Binary Quantization

Latest papers

9 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Tailoring the Quantization Space for 1-Bit KV Cache Compression
Oct 2, 2026Minsoo Cheong, Donghyun Son, Sungjoo YooBinary Quantization KV-Cache Compression
Stanford University · Seoul National University
FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy
Aug 16, 2026Qingyao Yang, Runming Yang, He Xiao +7Binary Quantization LLM Inference Acceleration
The University of Hong Kong · Harbin Institute of Technology
One Qubit Can Beat One Bit: Quantum Advantage for Post-Training Quantization
Aug 5, 2026Yuma Ichikawa, Moeto MishimaBinary Quantization Post-Training Quantization
Fujitsu Limited, RIKEN for AIP · RIKEN for AIP · Fujitsu Limited
Cross-Layer Error Compensation and Finite-Sample Feature-Statistics Matching for Extreme Low-Bit Quantization of Large Language Models
Jul 16, 2026Ryona NodaLLM Quantization Binary Quantization
Ryo Noda
Covariance Structure and Coordinate Heterogeneity Govern Binary Quantization of Contrastive Embeddings
May 17, 2026Wenxuan XiaoBinary Quantization Neural Representation Geometry
Changsha University
Generative Refinement Networks for Visual Synthesis
Apr 14, 2026Jian Han, Jinlai Liu, Jiahuan Wang +2Binary Quantization T2V Generation
ByteDance
SLaB: Sparse-Lowrank-Binary Decomposition for Efficient Large Language Models
Apr 6, 2026Ziwei Li, Yuang Ma, Yi KangBinary Quantization LLM Compression
School of Microelectronics, University of Science and Technology of China, Hefei, Anhui, China
BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design
Apr 5, 2026Yifu Ding, Xianglong Liu, Shenghao Jin +2Binary Quantization Low-Bit Quantization
School of Computer Science and Engineering, Beihang University, Beijing, China. · Institute of Artificial Intelligence, Beihang University, Beijing, China. · Department of Automation, Tsinghua University, Beijing, China.
Self-Indexing KVCache: Predicting Sparse Attention from Compressed Keys
Mar 15, 2026Xu Yang, Jiapeng Zhang, Dongyang Zhao +2Binary Quantization LLM Inference Acceleration
College of Computer Science and Electronic Engineering, Hunan University, Changsha, China · The Ministry of Education Key Laboratory of “Fusion Computing of Supercomputing and Artificial Intelligence” China · Shenzhen Research Institute, Hunan University, Shenzhen, China

Oct 2, 2026J/K move · Enter open · S save

Tailoring the Quantization Space for 1-Bit KV Cache Compression

Minsoo Cheong, Donghyun Son, Sungjoo Yoo

Stanford University · Seoul National University

Binary Quantization KV-Cache Compression KV-Cache Quantization Vector Quantization LLM Inference Acceleration Neural Network Quantization

Open paper AskPDF arXiv

The key-value (KV) cache becomes a major memory bottleneck in long-context LLM inference, placing substantial pressure on memory capacity and bandwidth. To mitigate this bottleneck, vector quantization (VQ) has emerged as a promising approach for aggressive KV cache compression. However, existing VQ methods degrade substantially in the 1-bit regime. At such extreme compression, each codebook must represent a larger group of channels with a limited set of centroids, making effective use of its capacity increasingly challenging. To address this, we introduce

\textbf{TaSQ}

, which tailors the VQ target space by combining query-guided channel weighting, cross-head normalization, and covariance-aware channel grouping to better reflect the error sensitivity and statistical structure of cached activations. Since these transforms are RoPE-compatible and can be easily merged into projection weights and codebooks, TaSQ preserves the conventional VQ lookup structure and adds negligible serving overhead. Across general, long-chain-of-thought reasoning, and long-context retrieval benchmarks, TaSQ consistently outperforms existing low-bit KV cache VQ baselines while preserving reasoning stability. On a single RTX 6000 Ada GPU, its SGLang implementation supports up to

14\times

larger batch sizes and achieves

1.87\times

higher peak throughput compared to the BF16 baseline.