Zebin Yao

I am a 1st-year PhD student in the Department of Computing at The Hong Kong Polytechnic University, fortunately advised by Prof. Jieming Shi. I completed my Bachelor's and Master's degrees in Computer Science at Nankai University, where I was supervised by Prof. Gang Wang and Prof. Xiaoguang Liu.

zebin.yao@connect.polyu.hk  /  GitHub  /  Scholar  

Dynamic Detect and Fix Hardness for Efficient Approximate Nearest Neighbor Search

We propose a novel method for improving approximate nearest neighbor search performance in out-of-distribution scenarios by introducing Escape Hardness to dynamically identify and fix defective graph regions.

Overcoming the Sync-Compute Dilemma in Parallel Graph-Based Vector Retrieval

This work addresses the sync-compute dilemma in parallel graph-based vector retrieval via ScatterSearch, a synchronization-free intra-query parallel design with leader-guided pruning and work-stealing.

Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents

We demystifies the key factors affecting the efficiency of LLM-based search agents and, based on these insights, designs SearchAgent-X to improve end-to-end efficiency without compromising generation quality.

ALGAS: A Low-latency GPU-Accelerated Approximate Nearest Neighbor Search System

We present a low-latency GPU vector search system for small batch processing that optimizes query bubble via dynamic batching, reduces sorting overhead with beam extend, eliminates TopK-merging overhead through GPU-CPU cooperation, and enhances resource utilization with adaptive tuning.

Design and source code from Jon Barron's website