ago

Qwen/QwQ-32B

upvoted an article 1 day ago

Open R1: Update #3

liked a model 1 day ago

google/gemma-3-27b-it

View all activity

Organizations

zhangchenxu's activity

upvoted an article 1 day ago

Article

Open R1: Update #3

By

and 9 others •

2 days ago

• 199

upvoted a paper 8 days ago

KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding

Paper • 2503.02951 • Published 9 days ago • 26

upvoted a collection 13 days ago

KodCode-V1

KodCode-V1 is the largest fully-synthetic open-source dataset providing verifiable solutions and tests for coding tasks. • 4 items • Updated 7 days ago • 2

upvoted 2 collections 20 days ago

Small Model Learnability Gap: Models

24 items • Updated 18 days ago • 1

Small Model Learnability Gap: Dataset

6 items • Updated 20 days ago • 2

upvoted a paper 22 days ago

Small Models Struggle to Learn from Strong Reasoners

Paper • 2502.12143 • Published 25 days ago • 28

upvoted a collection 2 months ago

Magpie Reasoning Datasets

Reasoning datasets built by Magpie and its friends! • 8 items • Updated Jan 27 • 10

upvoted an article 2 months ago

Article

Fine-tune a SmolLM on domain-specific synthetic data from a LLM

By

•

Jan 3

• 36

upvoted a collection 2 months ago

Magpie-Llama3.3 Datasets

Dataset built with Meta Llama 3.3 70B. • 3 items • Updated Jan 13 • 1

upvoted a paper 3 months ago

GRAPE: Generalizing Robot Policy via Preference Alignment

Paper • 2411.19309 • Published Nov 28, 2024 • 44

upvoted a paper 4 months ago

Stronger Models are NOT Stronger Teachers for Instruction Tuning

Paper • 2411.07133 • Published Nov 11, 2024 • 36

upvoted an article 5 months ago

Article

🇮🇹🇯🇵🇧🇷 Generating multilingual instruction datasets with Magpie 🐦‍⬛

By

•

Oct 21, 2024

• 19

upvoted a paper 6 months ago

Training Language Models to Self-Correct via Reinforcement Learning

Paper • 2409.12917 • Published Sep 19, 2024 • 138

upvoted a collection 6 months ago

MagpieLM

Aligning LMs with Fully Open Recipe + Synthetic Data Generated from Open-Source LMs. • 9 items • Updated Jan 13 • 16

upvoted a collection 7 months ago

Magpie Open Recipes

Open-aligned models using Magpie datasets. • 11 items • Updated Jan 13 • 1

upvoted 2 collections 8 months ago

Magpie-Llama3.1 Datasets

Dataset built with Meta Llama 3.1 70B. • 6 items • Updated Jan 13 • 3

Zebra Logic Bench

ZebraLogic Bench: Testing the Limits of LLMs in Logical Reasoning • 4 items • Updated about 15 hours ago • 5

upvoted a paper 8 months ago

ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates

Paper • 2406.12935 • Published Jun 17, 2024 • 2

upvoted 2 collections 9 months ago

synthetic-data-generation-demos

A collection of demos for various approaches to synthetic data generation • 4 items • Updated Jun 25, 2024 • 14

Magpie-Qwen2 Datasets

Dataset built with Qwen2 72B and Qwen2 7B. • 6 items • Updated Jan 13 • 10