Chao Huang
Assistant Professor
Department of Computer Science & Institute of Data Science
📧 chaohuang75@gmail.com 🎓 Google Scholar 🚀 Lab Github
Chao Huang
Assistant Professor
Department of Computer Science & Institute of Data Science
📧 chaohuang75@gmail.com 🎓 Google Scholar 🚀 Lab Github
I am an Assistant Professor & Ph.D Advisor at the Department of Computer Science and Institute of Data Science, at HKU. I am the director of Data Intelligence Lab@HKU, with the focus on Large Language Models, Autonamous Agents, Graph Learning, Recommender Systems and AI for Smart Cities.
👨💻✨ Our Research Works are Open-Sourced – Explore Them on Our Lab GitHub Repository 🚀
🔥 Recent LLM Research Work
🚀 Retrieval-Augmented Generation (RAG): LightRAG, RAG-Anything, MiniRAG, VideoRAG
🚀 LLM Agents: AutoAgent, Auto-Deep-Research, AI-Researcher, DeepCode, GraphAgent, Aria-UI
🚀 Graph Foundation Model (GFM): GraphGPT, HiGPT, OpenGraph, AnyGraph
🚀 LLMs for Recommender Systems: RLMRec, LLMRec, XRec, EasyRec, RecLM
~1.5k GitHub 🌟
🏆 2025 AI 100 Young Pioneers (AI100青年先锋)
🏆 2025 AI 2000 Most Influential Scholars
🏆 2025 World AI Conference (WAIC) Youth Outstanding Paper Honorable Mention Award (青年优秀论文提名奖)
🏆 2024 World AI Conference (WAIC) "Bright Stars" (云帆奖·璀璨明星)
🏆 2024 Frontiers of Science Award from ICBS 2024 (国际基础科学大会·前沿科学奖)
🏆 World's Top 2% Scientists Published by Stanford University (2022, 2023, 2024)
🏆 1 ✖️ WWW 2024 Most Influential Papers (Rank 1st / 405 Accepted Papers)
🏆 1 ✖️ SIGIR 2024 Most Influential Papers (Rank 4th / 159 Accepted Papers)
🏆 1 ✖️ KDD 2024 Most Influential Papers (Rank 8th / 559 Accepted Papers)
🏆 3 ✖️ WWW 2023 Most Influential Papers (Rank 4th, 5th, 8th / 323 Accepted Papers)
🏆 1 ✖️ SIGIR 2023 Most Influential Papers (Rank 12th / 165 Accepted Papers)
🏆 2 ✖️ KDD 2023 Most Influential Papers (Rank 8th, 10th / 497 Accepted Papers)
🏆 1 ✖️ AAAI 2023 Most Influential Papers (Rank 11th / 1721 Accepted Papers)
🏆 2 ✖️ KDD 2022 Most Influential Papers (Rank 12th, 14th / 450 Accepted Papers)
🏆 2 ✖️ SIGIR 2022 Most Influential Papers (Rank 2nd, 3rd / 161 Accepted Papers)
🏆 1 ✖️ SIGIR 2021 Most Influential Papers (Rank 13th / 151 Accepted Papers)
🏆 1 ✖️ KDD 2019 Most Influential Papers (Rank 3rd / 174 Accepted Papers)
🏆 WSDM 2024 Top-1 Most Cited Paper (Rank 1st / 112 Accepted Papers)
🏆 WSDM 2023 Top-1 Most Cited Paper (Rank 1st / 123 Accepted Papers)
🏆 WSDM 2022 Top-3 Most Cited Paper (Rank 3rd / 159 Accepted Papers)
🏆 ACM MM 2024 Best Paper Hornarable Mention Award
🏆 WWW 2023 Best Paper Nomination
🏆 WSDM 2022 Best Paper Nomination
🏆 WWW 2019 Best Paper Nomination
Google Scholar Citation 13,000+, h-index 58
[WWW'2024] "RLMRec: Representation Learning with Large Language Models for Recommendation"
X. Ren+, W. Wei, L. Xia, L. Su, S. Cheng, J. Wang, D. Yin and C. Huang*
🌟 (Top-1 Most Influential Paper: 1 / 405 Accepted Papers) 🌟
🌟 (Top-1 Most Cited Paper: 1 / 405 Accepted Papers) 🌟
[paper] (~270 Citations 📄) [code]
[SIGIR'2024] "GraphGPT: Graph Instruction Tuning for Large Language Models"
J. Tang+, Y. Yang, W. Wei, L. Shi, L. Su, S. Cheng, D. Yin and C. Huang*
🌟 (Top-4 Most Influential Paper: 4 / 159 Accepted Papers) 🌟
🌟 (Top-2 Most Cited Paper: 2 / 159 Accepted Papers) 🌟
[paper] (~310 Citations 📄) [code]
[KDD'2024] "UrbanGPT: Spatio-Temporal Large Language Models"
Z. Li+, L. Xia, J. Tang, Y. Xu, L. Shi, L. Xia, D. Yin and C. Huang*
🌟 (Top-8 Most Influential Paper: 8 / 559 Accepted Papers) 🌟
🌟 (Top-2 Most Cited Paper: 2 / 559 Accepted Papers) 🌟
[paper] (~160 Citations 📄) [code]
[KDD'2024] "HiGPT: Heterogenous Graph Language Models"
J. Tang+, Y. Yang, W. Wei, L. Shi, L. Xia, D. Yin and C. Huang*
🌟 (Top-15 Most Cited Paper at Research Track: 15 / 559 Accepted Papers) 🌟
[paper] (~60 Citations 📄) [code]
[MM'2024] "DiffMM: Multi-Modal Diffusion Model for Recommendation"
Y. Jiang+, L. Xia, W. Wei, D. Luo, K. Lin and C. Huang*
🌟 (Best Paper Honorable Mention Award: 10 / 1149 Accepted Papers) 🌟
[paper] (~40 Citations 📄) [code]
[WSDM'2024] "LLMRec: Large Language Models with Graph Augmentation for Recommendation"
W. Wei+, X. Ren, J. Tang, Q. Wang, L. Su, S. Cheng, J. Wang, D. Yin and C. Huang*
🌟 (Top-1 Most Cited Paper: 1 / 112 Accepted Papers) 🌟
[paper] (~330 Citations 📄) [code]
[WWW'2023] "Automated Self-Supervised Learning for Recommendation"
L. Xia+, C. Huang*, C. Huang, K. Lin, T. Yu and B. Kao
🌟 (Top-8 Most Influential Paper: 8 / 365 Accepted Papers) 🌟
🌟 (Top-9 Most Cited Paper: 9 / 365 Accepted Papers) 🌟
🌟 (Spotlight Paper: 16/365 Accepted Papers) 🌟
[paper] (~130 Citations 📄) [code]
[WWW'2023] "Multi-Modal Self-Supervised Learning for Recommendation"
W. Wei+, C. Huang*, L. Xia and C. Zhang
🌟 (Top-5 Most Influential Paper: 5 / 365 Accepted Papers) 🌟
🌟 (Top-4 Most Cited Paper: 4 / 365 Accepted Papers) 🌟
[paper] (~210 Citations 📄) [code]
[WWW'2023] "Debiased Contrastive Learning for Sequential Recommendation"
Y. Yang+, C. Huang*, L. Xia, C. Huang, D. Luo and K. Li
🌟 (Top-4 Most Influential Paper: 4 / 365 Accepted Papers) 🌟
🌟 (Top-6 Most Cited Paper: 6 / 365 Accepted Papers) 🌟
[paper] (~180 Citations 📄) [code]
[KDD'2023] "Adaptive Graph Contrastive Learning for Recommendation"
Y. Jiang+, C. Huang* and L. Xia
🌟 (Top-8 Most Influential Paper: 8/ 497 Accepted Papers) 🌟
🌟 (Top-7 Most Cited Paper: 7 / 497 Accepted Papers) 🌟
[paper] (~160 Citations 📄) [code]
[KDD'2023] "Knowledge Graph Self-Supervised Rationalization for Recommendation"
Y. Yang+, C. Huang*, L. Xia and C. Huang
🌟 (Top-10 Most Influential Paper: 10/ 497 Accepted Papers) 🌟
🌟 (Top-9 Most Cited Paper: 9 / 497 Accepted Papers) 🌟
[paper] (~150 Citations 📄) [code]
[SIGIR'2023] "Disentangled Contrastive Collaborative Filtering"
X. Ren+, L. Xia, J. Zhao, D. Yin and C. Huang*
🌟 (Top-10 Most Influential Paper: 10 / 165 Accepted Papers) 🌟
🌟 (Top-6 Most Cited Paper: 6 / 165 Accepted Papers) 🌟
[paper] (~140 Citations 📄) [code]
[ICLR'2023] "LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation"
X. Cai+, C. Huang*, L. Xia and X. Ren
🌟 (Top-5% Most Cited Paper among 1,574 Accepted Papers) 🌟
[paper] (~420 Citations 📄) [code]
[AAAI'2023] "Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction"
J. Ji+, J. Wang, C. Huang, J. Wu, B. Xu, Z. Wu, J. Zhang and Y. Zheng
🌟 (Top-11 Most Influential Paper: 11 / 1721 Accepted Papers) 🌟
🌟 (Top-11 Most Cited Paper: 11 / 1721 Accepted Papers) 🌟
[paper] (~260 Citations 📄) [code]
[WSDM'2023] "Heterogeneous Graph Contrastive Learning for Recommendation"
M. Chen+, C. Huang*, L. Xia, W. Wei, Y. Xu and R. Luo
🌟 (Top-1 Most Cited Paper: 1 / 123 Accepted Papers) 🌟
[paper] (~240 Citations 📄) [code]
[SIGIR'2022] "Hypergraph Contrastive Collaborative Filtering"
L. Xia+, C. Huang*, Y. Xu, J. Zhao, D. Yin and J. Huang
🌟 (Top-3 Most Influential Paper: 3/ 161 Accepted Papers) 🌟
🌟 (Top-2 Most Cited Paper: 2 / 161 Accepted Papers) 🌟
[paper] (~480 Citations 📄) [code]
[SIGIR'2022] "Knowledge Graph Contrastive Learning for Recommendation"
Y. Yang+, C. Huang*, L. Xia and C. Li
🌟 (Top-2 Most Influential Paper: 2 / 161 Accepted Papers) 🌟
🌟 (Top-3 Most Cited Paper: 3 / 161 Accepted Papers) 🌟
[paper] (~470 Citations 📄) [code]
[KDD'22] "Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendation"
Y. Yang+, C. Huang*, L. Xia, Y. Liang, Y. Yu and C. Li
🌟 (Top-12 Most Influential Paper: 12 / 450 Accepted Papers) 🌟
🌟 (Top-13 Most Cited Paper: 13 / 450 Accepted Papers) 🌟
[paper] (~170 Citations 📄) [code]
[KDD'22] "Self-Supervised Hypergraph Transformer for Recommender Systems"
L. Xia+, C. Huang*, and C. Zhang
🌟 (Top-15 Most Influential Paper: 15 / 450 Accepted Papers) 🌟
🌟 (Top-15 Most Cited Paper: 15 / 450 Accepted Papers) 🌟
[paper] (~160 Citations 📄) [code]
[WSDM'2022] "Contrastive Meta Learning with Behavior Multiplicity for Recommendation"
W. Wei+, C. Huang*, L. Xia, Y. Xu, J. Zhao and D. Yin
🌟 (Best Paper Award Nomination) 🌟
🌟 (Top-3 Most Cited Paper: 3 / 159 Accepted Papers) 🌟
[paper] (~220 Citations 📄) [code]
[SIGIR'2021] "Graph Meta Network for Multi-Behavior Recommendation"
L. Xia+, Y. Xu, C. Huang*, P. Dai and L. Bo
🌟 (Top-13 Most Influential Paper: 13/ 151 Accepted Papers) 🌟
[paper] (~250 Citations 📄) [code]
[KDD'2019] "Heterogeneous Graph Neural Network"
C. Zhang, D. Song, C. Huang, A. Swami, N. Chawla
🌟 (Top-3 Most Influential Paper: 3/ 174 Accepted Papers) 🌟
[03/2025] - 📣 Please check out our released Fully-Automated Scientific Discovery with LLM Agents: 🌟AI-Researcher🌟
🔥 Complete End-to-End Research Automation & Streamlined Scientific Innovation
🔥 📚→💡→🔬→⚙️ From Literature Review to Idea Generation, Algorithm Design
🔥 🧪→ 🔍→📊→✍️→📝 From Algorithm Implementation, Validation, Refinement to Result Analysis, and Manuscript Creation
[02/2025] - 📣 Please check out our released Fully-Automated & Zero-Code LLM Agent Framework: 🌟AutoAgent🌟
🔥 Top Open-Sourced Performer on the GAIA Benchmark with our Auto-Deep-Research
🔥 Natural Language to Effortlessly Build Ready-to-Use Agents and Workflows - No Coding Required
🔥 Equipped with a Native Self-Managing Vector Database & Integrates with A Wide Range of LLMs
[02/2025] - 📣 Please check out our released Extremely Long-Context Video Understanding System: 🌟VideoRAG🌟
🔥 Efficient Extreme Long-Context Video Processing by Leveraging a Single NVIDIA RTX 3090 GPU (24G)
🔥 Structured Video Knowledge Indexing & Multi-Modal Retrieval for Comprehensive Responses
🔥 The New Established LongerVideos Benchmark Features over 160 Videos Totaling 134+ Hours
[01/2025] - 📣 Please check out our released Small Language Models-Powered RAG System: 🌟MiniRAG🌟
🔥 Retrieval-Augmented Generation for Resource-Constrained Environments
🔥 Lightweight Topology-Enhanced Retrieval and Optimized for Small Language Models (SLMs)
🔥 75% Reduction in Storage Requirements and Perfect for Edge Devices
[10/2024] - 📣 Please check out our released Retrieval-Augmented Generation System: 🌟LightRAG🌟
🔥 Simple and Fast Retrieval-Augmented Generation (RAG) System
🔥 Comprehensive Information Retrieval with Complex Inter-dependencies
🔥 Efficient Information Retrieval with Dual-Level Retrieval Paradigm
🔥 Rapid Adaptability to Dynamic Data Changes
[08/2024] - 📣 Please check out our released new Graph Foundation Model: 🌟AnyGraph🌟
[08/2024] - 📣 Please check out our released new Spatio-Temporal Foundation Model: 🌟OpenCity🌟
[08/2024] - 📣 Please check out our released new Recommender Language Models 🌟EasyRec🌟
🔥 Easy-to-Use Language Models with Zero-Shot Recommendation Capacity
🔥 Fast Adaptation to Evolving User Preferences
🔥 Seamless Integration with Existing Recommender Systems
[05/2024] - 📣 Please check out our released LLM for Explainable Recommendation 🌟[EMNLP'2024] XRec🌟
🔥 XRec: An intelligent LLM that gives your recommender a voice to divine your preferences in Natural Language
🔥 Integrates Collaborative Filtering with LLMs to generate Comprehensive Explanations for Recommendations
[03/2024] - 📣 Please check out our released Graph Foundation Model: 🌟[EMNLP'2024] OpenGraph🌟
🔥 OpenGraph Uncovers the Potential of the Graph Foundation Model
🔥 Zero-shot Graph Generalization Distilled from LLMs
[03/2024] - 📣 Please check out our released Heterogenous Graph Language Models: 🌟[KDD'2024] HiGPT🌟
🔥 HiGPT One Model for Any Heterogeneous Graph
🔥 Cross-domain Zero-shot Heterogeneous Graph Learning
🔥 1-shot Beat 60-shot with Graph In-Context Learning
[02/2024] - 📣 Please check out our released Spatio-Temporal Large Language Models: 🌟[KDD'2024] UrbanGPT🌟
🔥 UrbanGPT empowers LLMs to comprehend the intricate inter-dependencies across time and space
🔥 We facilitate more comprehensive and accurate Spatio-Temporal Predictions under Data Scarcity
[02/2024] - 📣 Please check out our released Large Language Models for Graph Structure Learning: 🌟GraphEdit🌟
🔥 GraphEdit is a large language model to Effectively Denoises Noisy Connections
🔥 The proposed new framework identifies node-wise dependencies from a global perspective
[11/2023] - 📣 Please check out our released Graph Large Language Model: 🌟[SIGIR'2024] GraphGPT🌟
🔥 GraphGPT framework aligns LLMs with Graph Structural Knowledge for graph learning
🔥 We integrate Text-Graph Grounding with Instruction Tuning to build Effective and Efficient LLM for Graphs
[11/2023] - 📣 Please check out our released LLM-enhanced Recommender System: 🌟[WSDM'2024] LLMRec🌟
🔥 LLMRec: Simple yet Effective LLM-based Graph Augmentation strategies for recommendation
🔥 We enhance the understanding of user preference with the Incorporation of LLM-based Knowledge
[11/2023] - 📣 Please check out our released Representation Learning Framework with LLMs: 🌟[WWW'2024] RLMRec🌟
🔥 RLMRec: Enhancing existing recommenders with Model-agnostic LLM-empowered Representation Learning
🔥 We integrate Representation Learning with LLMs to capture Intricate Semantic Aspects of User Behaviors