$ whoami

Hi there, I'm Jipeng ZHANG

Researcher at Microsoft, building large language model systems across Data Techniques, Multimodal understanding, Reasoning, and Agent systems.

Data Techniques Multimodal Reasoning Agent
Current Research

Advancing Data Techniques, Multimodal understanding, Reasoning, and Agent systems.

My recent work focuses on data-centric pretraining and selection, multimodal foundation models, and reasoning methods for language, vision, code, and mathematical problem solving.

  • Data Techniques
  • Pretraining
  • Multimodal
  • Reasoning
  • Vision-Language
  • Agent
Education

Ph.D. in CSEHong Kong University of Science and Technology / 2021-Present

M.S. in Computer ScienceUniversity of Electronic Science and Technology of China / 2018-2021

B.S. in MathematicsUniversity of Electronic Science and Technology of China / 2014-2018

Recent Updates

news

const jipeng = new Terminal('updates')

ACTIVE
timecatpidmemory.dumplinks
Nowrole0x0000

Researcher at MicrosoftData Techniques, Multimodal understanding, Reasoning, and Agent systems.

2025paper0x0001

ExeSQL and DIDS accepted to EMNLP 2025Execution-driven Text-to-SQL bootstrapping and domain impact-aware data sampling.

2025paper0x0002

Bridge-Coder, TAGCOS, and ScaleBiO accepted in 2025Low-resource code generation, coreset selection, and scalable bilevel data reweighting.

2024model0x0003

Fox Foundation Model released as a small language modelCore contributor and data lead for a 1.6B model trained from scratch on 3T+ tokens.

2024demo0x0004

LMFlow won NAACL 2024 Best Demo PaperCore developer and data lead for an 8K+ star fine-tuning framework.

Experience

career

Microsoft

Researcher / Present

Data Techniques, Agent systems, and model reasoning.

TensorOpera

Research Intern / 2024

From-scratch pre-training for a 1.6B decoder-only language model for cloud and edge deployment.

ByteDance

Research Intern / 2022-2023

Multimodal foundation language models with Xinsong Zhang and Hang Li.

Microsoft

Research Intern / 2021

Code generation and pre-training language models for code with Nan Duan.

Living Analytics Research Centre

Research Assistant / 2019-2020

Multimodal knowledge graphs and math word problem solving.

Selected Publications

papers
TMLR 2023

Raft

Reward-ranked fine-tuning for generative foundation model alignment.

ICLR 2025

G-LLaVA

Solving geometric problems with multimodal large language models.

EMNLP 2024

Mitigating the Alignment Tax of RLHF

Reducing the capability cost introduced by RLHF alignment.

ACL 2020

Graph-to-Tree

Graph-to-tree learning for solving math word problems.

AAAI 2019

Template-Based MWP Solvers

Recursive neural networks for template-based math word problem solving.

EMNLP 2023

DetGPT

Detecting visual objects through multimodal reasoning.

View full publication list

Awards & Honors

honors
Outstanding Graduate Student of Sichuan Province, 2021 National Scholarship, UESTC, 2020 Goodix Technology Scholarship, 2020 HKUST Postgraduate Studentship, 2021-2025 NAACL Best Demo Paper Award, 2024 Outstanding Graduate, UESTC, 2018 Excellent Undergraduate Thesis Award, 2018 First-class People's Scholarship, 2017