Selected work

Representative Papers

Coordinate Heterogeneity Governs Binary Quantization: From InfoNCE to Recall

May 17, 2026

This work addresses the inconsistent performance of binary quantization in embedding spaces, which excels in contrastive learning embeddings but degrades sharply in others, and resolves the lack of a unified theoretical foundation between the “random rotation” and “axis-aligned” quantization strategies. The study identifies the heterogeneity of coordinate-wise variances as the key factor governing quantization efficacy and establishes, for the first time, an analytical framework under a Gaussian structural assumption. This framework yields a closed-form solution for rank fidelity, quantitatively linking the information content of magnitude bits to variance heterogeneity, and unifies the conditions under which the two seemingly opposing strategies are optimal. Theoretical predictions are validated across 13 datasets and 6 embedding types, providing the first principled design guidelines for binary quantization systems.

0 citationsRead paper

QuIVer: Rethinking ANN Graph Topology via Training-Free Binary Quantization

May 03, 2026

This work addresses the underutilization of binary quantization in traditional approximate nearest neighbor (ANN) graph indices, which typically apply it only during search. The paper proposes QuIVer—the first training-free ANN graph index that performs edge selection, pruning, and navigation entirely within a 2-bit sign-magnitude binary quantized (BQ) space. By elevating binary quantization from a mere acceleration tool to a core graph construction mechanism, QuIVer integrates sign-magnitude encoding, α-diversity pruning in BQ space, and a symmetric BQ beam search based on XOR, AND, and popcount operations, followed by lightweight float32 re-ranking. On multiple high-dimensional datasets, QuIVer achieves ≥91% Recall@10 while delivering approximately 16× higher throughput than hnswlib and 5× higher than USearch HNSW, with hot memory usage under 0.9 GB.

0 citationsRead paper

Recent publications

Latest Papers

Coordinate Heterogeneity Governs Binary Quantization: From InfoNCE to Recall

May 17, 2026

This work addresses the inconsistent performance of binary quantization in embedding spaces, which excels in contrastive learning embeddings but degrades sharply in others, and resolves the lack of a unified theoretical foundation between the “random rotation” and “axis-aligned” quantization strategies. The study identifies the heterogeneity of coordinate-wise variances as the key factor governing quantization efficacy and establishes, for the first time, an analytical framework under a Gaussian structural assumption. This framework yields a closed-form solution for rank fidelity, quantitatively linking the information content of magnitude bits to variance heterogeneity, and unifies the conditions under which the two seemingly opposing strategies are optimal. Theoretical predictions are validated across 13 datasets and 6 embedding types, providing the first principled design guidelines for binary quantization systems.

0 citationsRead paper

QuIVer: Rethinking ANN Graph Topology via Training-Free Binary Quantization

May 03, 2026

This work addresses the underutilization of binary quantization in traditional approximate nearest neighbor (ANN) graph indices, which typically apply it only during search. The paper proposes QuIVer—the first training-free ANN graph index that performs edge selection, pruning, and navigation entirely within a 2-bit sign-magnitude binary quantized (BQ) space. By elevating binary quantization from a mere acceleration tool to a core graph construction mechanism, QuIVer integrates sign-magnitude encoding, α-diversity pruning in BQ space, and a symmetric BQ beam search based on XOR, AND, and popcount operations, followed by lightweight float32 re-ranking. On multiple high-dimensional datasets, QuIVer achieves ≥91% Recall@10 while delivering approximately 16× higher throughput than hnswlib and 5× higher than USearch HNSW, with hot memory usage under 0.9 GB.

0 citationsRead paper