Qingfeng Sun

Microsoft researcher and co-creator of the WizardLM / WizardCoder / WizardMath family using Evol-Instruct.

Role: researcher
GitHub: github.com/sunqingfengprc
Scholar: scholar.google.com/citations
Papers: 6

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile: scholar.google.com/citations

Attribution policy →

6papers·1tool contribs

Authored papers

6

RubricBench: Aligning Model-Generated Rubrics with Human Standards

arXiv 2026

Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models

arXiv 2026

AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation

arXiv 2024

WizardLM: Empowering Large Language Models to Follow Complex Instructions

ICLR

WizardCoder: Empowering Code Large Language Models with Evol-Instruct

arXiv 2023

MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation

arXiv 2022

Tool contributions

1

WizardLM Evol-Instruct

Microsoft

Microsoft's "Evol-Instruct" recipe - automatically rewriting simple instructions into harder, more diverse ones using an LLM evolver.

SFT DatasetCode GenerationMathInstruction Following

Affiliations

Previously

Microsoftfrontier lab

Frequent co-authors

10

from 6 papers

Can Xu

researcher

6 shared papers

Pu Zhao

researcher

4 shared papers

Chongyang Tao

professor

3 shared papers

Kai Zheng

researcher

3 shared papers

QIngwei Lin

3 shared papers

Chen Ma

2 shared papers

Daxin Jiang

founder

2 shared papers

Jiazhan Feng

researcher

2 shared papers

Qiyuan Zhang

2 shared papers

Xiubo Geng

researcher

2 shared papers