Graduate Student
Computer Science & Artificial Intelligence Laboratory
MIT
I am a third-year graduate student at EECS, MIT and am very fortunate to be advised by Prof. Piotr Indyk.
Before coming to MIT, I was an undergrad in Yao's Class, Tsinghua University, and I was very fortunate to be advised by Prof. Jian Li, Prof. Tengyu Ma, Prof. Simon Du, and Prof. Zhilin Yang.
Feel free to contact me at {my first name}{my last name}@mit.edu.
Research interests
Algorithm Design, Nearest Neighbor Search
Publications
A full list of my publications can be found on DBLP and Google Scholar.
- In-Place Updates of a Graph Index for Streaming Approximate Nearest Neighbor Search
Haike Xu, Magdalen Dobson Manohar, Philip A Bernstein, Badrish Chandramouli, Richard Wen, Harsha Vardhan Simhadri
- A Bi-metric Framework for Fast Similarity Search
Haike Xu, Sandeep Silwal, Piotr Indyk
ICML 2025 Workshop on Vector Databases (Best Paper Award) - Graph-based algorithms for diverse similarity search
Piyush Anand, Piotr Indyk, Ravishankar Krishnaswamy, Sepideh Mahabadi, Vikas C Raykar, Kirankumar Shiragur, Haike Xu
ICML 2025 - SparseCL: Sparse Contrastive Learning for Contradiction Retrieval
Haike Xu, Zongyu Lin, Yizhou Sun, Kai-Wei Chang, Piotr Indyk
ICML 2025 - Statistical-Computational Trade-offs for Density Estimation
Anders Aamand, Alexandr Andoni, Justin Y Chen, Piotr Indyk, Shyam Narayanan, Sandeep Silwal, Haike Xu
NeurIPS 2024 - Worst-case Performance of Popular Approximate Nearest Neighbor Search Implementations: Guarantees and Limitations
Piotr Indyk, Haike Xu
NeurIPS 2023 - A Universal Discriminator for Zero-Shot Generalization
Haike Xu, Zongyu Lin, Jing Zhou, Yanan Zheng and Zhilin Yang
ACL 2023 - Embeddings and labeling schemes for A*
Talya Eden, Piotr Indyk, Haike Xu
ITCS 2022 - Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap
Haike Xu, Tengyu Ma, Simon S. Du
COLT 2021 - Simple Combinatorial Algorithms for Combinatorial Bandits: Corruptions and Approximations
Haike Xu, Jian Li
UAI 2021