I am Huyu Wu (ไผ่กๅฎ), a second-year Masterโs student at the Institute of Computing Technology, Chinese Academy of Sciences (ICT). Currently, I am a Search Algorithm Intern on the Tako team at TikTok Search, where we develop core technologies for next-generation intelligent search experiences. I focus on building LLM-based agents for the comment section.
My previous research background covers Dataset Distillation and Multimodal Large Language Models, where I explored methods for efficient data representation and modality bias. I am always open to discussions and potential collaborations!
You can find my more research interests on 
๐ฅ News
- 2026.09: ย ๐๐ Two papers are accepted by NeurIPS 2026.
- 2026.02: ย ๐๐ One paper is accepted by ICLR 2026.
- 2025.10: ย ๐๐ One paper is accepted by Transactions on Machine Learning Research.
- 2025.10: ย ๐๐ I joined Xiaohongshu as a Research Intern to work on Agentic Search.
- 2025.09: ย ๐๐ One paper is accepted by Neural Networks.
๐ Publications
- Wu H, Liu J, Wei X, Gao Y, Wu Y, Hu Y. โKnowledge-Graph Paths as Intermediate Supervision for Self-Evolving Search Agents.โ Advances in Neural Information Processing Systems (NeurIPS), 2026. (First Author, CCF-A)
- Wu H, Tang M, Zheng X, Su D, Jiang H. โWhen Language Overrules: Revealing Text Dominance in Multimodal Large Language Models.โ Advances in Neural Information Processing Systems (NeurIPS), 2026. (First Author, CCF-A)
- Su D, Wu H, Chen H, Shi Y, Wang Y, Ye X, Zhu J. โDiffusion Models as Dataset Distillation Priors.โ The Fourteenth International Conference on Learning Representations, 2026. (Second Author)
- Wu H, Su D, Hou J, Li G. Dataset Condensation with Color Compensation[J]. Transactions on Machine Learning Research (TMLR), 2025. (First Author)
- Wu H, Jia B, Yuan X M. LLM-Led Vision-Spectral Fusion: A Zero-Shot Approach to Temporal Fruit Image Classification[J]. Neural Networks, 2025: 108155. (First Author, CCF-B)
- Jia B, Guo Z, Huang T, Guo F, & Wu H. A generalized Lorenz system-based initialization method for deep neural networks[J]. Applied Soft Computing, 2024, 167: 112316. (Last Author, ไธญ็ง้ขไธๅบTOP)
- Jia B, Wu H, Guo K. Chaos theory meets deep learning: A new approach to time series forecasting[J]. Expert Systems with Applications, 2024, 255: 124533. (Co-First Author, ไธญ็ง้ขไธๅบTOP)
- Wu H, Jia B, Sheng G. Early-Late Dropout for DivideMix: Learning with Noisy Labels in Deep Neural Networks[C]//2024 International Joint Conference on Neural Networks (IJCNN). IEEE, 2024: 1-8. (First Author, CCF-C)
๐ Educations
- 2025.09 โ Present, M.S., Institute of Computing Technology, University of Chinese Academy of Sciences
- 2021.09 โ 2025.06, B.S., College of Computer Science, Sichuan University
- 2020.09 โ 2021.06, Business School, Business Administration, Sichuan University
๐ป Internships
-
2026.09 - Present, Intern at TikTok Search Tako
-
2025.10 - 2026.09, Search Algorithm Intern at Xiaohongshu (Beijing)
-
2024.08 - 2025.09, Intern of TSAIL - Tsinghua University
- 2023.12 - 2024.04, Research Assistant of National University of Singapore - Institute of Operations Research and Analytics
- 2022.11 - 2024.08, Research Assistant of Sichuan University - Machine Intelligence Lab
๐ Projects
VEX Robotics Competition
Led the schoolโs VEX Robotics club, responsible for programming and debugging of the robotic systems.
Attained Gold Awards at China Zone Selections, the Asia Championships, Asia Open and the World Championships in the United States during the 2018 season.
๐ Honors and Awards
- 2024.10 Huang Qianheng Scholarship.
- 2023.06 Champion, 3rd Youth Campus Volleyball League of Sichuan Province.
- 2022.11 Second Prize, Asia-Pacific Undergraduate Mathematical Contest in Modeling.
- 2022.06 Third Prize, 2th Youth Campus Volleyball League of Sichuan Province.
๐ Academic Services
-
Conference Reviewer: IJCNN 2024, ACL 2024, CaLM @NeurIPS 2024, ICLR 2025, AAAI 2026, ICME 2026, ACMMM 2026
-
Journal Reviewer: IEEE Transactions on Neural Networks and Learning Systems(IEEE TNNLS), Journal of Supercomputing