Hao Zhang

Hao Zhang

Staff Algorithm Engineer

DAMO Academy, Alibaba Group

Biography

Hi! My name is Hao Zhang (张豪). I am currently a senior research scientist at Alibaba DAMO Academy (Singapore R&D Center), working on multimodal large language models. My research interests primary focuses on developing novel techniques, including RAG, agents, complex reasoning and data synthesis, to enhance the capabilities of multimodal LLMs and apply them to address real-world challenges.

Prior joining Alibaba DAMO Academy, I served as a principal engineer at Huawei Noah’s Ark Lab for around two years. I earned my PhD in Computer Science from the College of Computing and Data Science at Nanyang Technological University (NTU), Singapore in July 2022, under the supervision of Professor Aixin SUN. Before that, I obtained my M.Sc degree from the School of Electrical and Electronic Engineering at NTU in June 2016.

Research Community Services:
Area Chair: ACL Rolling Review
Reviewer: ACL Rolling Review, ACL, EMNLP, COLING, ICLR, AAAI, IJCAI, WWW, KDD, SIGIR, MM
Co-organizer: Interactive Recommendation System Workshop, WSDM 2023

Interests
  • (Multimodal) Large Language Models
  • (M)LLM Reasoning
  • (M)LLM Analysis
  • RAG and Agent
Education
  • PhD in Computer Science, 2019-2022

    Nanyang Technological University, Singapore

  • MSc in Communications Engineering, 2015-2016

    Nanyang Technological University, Singapore

  • BEng in Communications Engineering, 2011-2015

    Dalian University of Technology, China

Experience

 
 
 
 
 
Staff Algorithm Engineer
September 2024 – Present Singapore
Working on LLMs, Multimodal LLMs, Complex Reasoning, Agent, etc.
 
 
 
 
 
Principal Engineer
July 2022 – August 2024 Singapore
Working on PanGu LLM, Retrieval-Augmented Generation, Agent, LLM4Rec, etc.
 
 
 
 
 
Senior Research Engineer
June 2018 – May 2022 Singapore

Senior Research Engineer/Principal Investigator, Centre for Frontier AI Research, Jan 2022 - May 2022

Research Engineer, Institute of High Performance Computing, Jun 2018 - Dec 2021

 
 
 
 
 
Research Associate
July 2016 – May 2018 Singapore

Publications

Quickly discover relevant content by filtering publications.
(2025). FineReason: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving. In ACL.

PDF Cite 📌ACL'25

(2025). Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations. In ACL.

Preprint Cite Code 📌ACL'25

(2025). CoIR: A Comprehensive Benchmark for Code Information Retrieval Models. In ACL.

Preprint Cite Code Dataset Project 📌ACL'25

(2025). Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger. In ACL.

PDF Cite 📌ACL'25

(2025). CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control. In ACL.

Preprint Cite Code 📌ACL'25