arXiv Computer Vision August 26, 2026 By Peng Xia, Junbiao Pang

SandwichQuant: Which Parameters Matter Before and After Quantization?

Read the original on arXiv Computer Vision →

The paper investigates which trainable parameters most influence quantization correction, finding that normalization-affine parameters form a low‑dimensional subspace that is highly effective for correction. It introduces SandwichQuant, a two‑stage framework that first adapts normalization-affine parameters before quantization to boost robustness, then fine‑tunes them after quantization to reduce residual errors. Experiments on vision and large language models show consistent gains across various low‑bit settings, confirming the benefit of subspace‑aligned correction.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

Jul 16

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache

arXiv:2505. 18231v3 Announce Type: replace-cross Abstract: Large Language Model (LLM) inference is typically memory-intensive, especially when processing large batch sizes and long sequences, due to the large size of key-value (KV) cache.

By Donghyun Son, Euntae Choi, Sungjoo Yoo

llms efficiency safety

arXiv AI

Aug 10

ReQuant: Fixed-Grid Discrete Refinement for Post-Training Quantization

arXiv:2608. 07019v1 Announce Type: new Abstract: Post-training quantization (PTQ) is widely used to reduce the memory and computational cost of large language models.

By Yongge Ma, Guoan Wang, Feiyu Wang, Yaoming Li, Qian Zhang, Zihan Yan, Yinjun Han, Tong Yang

llms efficiency

arXiv Machine Learning

Aug 18

SchurQuant: Groupwise Discrete Optimization for Layer-Wise LLM Quantization

arXiv:2608. 15567v1 Announce Type: new Abstract: Weight-only post-training quantization (PTQ) enables the deployment of large language models under tight memory budgets, but accuracy often collapses at 2-3 bits.

By Gunjun Lee, Sehwan Son, Younjoo Lee, Byungjun Kim, Jung Ho Ahn

llms efficiency

arXiv AI

Jun 4

MorphoQuant: Modality-Aware Quantization for Omni-modal Large Language Models

arXiv:2606. 04349v1 Announce Type: cross Abstract: Conventional Post-Training Quantization (PTQ) methods struggle with 4-bit Omni-modal Large Language Models (OLLMs) due to the extreme distribution heterogeneity and disparate outlier patterns across modalities.

By Yue Wu, Changyuan Wang, Zixuan Wang, Shilin Ma, Yansong Tang

llms efficiency multimodal benchmarks safety

arXiv Machine Learning

Jun 2

ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression

arXiv:2606. 00494v1 Announce Type: new Abstract: Post-Training Quantization (PTQ) and Low-Rank Adaptation (LoRA) constitute the standard pipeline for efficient Large Language Model (LLM) deployment.

By Wneya Yu, Chao Zhang, Li Wang, Samson Lasaulce, Merouane Debbah

llms fine-tuning efficiency

arXiv Machine Learning

Jun 19

CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training

arXiv:2510. 18784v3 Announce Type: replace Abstract: Despite significant work on low-bit quantization-aware training (QAT), there is still an accuracy gap between such techniques and native training.

By Soroush Tabesh, Mher Safaryan, Andrei Panferov, Alexandra Volkova, Dan Alistarh

llms fine-tuning efficiency benchmarks

One email a morning, machine-written

Related stories

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache

ReQuant: Fixed-Grid Discrete Refinement for Post-Training Quantization

SchurQuant: Groupwise Discrete Optimization for Layer-Wise LLM Quantization

MorphoQuant: Modality-Aware Quantization for Omni-modal Large Language Models

ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression

CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training