Yukun Cao (曹宇坤)

Yukun Cao (曹宇坤)

Ph.D., USTC CS

👦 About me

Hi！I obtained my Ph.D. degree in Engineering in November 2025 from the School of Computer Science and Technology, the University of Science and Technology of China (USTC,中国科大计算机学院). During my Ph.D. studies, I worked in the Data Darkness Lab (DDL Lab), Center for Medical Imaging, Robotics, Analytic Computing & Learning (MIRACLE Center), Suzhou Institute for Advance Research, USTC, supervised by Prof. Xike Xie (since September 2020, postgraduate recommendation/推免入学). I received B.E. degree from the College of Computer and Information Science and College of Software, Southwest University (SWU, 西南大学) in 2020.

🔎 Research Interests

  • AI Field： Few-shot Learning, Meta-learning, Memory-augmented Network, Deep Generative Models
  • LLMs Field： Graph/KG RAG, LLMs for Graph Understanding/Reasoning, Memory Module in LLMs Agent
  • DB Field： Data/Graph Stream Processing, Data Exploration, Approximate Query Processing (AQP)
  • Focus Applications: AI for DB (e.g., Neural Data Structures, Automated Data Exploration, Learning-augmented Algorithms, Deep Generative Models-based AQP), Memory Architecture and Mechanisms in LLMs

📝 Publications

🟦 First/Corresponding Author Publications

  • [PVLDB 25-Research Paper (CCF-A)] Yukun Cao, Zengyi Gao, Zhiyang Li, Xike Xie, S Kevin Zhou, Jianliang Xu: “LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration”: 51st International Conference on Very Large Data Bases (PVLDB 2025). Paper
  • [ACL 25-Main (CCF-A)] Yukun Cao, Shuo Han, Zengyi Gao, Zezhong Ding, Xike Xie, S Kevin Zhou: “GraphInsight: Unlocking Insights in Large Language Models for Graph Structure Understanding”: The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025). Paper
  • [TPAMI 24-Regular Paper (CCF-A)] Yukun Cao, Yuan Feng, Hairu Wang, Xike Xie, S. Kevin Zhou: “Learning to Sketch: A Neural Approach to Item Frequency Estimation in Streaming Data”: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). Paper
  • [ICDE 23-Regular Paper (CCF-A)] Yukun Cao, Xike Xie, Kexing Huang: “Learn to Explore: on Bootstrapping Interactive Data Exploration with Meta-learning”: The 39th IEEE International Conference on Data Engineering (ICDE 2023). Paper
  • [AAAI 23-Oral Paper (CCF-A)] Yukun Cao, Yuan Feng, Xike Xie: “Meta-sketch: A Neural Data Structure for Estimating Item Frequencies of Data Streams”: Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023), Oral (Rate:11%). Paper
  • [ICML 25-Poster Paper (CCF-A)] Yuan Feng, Yukun Cao Co-First, Hairu Wang, Xike Xie, S Kevin Zhou: “Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams”: Forty-second International Conference on Machine Learning (ICML 2025). Paper
  • [ACL 25-Findings (CCF-A)] Zengyi Gao, Yukun Cao Co-First, Hairu Wang, Ao Ke, Yuan Feng, Xike Xie, S Kevin Zhou: “FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs”: The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025). Paper
  • [ICLR 24-Spotlight Paper (Top AI conf.)] Yuan Feng, Yukun Cao Co-First, Hairu Wang, Xike Xie, S. Kevin Zhou: “Mayfly: a Neural Data Structure for Graph Stream Summarization”: The Twelfth International Conference on Learning Representations (ICLR 2024), Spotlight (Rate:5%). Paper
  • [Arxiv] Shuo Han, Yukun Cao Co-First, Zezhong Ding, Zengyi Gao, S Kevin Zhou, Xike Xie: “See or Say Graphs: Agent-Driven Scalable Graph Understanding with Vision-Language Models”. Paper

⬜ Other Publications

  • [NeurIPS 25-Poster Paper (CCF-A)] Yuan Feng, Junlin Lv, Yukun Cao, Xike Xie, S Kevin Zhou : “Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference”: The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025). Paper
  • [IJCAI 25-Long Paper (CCF-A)] Ao Ke, Wenlong Chen, Chuanwen Feng, Yukun Cao, Xike Xie, S.Kevin Zhou, Lei Feng: “Prototype-based Optimal Transport for Out-of-Distribution Detection”: The 34th International Joint Conference on Artificial Intelligence (IJCAI 2025). Paper
  • [EMNLP 25-Findings Paper (CCF-B)] Hairu Wang, Yuan Feng, Yukun Cao, Xike Xie, S Kevin Zhou: “SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context”: The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025). Paper
  • [GROUP 23-Demo Paper (CCF-B)] Haoyun Li, Yukun Cao, Xike Xie: “VR-Explorer: A Demonstration of a Virtual Reality Interactive Data Exploration System”: The 2023 ACM International Conference on Supporting Group Work (GROUP 2023), Companion. Paper, Project Site
  • [KSEM 19-Long Paper (CCF-C)] Jingyuan Wang, Yukun Cao, Ye Du, Li Li: “DST: A Deep Urban Traffic Flow Prediction Framework Based on Spatial-Temporal Features”: Knowledge Science, Engineering and Management-12th International Conference (KSEM 2019).
  • [ICWE 19-Long Paper (CCF-C)] Xiaofei Xu, Yukun Cao, Li Li: “Exploring Semantic Change of Chinese Word Using Crawled Web Data”: Web Engineering-19th International Conference (ICWE 2019).
  • [KSEM 19-Long Paper (CCF-C)] Kexin Huang, Yukun Cao, Ye Du, Li Li: “Social-Aware and Sequential Embedding for Cold-Start Recommendation”: Knowledge Science, Engineering and Management-12th International Conference (KSEM 2019).
  • [Arxiv] Yuan Feng, Junlin Lv, Yukun Cao, Xike Xie, S. Kevin Zhou: “Identify Critical KV Cache in LLM Inference from an Output Perturbation Perspective”. Paper


🎖 Honors and Awards

  • 2024 Suzhou Industrial Park Scholarship (苏州工业园区奖学金) at USTC.
  • 2023 Suzhou Industrial Park Scholarship (苏州工业园区奖学金) at USTC.
  • 2022 Yuan-Qing Scholarship (元庆奖学金，选拔中国科大计算机学院2022级的4名博士生) at USTC (Selecting 4 PhD students in the 2022 class of School of Computer Science).
  • 2020 Outstanding Graduates Award of Chongqing City (重庆市优秀毕业生).
  • 2020 Scholarship of Gratitude to Chinese Modern and Contemporary Scientists (感恩中国近现代科学家奖学金，面向中国西部的985/211高校评选，每所高校只评选10名) (Targeting 985/211 project Universities in Western China, each university has only 10 students).
  • 2020 Pin-Sheng Scholarship (品胜奖学金) at SWU (Rate: $\approx$ 1/480).
  • 2019 Yu-Hui Scholarship (玉辉奖学金) at SWU (Rate: $\approx$ 1/480).
  • 2017/2018/2019 three times National Scholarship (三次获得 国家奖学金) at SWU (Rate: $\approx$ 1/120).
  • 2019 Excellence in Learning Award (学习优胜奖) at SWU.
  • 2018 Advanced Individual in Technological Innovation (科创先进个人称号) at SWU.
  • 2017/2018 twice Outstanding Student Award（两次获得 三好学生称号） at SWU.

📖 Educations

  • 2022.09 - 2025.11 , PhD candidate in Computer Science.

    School of Computer Science and Technology, University of Science and Technology of China (CS, USTC), Hefei, Anhui.

  • 2020.09 - 2022.06, Master in Computer Science.

    School of Computer Science and Technology, University of Science and Technology of China (CS, USTC), Hefei, Anhui.

  • 2016.09 - 2020.06, Bachelor in Computer Science.

    College of Computer and Information Science and College of Software, Southwest University (CS, SWU), Beibei, Chongqing. Rank：1/126