most citedVectorSearch: Enhancing Document Retrieval with Semantic Embeddings and Optimized Search

5 citations · 6 across the 7 of their papers we have counts for

collaborators

8 papers

cs.IR2026

AdaWidth: Query-Adaptive Embedding Width for Dense Retrieval

Shubing Yang, Dongfang Zhao

High-dimensional embeddings are central to dense retrieval, but not all of these dimensions need to be evaluated at retrieval time. Existing methods reduce dimensions in two ways:…

cs.IR2026

SHEAF: Self-profiled Hardness Estimation from Answer-set Flux for Predicting Query Hardness in Graph-based ANN Search

Dongfang Zhao

Graph-based approximate nearest neighbor (ANN) search is usually governed by a beam-width parameter that trades recall for throughput and is fixed for the whole workload. Yet, quer…

cs.DC2026

ETALE: Evolving Topology with Accelerated Lock-free Execution for Dynamic Graph ANN Search on GPUs

Dongfang Zhao

Graph-based approximate nearest neighbor (ANN) indexes on the GPU are originally built for static collections and must reconstruct the affected window to absorb any update, while t…

cs.IR2026

Slipstream: Locality-Aware Graph Index Construction for Streaming Approximate Nearest Neighbor Search

Shubing Yang, Dongfang Zhao

Graph indexes are widely used for high-recall approximate nearest neighbor search (ANNS), but many real-time applications require streaming ANNS. In these real-time applications, c…

cs.IR2024

NexusIndex: Integrating Advanced Vector Indexing and Multi-Model Embeddings for Robust Fake News Detection

Solmaz Seyed Monir, Dongfang Zhao

The proliferation of fake news on digital platforms has underscored the need for robust and scalable detection mechanisms. Traditional methods often fall short in handling large an…

cs.LG20241 cited

VecLSTM: Trajectory Data Processing and Management for Activity Recognition through LSTM Vectorization and Database Integration

Solmaz Seyed Monir, Dongfang Zhao

Activity recognition is a challenging task due to the large scale of trajectory data and the need for prompt and efficient processing. Existing methods have attempted to mitigate t…