Lu Dai

Ph.D. Student, HKUST · Agentic Search · RAG · Long Context LLMs

prof_pic.jpg

Hong Kong University of Science and Technology

Division of Emerging Interdisciplinary Areas

Hong Kong

I am a Ph.D. student at the Hong Kong University of Science and Technology (HKUST), advised by Prof. Hui Xiong and co-advised by Prof. Hao Liu. My research lies at the intersection of agentic search, retrieval-augmented generation (RAG), and large language models (LLMs), with a focus on building more effective agentic search and retrieval-augmented systems, advancing long-context LLMs, and understanding how knowledge is stored and generalized in LLMs.

I have published at top-tier venues including ICLR (Spotlight), ICCV, EMNLP, KDD, CVPR, and NeurIPS. Prior to my Ph.D., I interned at Google Cloud AI and Baidu Research, and received my B.E. in Computer Science from the University of Science and Technology of China (USTC) where I graduated as an outstanding graduate (top 5%).

Beyond research, I have been playing electronic piano and violin for over 10 years 🎹🎻.

News

Feb 20, 2026 📄 Our paper VL-Eraser on machine unlearning in VLMs has been accepted at CVPR 2026!
Jan 15, 2026 📄 Our paper on global temporal retrieval for time series forecasting has been accepted at ICLR 2026!
Sep 20, 2025 📄 Our paper on Foundation Models for Scientific Discovery has been accepted at NeurIPS 2025!
Sep 15, 2025 📄 Our paper MolErr2Fix has been accepted at EMNLP 2025!
May 01, 2025 📄 Our paper ScIRGen has been accepted at KDD 2025!

Selected Publications

  1. ICCV
    Cloth2Body: Generating 3D Human Body Mesh from 2D Clothing
    Lu Dai, Liqian Ma, Shenhan Qian, and 3 more authors
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023
  2. EMNLP
    Improve Dense Passage Retrieval with Entailment Tuning
    Lu Dai, Hao Liu, and Hui Xiong
    In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
  3. ICLR
    SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction
    Lu Dai, Yijie Xu, Jinhui Ye, and 2 more authors
    In International Conference on Learning Representations (ICLR), 2025
    Spotlight
  4. KDD
    ScIRGen: Synthesize Realistic and Large-Scale RAG Dataset for Scientific Research
    Junyong Lin*, Lu Dai* (Project Leader), Ruiqian Han, and 1 more author
    In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025
  5. ICLR
    Enhancing Multivariate Time Series Forecasting with Global Temporal Retrieval
    Fanpu Cao, Lu Dai, Jindong Han, and 1 more author
    In International Conference on Learning Representations (ICLR), 2026
  6. CVPR
    VL-Eraser: Vacuum Distillation for Machine Unlearning in Vision-Language Models
    Yili Wang, Lu Dai, Tairan Huang, and 2 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
  7. EMNLP
    MolErr2Fix: Benchmarking LLM Trustworthiness in Chemistry
    Yuyang Wu, Jinhui Ye, Shuhao Zhang, and 3 more authors
    In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
    Oral