About Me

First Post:

2025-01-18

Last Update:

2026-06-10

Word Count:

2.5k

Read Time:

15 min

Page View: loading...

Haoxiang Zhang 张灏翔

Intelligence is born of bounded stochasticity.

isaacpfino@gmail.com or haz140@ucsd.edu or Isaac_GHX@shu.edu.cn

ipfipfipf isaac_ghx 𝕏

Hello! 好呀 ~ こんにちは！안녕 ~

Hello! I am a passionate data researcher focusing on data centric AI. I am currently pursuing my Master of Science in Data Science at UC San Diego. I now work closely with Prof. Julian McAuley's lab @ UCSD and Prof. Yu Zhang's lab @ Texas A&M University. Previously, I was a visiting student @ Stanford University, working with Dr. Pan Lu, where I was fortunate to be advised by Prof. Yejin Choi and Prof. James Zou.

My research experienced computer vision, continual learning, out-of-distribution generalization, and agentic LLMs. Right now I'm exploring intelligent decision-making. Looking forward to discussing new inspirations!

Education

University of California San Diego

Master of Science in Data Science (Expected)

09/2025 - 06/2027

Shanghai University

Bachelor of Engineering in Data Science & Big Data Technology

09/2021 - 06/2025

Hong Kong University of Science and Technology

Summer Session - Data & Computer Science

08/2024

University of Pennsylvania, Wharton School

Wharton Innovation, Entrepreneurship and Leadership Program & The Global Leadership Program for Young Scholars.

07/2023 - 08/2023

Selected Publications

arXiv 2026

Masking Stale Observations Helps Search Agents – Until It Doesn't: A Regime Map and Its Mechanism

Haoxiang Zhang^{*Equal contribution}, Qixin Xu^{*Equal contribution}, Yu Zhang^{✝Co-senior author}, Julian McAuley^{✝Co-senior author}, and 3 more authors

Paper | Code | Abstract | BibTeX

GitHub ⭐

arXiv 2026

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Zhuofeng Li, Haoxiang Zhang, Dongfu Jiang^{✝Corresponding author}, Yu Zhang^{✝Corresponding author}, and 15 more authors

Paper | Code | Demo | Abstract | BibTeX

Hugging Face Daily Paper #1 • GitHub ⭐

bioRxiv 2026

Eubiota: Modular Agentic AI for Autonomous Discovery in the Gut Microbiome

Pan Lu^{*Equal contribution}, Yifan Gao^{*Equal contribution}, Haoxiang Zhang, and 12 more authors

GitHub ⭐

ICLR 2026 Oral & NIPS 2025 ER Workshop

In-the-Flow Agentic System Optimization for Effective Planning and Tool Use

Zhuofeng Li^{*Equal contribution}, Haoxiang Zhang^{*Equal contribution}, James Zou^{✝Corresponding author}, Pan Lu^{✝Corresponding author}, and 5 more authors

Hugging Face Daily Paper #2 • GitHub ⭐

arXiv 2026

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

Zhuofeng Li^{*Equal contribution}, Dongfu Jiang^{*Equal contribution}, Xueguang Ma, Haoxiang Zhang, and 6 more authors

Hugging Face Daily Paper #2 • Adopted by NVIDIA's Nemotron family of models
GitHub ⭐

TMLR

Avoiding Structural Pitfalls: Self-Supervised Low-Rank Feature Tuning for Graph Test-Time Adaptation

Haoxiang Zhang, Zhuofeng Li, Shichao Pei^{✝Corresponding author}, and 3 more authors

Paper | Code | Abstract | BibTeX

Long-term Collaboration

Lambda, Inc.

Student credit grant, Lambda Platform GPU inference service, and agentic AI research.

CocoaBench Team

Collaborative research with the CocoaBench team on multimodal evaluation and benchmarking.

Homepage | Paper | GitHub | Blog

Shanghai Tongliang Intelligent Technology Co., Ltd.

Research Consultant (Permanent) & Chief Scientist (04/2025 – 06/2025). Developed and validated Multi-Agent Adversarial (MAA) strategies for medium-frequency quantitative trading across futures, options, crypto, and equities.

Industrial Internship

Shanghai Artificial Intelligence Labotary

Multimodal Unified Auto-regressive Generation.

View Detail [Lumina-mGPT]

08/2024 - 02/2025

Bank of Communications, Shanghai Branch

Intern, Internet Finance Team & Data Application Team. Decentralized Finance.

07/2024

FASOTEC Co., Ltd.

Technical Assistant. Server Hardware & CATIA Software.

08/2023 - 10/2023

≡