|
I am currently pursuing a PhD degree at the Hong Kong Polytechnic University. My supervisors are Qing Li and Wenqi Fan. My current Cumulative GPA is 3.60/4.00. I studied at Sichuan University (SCU) from 2020 to 2024, where I majored in Computer Science & Technology. My Major GPA (CS courses): 3.79/4, 89.39/100; Overall GPA: 3.78/4, 89.25/100 During my time at Sichuan University, I worked as a research assistant at MachineILab from 2022 to 2024, advised by Prof. JiZhe Zhou. I participated in one National Natural Science Foundation of China project and one National Key R&D Program of China. Email / CV / Google Scholar / Github |
|
|
My research interests lie in large language models (LLMs), retrieval-augmented generation (RAG), and Recommender Systems (RecSys). I focus on both theoretical foundations and practical applications of LLM-based systems. My previous research was primarily focused on topics within computer vision, such as tampering detection and object recognition tasks. I have contributed to the design of high-impact benchmarks, such as HiBench, and comprehensive surveys like WebAgents. My work has been published in top-tier conferences, including NeurIPS 2024 (spotlight) and AAAI 2025, and has accumulated 300+ citations, with an h-index of 5. |
|
|
|
🏆 2026-05-16 - Our paper Atomic Intent Reasoning: Bringing LLM Semantics to Industrial Cross-Domain Recommendations was accepted as a presentation at the KDD 2026 Main Conference ADS Track! 🎉 🏆2026-04 - Our paper SUPERGLASSES was accepted by CVPR 2026 Findings! 🎉 💼 2025-10 - Will join Kuaishou E-commerce Team as a research intern. 📝 2025-09 - Appointed as Topic Coordinator for Frontiers in Artificial Intelligence (Impact Factor: 4.7, CiteScore: 7.3, Logic and Reasoning Section) and Frontiers in Big Data (Impact Factor: 2.3, CiteScore: 6.1). 🏆 2025-08-20 - Our work QA-Dragon was accepted by KDD 2025 Workshop for Multimodal Retrieval Augmented Generation. 🎤 2025-08-07 - Invited to give a talk "Understanding Hierarchical Data with Large Language Models: RAG, Structural Reasoning, and Future Directions" at KDD 2025 Reasoning Day in Toronto, Canada! 🎙️ 🏅 2025-06-18 - Achieved 12th place globally in KDD Cup 2025 - Meta CRAG-MM Multimodal Retrieval Challenge among hundreds of international teams! 🌍 🏆 2025-05-16 - Our benchmark paper HiBench was accepted to KDD Benchmark Track! 🎉 🎉 2025-05-07 - Our survey paper A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models was accepted to KDD Tutorial Track! 🎊 📜 2025-03-30 - Completed the survey paper A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models. 📘 2025-03-01 - Completed the HiBench paper and released the code and dataset on GitHub and Hugging Face. 🌟 2025-01-15 - Mesoscopic Insights: Orchestrating Multi-Scale & Hybrid Architecture for Image Manipulation Localization was published in AAAI 2025. 🏆 2024-12-01 - IMDL-BenCo was published in NeurIPS 2024 Benchmark Tracks and received a Spotlight award. 🎓 2024-09-01 - Beginning my pursuit of a PhD degree in Hong Kong PolyU. 🎓 2024-06-26 - Got Outstanding Graduate Award from Sichuan University and Sichuan Province! 🎉 🎓 2024-06-26 - Graduated from Sichuan University with a bachelor's degree. 🛠️ 2024-06-12 - Completed the co-work project IMDLBenCo and finished a paper IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization 🔍 2024-05-24 - Finished a paper Beyond Visual Appearances: Privacy-sensitive Objects Identification via Hybrid Graph Reasoning 📚 2023-08-01 - Participated in NUS Summer School research program at National University of Singapore, completed face recognition project! 🇸🇬 |
|
|
|
Zhuohang Jiang, Yuxin Chen, Shijie Wang, Haohao Qu, Zhou Jindong, Wenqi Fan, Li Qing, Dongxu Liang, Jun Wang 
We introduce AIR, an LLM-driven cross-domain recommendation framework that moves semantic reasoning offline and composes user intent representations efficiently online. AIR achieves about 400x inference acceleration, reaches state-of-the-art results on public benchmarks, and improves Kuaishou E-commerce online GMV by +3.446% in large-scale A/B testing. |
|
Zhuohang Jiang, Xu Yuan, Haohao Qu, Shanru Lin, Kanglong Liu, Wenqi Fan, Qing Li 
SUPERGLASSES is a real-world smart-glasses VQA benchmark with 2,422 egocentric image-question pairs across 14 domains and 8 query types. We evaluate 26 VLMs and propose SUPERLENS, a multimodal RAG agent that surpasses GPT-4o by 2.19% on this setting. |
|
Zhuohang Jiang, Pangjing Wu, Xu Yuan, Wenqi Fan, Qing Li
QA-Dragon is a query-aware dynamic RAG system for knowledge-intensive VQA. By routing queries across domains and retrieval strategies, it supports multimodal, multi-turn, and multi-hop reasoning and improves Meta CRAG-MM Challenge performance by up to 6.35% over baselines. |
|
Liangbo Ning, Ziran Liang, Zhuohang Jiang, Haohao Qu, Yujuan Ding, Wenqi Fan, Xiao-yong Wei, Shanru Lin, Hui Liu, Philip S. Yu, Qing Li
This survey reviews WebAgents powered by large foundation models, focusing on architectures, training methods, and trustworthiness. It organizes recent progress in web automation and outlines key directions for building more reliable autonomous web agents. |
|
Zhuohang Jiang, Pangjing Wu, Ziran Liang, Peter Q. Chen, Xu Yuan, Ye Jia, Jiancheng Tu, Chen Li, Peter H.F. Ng, Qing Li
HiBench is a benchmark for evaluating hierarchical structure reasoning in LLMs, covering 30 tasks and 39,519 queries across six scenarios. Experiments on 20 LLMs reveal strengths in basic hierarchy reasoning and limitations on complex or implicit structures; a compact instruction dataset further improves model performance. |
|
Xuekang Zhu, Xiaochen Ma, Lei Su, Zhuohang Jiang, Bo Du, Xiwen Wang, Zeyu Lei, Wentao Feng, Chi-Man Pun, Jizhe Zhou 
This work introduces Mesorch, a mesoscopic architecture for image manipulation localization that combines macro-level semantic cues with micro-level tampering traces. Across four datasets, the proposed models improve accuracy, efficiency, and robustness over prior methods. |
|
Xiaochen Ma, Xuekang Zhu, Lei Su, Bo Du, Zhuohang Jiang, Bingkui Tong, Zeyu Lei, Xinyu Yang, Chi-Man Pun, Jiancheng Lv, Jizhe Zhou 
IMDL-BenCo is a comprehensive benchmark and modular codebase for image manipulation detection and localization. It standardizes training, evaluation, metrics, robustness tests, and eight strong baselines, enabling more reliable comparison across IMDL methods. |
|
|
|
First Author & Team Leader • KDD 2025 Benchmark Track • 2025
Designed and developed the first comprehensive benchmark for evaluating LLMs' capability on
hierarchical structure reasoning.
The benchmark encompasses six representative scenarios with 39,519 queries across varying
hierarchical complexity.
Key contributions: (1) Led the architectural design and implementation of the
evaluation framework,
(2) Coordinated a multi-institutional team across different time zones, (3) Open-sourced the
complete toolkit
including dataset, evaluation metrics, and baseline implementations. The benchmark has been
accepted
as an
oral presentation at KDD 2025 and is being adopted by multiple research groups
for
hierarchical reasoning evaluation.
|
|
Team Leader • KDD Cup 2025 • 2025
Led a team to achieve 12th place globally among hundreds of international teams
in
the Meta CRAG-MM
Multimodal Retrieval Challenge. Key contributions: (1) Designed novel multimodal
fusion architectures
combining vision and language understanding, (2) Implemented efficient retrieval-augmented
generation pipelines,
(3) Coordinated team efforts in model development, hyperparameter optimization, and submission
strategies.
The challenge focused on developing AI systems capable of understanding and retrieving information
from
multimodal content, which aligns with current trends in large multimodal models.
|
|
Co-First Author • NeurIPS 2024 Benchmark Track — Spotlight • 2024
Developed the first comprehensive benchmark and codebase for Image Manipulation Detection &
Localization (IMDL).
Key contributions: (1) Implemented GPU-accelerated evaluation metrics for fair
and
efficient comparison,
(2) Designed modular codebase architecture enabling easy customization and extension, (3)
Co-authored the manuscript
that received a Spotlight Award at NeurIPS 2024. The benchmark includes 8
state-of-the-art models,
15 evaluation metrics, and comprehensive robustness evaluation protocols, significantly advancing
the field's
standardization and reproducibility.
|
|
|
|
Invited Talks • Reasoning Day @ KDD 2025 • Toronto, ON, Canada • Aug 2025
Invited to deliver a presentation at the prestigious KDD 2025 Reasoning Day workshop.
The talk will explore cutting-edge developments in leveraging Large Language Models for hierarchical data understanding, with particular focus on Retrieval-Augmented Generation (RAG) systems and structural reasoning capabilities. Key topics: (1) Novel approaches to hierarchical data representation in LLM contexts, (2) Integration of structural reasoning with retrieval-augmented generation, (3) Future research directions in reasoning-enhanced AI systems, (4) Practical applications and deployment considerations for hierarchical reasoning in real-world scenarios. This invitation recognizes the impact of our HiBench work and positions our research at the forefront of LLM reasoning capabilities. |
|
|
|
Sichuan University, Chengdu, Sichuan, China
B.E. in Computer Science and Technology • Sep. 2020 to Jun. 2024 |
 |
|
Hong Kong Polytechnic University, Hongkong, China
PHD. in Computer Science and Technology • Sep. 2024 to Present |
 |
|
|
|
National University of Singapore (NUS)
Summer School Participant • Aug. 2023 • Participated in intensive research program at School of Computing • Completed face recognition project using CNN-based feature extraction and similarity matching • Gained international research experience and cross-cultural collaboration skills |
 |
|
DICALab, Sichuan University
Research Assistant • Sep. 2022 to Jun. 2024 Advisor: Prof. JiZhe Zhou • Developed graph-based frameworks for privacy-sensitive object detection • Participated in National Natural Science Foundation of China project • Contributed to National Key R&D Program of China • Co-authored multiple publications in top-tier conferences and journals |
 |
|
Kuaishou E-commerce Team, Kuaishou Inc.
Research Intern • Oct. 2025 to Present Beijing, China • Conducted end-to-end recommendation research based on large language models |
 |
|
|
|
|
KDD Cup 2025 — Meta CRAG-MM Toronto, Canada, 2025 |
12th Place (Global) |
|
NeurIPS 2024 — IMDL‑BenCo (Co‑first Author) Vancouver, Canada, 2024 |
Spotlight Award |
|
Outstanding Graduate Sichuan University & Sichuan Province, 2024 |
Top Achievement |
|
Tencent Scholarship Sichuan University, China, 2023 |
Top 2% |
|
A-Level Certificate Comprehensive Quality Evaluation, China, 2023 |
Excellence |
|
Comprehensive First Class Scholarship Sichuan University, Sichuan, China, 2022 |
Top 1% |
|
Outstanding Students of Sichuan University Sichuan University, Sichuan, China, 2022 |
Top 5% |
|
|
|
|
Conference & Journal Reviewer 2023-2025 |
TIP, ECCV, NeurIPS, KDD, AAAI, IoTJ, |
|
Conference & Journal Topic Coordinator 2025-2026 |
Frontiers in Artificial Intelligence, Frontiers in Big Data |
|
Teaching Assistant The Hong Kong Polytechnic University (PolyU) |
Artificial Intelligence (COMP4431) NLP Practicum (COMP5423) DataBase System (COMP2411) |
|
|
|
| Research Topics | Large Language Models (LLMs), Retrieval‑Augmented Generation (RAG), Recommender Systems (RecSys) |
| Frameworks & Tools | PyTorch, Hugging Face, NumPy, Docker, Git, Anaconda |
| Languages | Mandarin (native), English (fluent, IELTS 6.5) |
