Qdrant TurboQuant Explained: Is TurboQuant the Silver Bullet?

VQ-bench: A Composable Vector Quantization Framework

arXiv:2608. 11240v1 Announce Type: new Abstract: Vector quantization is an old problem but has recently become central to AI infrastructure.

Leech Lattice Vector Quantization for Efficient LLM Compression

arXiv:2603. 11021v2 Announce Type: replace Abstract: Scalar quantization of large language models (LLMs) is fundamentally limited by information-theoretic bounds.

Quanto: a PyTorch quantization backend for Optimum

HeRo-Q: A General Framework for Stable Low Bit Quantization via Hessian Conditioning

arXiv:2601. 21626v2 Announce Type: replace-cross Abstract: Post Training Quantization (PTQ), a mainstream model compression technique, often leads to the paradoxical 'low error, high loss' phenomenon because it focuses solely on minimizing quantization error.

SSTQ:Privacy-Preserving Vector Quantization via Subsampled Stochastic TurboQuant

arXiv:2608. 05127v1 Announce Type: cross Abstract: Achieving local differential privacy in distributed optimization while maintaining low communication cost remains challenging.

ShamAN-Q: Shampoo Augmented NanoQuant for Sub-1-bit LLM Weights

ShamAN-Q is a sub‑1‑bit post‑training quantization technique that builds on NanoQuant by replacing its diagonal reconstruction geometry with a dense curvature metric inspired by the Shampoo optimizer. For each linear weight, it fits a Kronecker product to the empirical Fisher information matrix of a small calibration set via Kullback–Leibler minimization, yielding a Mahalanobis reconstruction loss. The method updates continuous ADMM steps to Sylvester equations while keeping the discrete projection and deployment format unchanged, and it redistributes uniform rank across layers, achieving lower perplexity on Qwen3‑Base at roughly 1 bpw and matching or improving zero‑shot accuracy on the Eleuther LM Evaluation Harness.

Inner Product Aware Quantization: Provably Fast, Accurate, and Adaptive Algorithms

arXiv:2606. 00289v1 Announce Type: new Abstract: Quantization is a fundamental tool used to compress datasets, neural network weights, and memory usage in a range of computational tasks.

Price of metric universality in vector quantization is at most 0.11 bit

arXiv:2602. 05790v2 Announce Type: replace-cross Abstract: Fast computation of a matrix product $W^\top X$ is a workhorse of modern LLMs.

Fragmentation is Efficiently Learnable by Quantum Neural Networks

arXiv:2512.00751v4 Announce Type: replace-cross Abstract: In certain classes of physical quantum systems, the exponentially large state space "fragments" into many low-dimensional, dynamically discon...

NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models

arXiv:2602. 06694v3 Announce Type: replace Abstract: Weight-only quantization has become a standard approach for efficiently serving large language models (LLMs).

WaterSIC: Information-Theoretically (Near) Optimal Linear Layer Quantization

arXiv:2603. 04956v2 Announce Type: replace Abstract: This paper considers the problem of converting a given dense linear layer to low precision.

Exponential quantum advantage in processing massive classical data

The paper demonstrates that a small quantum computer of polylogarithmic size can achieve large‑scale classification and dimension reduction on massive classical data, while any classical machine achieving the same performance would need exponentially larger size. It shows that classical machines even if exponentially larger still require superpolynomially more samples and time. The authors provide evidence from real‑world applications such as single‑cell RNA sequencing and movie review sentiment analysis, achieving four to six orders of magnitude reduction in size with fewer than 60 logical qubits.