Neural Network Quantization

Follow this topic Ask about this topic

Momentum

57 papers in the last four weeks, up 54% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 312

Apr 28, 2026cs.AR

Multibit neural inference in a N-ary crossbar architecture

In-memory computing (IMC) is a paradigm that enables neural network inference by computing analog matrix-vector multiplications (MVM) directly in memory crossbar arrays, with the potential for energy efficiency gains over conventional von Neumann architectures. In this work we present a simulation framework for N-ary crossbar architectures that retrieves MVM results with minimal implementation assumptions. The XOR and MNIST classification tasks were successfully inferred using a simulated crossbar array of (4x4) 4-states magnetic tunnel junctions (MTJ). MNIST accuracy reached 93.56% (vs. 97.56% software baseline). PCA dimensionality reduction was shown to drastically lower the number of required operations and improve the software baseline, for only a modest reduction in crossbar inference accuracy. We identified weight quantization as the primary error source, and studied its impact alongside systematic non-idealities and random noise. We find that cell-specific random noise is less detrimental than systematic errors due to averaging across the array. Finally, we demonstrate an optimal number of states per cell that balances quantization error against resistance state resolution to minimize total MVM error.

Anatole Moureaux, Anthony Lopes Temporao, Flavio Abreu Araujo

Universit´e catholique de Louvain, Institute of Condensed Matter and Nanosciences, Louvain-la-Neuve, 1348, Belgium

Efficient Neural Network Inference Compute-in-Memory Neural Network Quantization

Apr 28, 2026cs.LG

QFlash: Bridging Quantization and Memory Efficiency in Vision Transformer Attention

FlashAttention improves efficiency through tiling, but its online softmax still relies on floating-point arithmetic for numerical stability, making full quantization difficult. We identify three main obstacles to integer-only FlashAttention: (1) scale explosion during tile-wise accumulation, (2) inefficient shift-based exponential operations on GPUs, and (3) quantization granularity constraints requiring uniform scales for integer comparison. To address these challenges, we propose \textit{QFlash}, an end-to-end integer FlashAttention design that performs softmax entirely in the integer domain and runs as a single Triton kernel. On seven attention workloads from ViT, DeiT, and Swin models, QFlash achieves up to 6.73

\times

speedup over I-ViT and up to 8.69

\times

speedup on Swin, while reducing energy consumption by 18.8% compared to FP16 FlashAttention, without sacrificing Top-1 accuracy on ViT/DeiT and remaining competitive on Swin under per-tensor quantization. Our code is publicly available at https://github.com/EfficientCompLab/qflash.

Sehyeon Oh, Yongin Kwon, Jemin Lee

University of Science and Technology, Daejeon, Republic of Korea · Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea · Pusan National University, Busan, Republic of Korea +1

Softmax Attention GPU Acceleration Vision Transformer Efficient ViTs Attention Quantization Attention Mechanisms+2

Apr 27, 2026cs.CV

Deployment-Aligned Low-Precision Neural Architecture Search for Spaceborne Edge AI

Designing deep networks that meet strict latency and accuracy constraints on edge accelerators increasingly relies on hardware-aware optimization, including neural architecture search (NAS) guided by device-level metrics. Yet most hardware-aware NAS pipelines still optimize architectures under full-precision assumptions and apply low-precision adaptation only after the search, leading to a mismatch between optimization-time behavior and deployment-time execution on low-precision hardware that can substantially degrade accuracy. We address this limitation by integrating deployment-aligned low-precision training directly into hardware-aware NAS. Candidate architectures are exposed to FP16 numerical constraints during fine-tuning and evaluation, enabling joint optimization of architectural efficiency and numerical robustness without modifying the search space or evolutionary strategy. We evaluate the proposed framework on vessel segmentation for spaceborne maritime monitoring, targeting the Intel Movidius Myriad X Visual Processing Unit (VPU). While post-training precision conversion reduces on-device performance from 0.85 to 0.78 mIoU, deployment-aligned low-precision training achieves 0.826 mIoU on-device for the same architecture (95,791 parameters), recovering approximately two-thirds of deployment-induced accuracy gap without increasing model complexity. These results demonstrate that incorporating deployment-consistent numerical constraints into hardware-aware NAS substantially improves robustness and alignment between optimization and deployment for resource-constrained edge Artificial Intelligence (AI).

Parampuneet Kaur Thind, Vaibhav Katturu, Giacomo Zema +1

1Sapienza University of Rome · 2 Φ-lab, ESA ESRIN · 4Argotec Srl +1

Edge Computing Hardware-Aware NAS Neural Architecture Search Neural Network Quantization

Apr 25, 2026cs.CV

Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy

Federated learning (FL) is a distributed machine learning method where multiple devices collaboratively train a model under the management of a central server without sharing underlying data. One of the key challenges of FL is the communication bottleneck caused by variations in connection speed and bandwidth across devices. Therefore, it is essential to reduce the size of transmitted data during training. Additionally, there is a potential risk of exposing sensitive information through the model or gradient analysis during training. To address both privacy and communication efficiency, we combine differential privacy (DP) and adaptive quantization methods. We use Laplacian-based DP to preserve privacy, which is relatively underexplored in FL and offers tighter privacy guarantees than Gaussian-based DP. We propose a simple and efficient global bit-length scheduler using round-based cosine annealing, along with a client-based scheduler that dynamically adapts based on client contribution estimated through dataset entropy analysis. We evaluate our approach through extensive experiments on CIFAR10, MNIST, and medical imaging datasets, using non-IID data distributions across varying client counts, bit-length schedulers, and privacy budgets. The results show that our adaptive quantization methods reduce total communicated data by up to 52.64% for MNIST, 45.06% for CIFAR10, and 31% to 37% for medical imaging datasets compared to 32-bit float training while maintaining competitive model accuracy and ensuring robust privacy through differential privacy.

Emre Ardıç, Yakup Genç

Department of Computer Engineering, Gebze Technical University, Gebze, Kocaeli 41400, Türkiye

Non-IID Federated Learning Differentially Private Federated Learning Neural Network Quantization Federated Learning

Apr 25, 2026cs.LG

Efficient VQ-QAT and Mixed Vector/Linear quantized Neural Networks

In this work, we developed and tested 3 techniques for vector quantization (VQ) based model weight compression. To mitigate codebook collapse and enable end-to-end training, we adopted cosine similarity-based assignment. Building on ideas from attention-based formulations in Differentiable K-Means (DKM), we further improved this approach by using cosine similarity for assignment combined with top-1 sampling and a straight-through estimator, thereby eliminating the need for weighted-average reconstruction. Finally, we investigated the use of differentiable neural architecture search (NAS) to adaptively select layer-wise quantization configurations, further optimizing the compression process. Although our method does not consistently outperform existing approaches across all quantization levels, it provides useful insights into the design trade-offs and behaviors of VQ-based model compression methods.

Terry Gou, Puneet Gupta

Quantization-Aware Training Vector Quantization Neural Network Quantization Neural Network Compression

Apr 24, 2026cs.AR

HGQ-LUT: Fast LUT-Aware Training and Efficient Architectures for DNN Inference

Lookup-table (LUT) based neural networks can deliver ultra-low latency and excellent hardware efficiency on FPGAs by mapping arithmetic operations directly onto the logic primitives. However, state-of-the-art LUT-aware training (LAT) approaches remain difficult to use in practice: they are often orders of magnitude slower to train than conventional networks, require non-trivial manual tuning for hardware efficiency, and lack an end-to-end workflow. This work presents HGQ-LUT, integrated in https://github.com/calad0i/HGQ2, a new LAT approach that achieves state-of-the-art hardware efficiency while accelerating training by over 100 times on modern GPUs. HGQ-LUT introduces LUT-Dense and LUT-Conv layers that are implemented with regular, accelerator-efficient tensor operations during training, which are then compiled into logic LUTs for hardware. By combining these layers with fine-grained, element-wise heterogeneous quantization (including zero-bit pruning) and a LUT-aware resource surrogate, HGQ-LUT enables the automatic exploration of accuracy-resource trade-offs without manual bit-width tuning. We further integrate HGQ-LUT into open-source toolchains, enabling unified design, compilation, and bit-exact verification of hybrid architectures that mix LUT-based with conventional arithmetic blocks. These features make LAT-based DNNs practical for real-world deployment, such as at the CERN Large Hadron Collider's experiments.

Chang Sun, Zhiqiang Que, Bakhtiar Zadeh +4

California Institute of Technology, Pasadena, CA, USA · University of Bristol, UK · Imperial College London, UK +1

Efficient Neural Network Inference FPGA-Based Neural Network Acceleration Neural Network Quantization

Apr 22, 2026cs.LG

FASQ: Flexible Accelerated Subspace Quantization for Calibration-Free LLM Compression

Compressing large language models (LLMs) for deployment on commodity GPUs remains challenging: conventional scalar quantization is limited to fixed bit-widths (e.g., 8/4/3-bit), offers only a few discrete compression points, and typically requires calibration data. We present FASQ (Flexible Accelerated Subspace Quantization), a calibration-free framework that applies product quantization to LLM weight matrices. By tuning two parameters, sub-vector size and codebook cardinality, FASQ exposes a continuous design space spanning 27-49% of the original FP16 model size, filling compression gaps that fixed-bit schemes cannot reach. On Meta-Llama-3-8B, FASQ surpasses 4-bit GPTQ and AWQ in accuracy (67.1-67.7 avg.) at 37-42% model size, with consistent results on Qwen3-8B and Qwen3.5-9B-Base. To make product quantization practical at inference time, we design custom CUDA kernels: a LUT-free direct-compute GEMV for decode and an output-stationary double-buffered LUT GEMM for prefill, both with split-K parallelism. On an RTX~3090, FASQ achieves 45.2 tok/s decode at effective 4-bit (2.56x memory reduction) and 51.8 tok/s at effective 3-bit (2.80x), both surpassing FP16 tensor-core performance (43.9 tok/s) and delivering 1.6 to 1.8x the throughput of AWQ, 2.5 to 2.5x of GPTQ, and 4.3 to 5x of RTN. FASQ is the only compressed method that accelerates decode beyond FP16, offering calibration-free compression, continuous size-quality trade-offs, and real-time inference on a single consumer GPU.

Ye Qiao, Yian Wang, Zhiheng Chen +2

University of California, Irvine Irvine, California, USA

LLM Compression GPU Acceleration Vector Quantization LLM Inference Acceleration Product Quantization Post-Training Quantization+1

Apr 22, 2026cs.NE

Quantization robustness from dense representations of sparse functions in high-capacity kernel associative memory

High-capacity associative memories based on Kernel Logistic Regression (KLR) achieve strong retrieval performance but typically require substantial computational resources. This paper investigates the compressibility of KLR Hopfield networks to clarify the geometric principles underlying their robust representations. We present a geometric interpretation based on spontaneous symmetry breaking and Walsh analysis, and examine it through compression experiments involving quantization and pruning. The experiments reveal a clear asymmetry: the network remains robust under low-precision quantization while exhibiting strong sensitivity to pruning. We interpret this behavior through a "sparse function, dense representation" principle, in which a sparse input mapping is implemented through a dense bimodal parameterization. These findings suggest a practical route toward hardware-efficient kernel associative memories and provide insight into the geometric principles underlying robust representation in neural systems.

Akira Tamamori

Faculty of Information Science, Aichi Institute of Technology 1247 Yachigusa, Yakusa-cho, Toyota-shi, Aichi 470-0392, Japan

Neural Representation Geometry Hopfield Networks Associative Memory Neural Network Quantization

Apr 22, 2026cs.LG

FairyFuse: Multiplication-Free LLM Inference on CPUs via Fused Ternary Kernels

Large language models are increasingly deployed on CPU-only platforms where memory bandwidth is the primary bottleneck for autoregressive generation. Weight quantization to four bits or below reduces memory pressure, yet existing systems still dequantize weights and perform floating-point multiplications, limiting the achievable gains. Ternary weights in {-1, 0, +1} provide a more efficient alternative, replacing multiplications with conditional additions, subtractions, or no-ops. While Fairy2i shows that ternary LLMs can match FP16 quality, its runtime does not exploit this structure. We present FairyFuse, an inference system that enables multiplication-free execution on commodity CPUs by fusing the eight real-valued sub-GEMVs of each widely-linear layer into a single AVX-512 loop using masked additions and subtractions, with zero floating-point multiplications. Roofline analysis shows that 16x weight compression shifts memory-bound GEMV toward the compute regime on bandwidth-limited CPUs, yielding a 29.6x kernel speedup while offering little benefit on GPUs. End-to-end, FairyFuse achieves 32.4 tokens per second on a single Intel Xeon 8558P, outperforming llama.cpp Q4_K_M by 1.24x with near-lossless quality (WikiText-2 perplexity 5.52 vs. 5.47 FP16; downstream accuracy 66.0%).

Fei Zuo, Xiaoyan Xi, Quanyi Zeng +2

BA TechWorks · Peking University

Efficient Neural Network Inference Ternary Quantization Inference-Time Optimization LLM Inference Acceleration Neural Network Quantization

Apr 22, 2026cs.LG

On the Quantization Robustness of Diffusion Language Models in Coding Benchmarks

Auto-regressive Large Language Models (LLMs) achieve strong performance on coding tasks, but incur high memory and inference costs. Diffusion-based language models (d-LLMs) offer bounded inference cost via iterative denoising, but their behavior under post-training quantization (PTQ) has been sparsely explored. We investigate the application and robustness of PTQ techniques, specifically GPTQ and a modified Hessian-Aware Quantization (HAWQ) algorithm, on a diffusion-based coding LLM (CoDA) and observe that these methods applied to CoDA exhibit greater robustness at low bitwidths compared to Qwen3-1.7B, its auto-regressive counterpart, under a standardized evaluation pipeline. We find that in our setup, CoDA exhibits greater robustness at low bitwidths (2-4 bits), with smaller accuracy degradation across HumanEval and MBPP benchmarks. Additionally, mixed-precision configurations derived from HAWQ provide smooth trade-offs across accuracy, latency, and memory. The results suggest that diffusion LLMs may offer advantages for efficient deployment due to more quantization-resilience.

Aarav Gupta, Gururaj Deshpande, Chandreyi Chakraborty

College of Computing · Georgia Institute of Technology

Mixed-Precision Quantization Diffusion Model Quantization Diffusion Language Models Post-Training Quantization Neural Network Quantization

Apr 21, 2026cs.CL

From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization

Post-Training Quantization (PTQ) is critical for the efficient deployment of Large Language Models (LLMs). While 4-bit quantization is widely regarded as an optimal trade-off, reducing the precision to 2-bit usually triggers a catastrophic ``performance cliff.'' It remains unclear whether the underlying mechanisms differ fundamentally. Consequently, we conduct a systematic mechanistic analysis, revealing two qualitatively distinct failure modes: Signal Degradation, where the computational patterns remain intact but information precision is impaired by cumulative error; and Computation Collapse, where key components fail to function, preventing correct information processing and destroying the signal in the early layers. Guided by this diagnosis, we conduct mechanism-aware interventions, demonstrating that targeted, training-free repair can mitigate Signal Degradation, but remains ineffective for Computation Collapse. Our findings provide a systematic diagnostic framework for PTQ failures and suggest that addressing Computation Collapse requires structural reconstruction rather than mere compensation.

Chenxi Zhou, Pengfei Cao, Jiang Li +4

School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences · College of Computer Science, Inner Mongolia University +1

LLM Quantization Post-Training Quantization Low-Bit Quantization Neural Network Quantization

Apr 21, 2026cs.LG

SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving

KV-cache memory is a major bottleneck in real-world LLM serving, where systems must simultaneously support latency-sensitive small-batch requests and high-throughput concurrent workloads. Although many KV-cache compression methods improve offline accuracy or compression ratio, they often violate practical serving constraints such as paged memory layouts, regular memory access, and fused attention execution, limiting their effectiveness in deployment. In this work, we identify the minimal set of 4-bit KV-cache quantization methods that remain viable under these constraints. Our central finding is that a simple design--token-wise INT4 quantization with block-diagonal Hadamard rotation--consistently achieves the best accuracy-efficiency trade-off. Across multiple models and benchmarks, this approach recovers nearly all of the accuracy lost by naive INT4, while more complex methods such as vector quantization and Hessian-aware quantization provide only marginal additional gains once serving compatibility is taken into account. To make this practical, we implement a fused rotation-quantization kernel that integrates directly into paged KV-cache layouts and introduces zero measurable end-to-end overhead, matching plain INT4 throughput across concurrency levels. Our results show that effective KV-cache compression is fundamentally a systems co-design problem: under real serving constraints, lightweight block-diagonal Hadamard rotation is a viable method that delivers near-lossless accuracy without sacrificing serving efficiency.

Jinda Jia, Jisen Li, Zhongzhu Zhou +8

Together AI

LLM Serving KV Caching Memory-Efficient Optimization 4-Bit Quantization Rotation-Based Quantization LLM Inference Acceleration+2

Apr 20, 2026cs.CL

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling

Quantization has become a standard tool for efficient LLM deployment, especially for local inference, where models are now routinely served at 2-3 bits per parameter. The state of the art is currently split into simple scalar quantization techniques, such as GPTQ or AWQ, which are widely deployed but plateau in accuracy at 3-4 bits per parameter (bpp), and "second-generation" vector- or trellis-quantized methods, such as QTIP, GPTVQ and AQLM, which push the accuracy frontier but are notoriously hard to implement and to scale. In this paper, we ask whether this gap is fundamental, or whether a carefully optimized

\textit{scalar}

quantizer can recover most of it. We answer in the affirmative, by introducing GSQ (Gumbel-Softmax Quantization), a post-training scalar quantization method which jointly learns the per-coordinate grid assignments and the per-group scales using a Gumbel-Softmax relaxation of the discrete grid. GSQ matches the cardinality of the relaxation to the small number of levels available in the target bit-width regime (e.g., 3-8 levels for ternary and 3 bpp, respectively), making optimization tractable. Practically, on the standard Llama-3.1-8B/70B-Instruct models, GSQ closes most of the gap between scalar quantization and the QTIP frontier at 2 and 3 bits, while using a symmetric scalar grid with group-wise quantization, and thus remains compatible with existing scalar inference kernels. We further show that the same discrete-assignment optimization can be applied to practical GGUF K-Quant checkpoints: starting from publicly released GGUF models, GSQ improves accuracy while projecting the result back into the same deployment format. Finally, GSQ scales to trillion-scale Mixture-of-Experts models such as Kimi-K2.5, where vector-quantized methods are difficult to apply. The source code is publicly available at https://github.com/IST-DASLab/GSQ.

Alireza Dadgarnia, Soroush Tabesh, Mahdi Nikdan +4

ISTA · ETH Zürich · ISTA & Red Hat AI +1

LLM Quantization Post-Training Quantization Low-Bit Quantization Neural Network Quantization

Apr 20, 2026cs.LG

A Note on TurboQuant and the Earlier DRIVE/EDEN Line of Work

This note clarifies the relationship between the recent TurboQuant work and the earlier DRIVE (NeurIPS 2021) and EDEN (ICML 2022) schemes. DRIVE is a 1-bit quantizer that EDEN extended to any

b>0

bits per coordinate; we refer to them collectively as EDEN. First, TurboQuant

_{\text{mse}}

is a special case of EDEN obtained by fixing EDEN's scalar scale parameter to

S=1

. EDEN supports both biased and unbiased quantization, each optimized by a different

S

(chosen via methods described in the EDEN works). The fixed choice

S=1

used by TurboQuant is generally suboptimal, although the optimal

S

for biased EDEN converges to

1

as the dimension grows; accordingly TurboQuant

_{\text{mse}}

approaches EDEN's behavior for large

d

. Second, TurboQuant

_{\text{prod}}

combines a biased

(b-1)

-bit EDEN step with an unbiased 1-bit QJL quantization of the residual. It is suboptimal in three ways: (1) its

(b-1)

-bit step uses the suboptimal

S=1

; (2) its 1-bit unbiased residual quantization has worse MSE than (unbiased) 1-bit EDEN; (3) chaining a biased

(b-1)

-bit step with a 1-bit unbiased residual step is inferior to unbiasedly quantizing the input directly with

b

-bit EDEN. Third, some of the analysis in the TurboQuant work mirrors that of the EDEN works: both exploit the connection between random rotations and the shifted Beta distribution, use the Lloyd-Max algorithm, and note that Randomized Hadamard Transforms can replace uniform random rotations. Experiments support these claims: biased EDEN (with optimized

S

) is more accurate than TurboQuant

_{\text{mse}}

, and unbiased EDEN is markedly more accurate than TurboQuant

_{\text{prod}}

, often by more than a bit (e.g., 2-bit EDEN beats 3-bit TurboQuant

_{\text{prod}}

). We also repeat all accuracy experiments from the TurboQuant paper, showing that EDEN outperforms it in every setup we have tried.

Ran Ben-Basat, Yaniv Ben-Itzhak, Gal Mendelson +3

UCL and Broadcom · VMware Research by Broadcom · North Carolina State University +2

Residual VQ Vector Quantization Low-Bit Quantization Neural Network Quantization

Apr 20, 2026cs.LG

LoRaQ: Optimized Low Rank Approximation for 4-bit Quantization

Post-training quantization (PTQ) is essential for deploying large diffusion transformers on resource-constrained hardware, but aggressive 4-bit quantization significantly degrades generative performance. Low-rank approximation methods have emerged as a promising solution by appending auxiliary linear branches to restore performance. However, current state-of-the-art approaches assume these branches must retain high precision (W16A16) and rely on heavy, data-dependent calibration for initialization. We challenge both limitations with LoRaQ (Low-Rank Approximated Quantization), a simple, data-free calibration approach that optimizes quantization error compensation. By overcoming the need for high-precision branches, LoRaQ enables the first fully sub-16 bit pipeline, allowing the low-rank branch itself to be quantized. We demonstrate that, at equal memory overhead, LoRaQ outperforms the state-of-the-art methods in their native implementations on Pixart-

Σ

and SANA. We also analyze mixed-precision configurations, showing that setups such as W8A8, W6A6, and W4A8 for the low-rank branch, alongside a W4 main layer, yield superior results while maintaining a fully quantized architecture compatible with modern mixed-precision hardware.

Yann Bouquet, Alireza Khodamoradi, Sophie Yáng Shen +2

Research and Advancement Development Team, Advanced Micro Devices, Inc, USA · Computer Vision Laboratory, Ecole Polytechnique F´ed´erale de Lausanne, Lausanne, Switzerland.

Mixed-Precision Quantization Diffusion Transformer Diffusion Model Quantization 4-Bit Quantization Low-Rank Approximation Post-Training Quantization+1

Apr 20, 2026cs.CV

DuQuant++: Fine-grained Rotation Enhances Microscaling FP4 Quantization

The MXFP4 microscaling format, which partitions tensors into blocks of 32 elements sharing an E8M0 scaling factor, has emerged as a promising substrate for efficient LLM inference, backed by native hardware support on NVIDIA Blackwell Tensor Cores. However, activation outliers pose a unique challenge under this format: a single outlier inflates the shared block scale, compressing the effective dynamic range of the remaining elements and causing significant quantization error. Existing rotation-based remedies, including randomized Hadamard and learnable rotations, are data-agnostic and therefore unable to specifically target the channels where outliers concentrate. We propose DuQuant++, which adapts the outlier-aware fine-grained rotation of DuQuant to the MXFP4 format by aligning the rotation block size with the microscaling group size (B{=}32). Because each MXFP4 group possesses an independent scaling factor, the cross-block variance issue that necessitates dual rotations and a zigzag permutation in the original DuQuant becomes irrelevant, enabling DuQuant++ to replace the entire pipeline with a single outlier-aware rotation, which halves the online rotation cost while simultaneously smoothing the weight distribution. Extensive experiments on the LLaMA-3 family under MXFP4 W4A4 quantization show that DuQuant++ consistently achieves state-of-the-art performance. Our code is available at https://github.com/Hsu1023/DuQuant-v2.

Haokun Lin, Xinle Jia, Haobo Xu +7

CASIA · CityU · NJU +3

LLM Quantization 4-Bit Quantization Rotation-Based Quantization Activation Quantization Neural Network Quantization

Apr 19, 2026cs.LG

Evolutionary fine tuning of quantized convolution-based deep learning models

Deep learning models are the most efficient models in many machine learning tasks. The main disadvantage when using them in IoT, mobile devices, independent autonomous or real-time systems is their complexity and memory size. Therefore, much research has concentrated on compression techniques of deep learning architectures. One of the most popular technique is quantization. In most of the works, the quantization is done based on the nearest neighbour quantization technique. This work focuses on improving the quantization efficiency in pretrained and quantized models. This approach has the potential to improve the final accuracy of quantized models. The main postulate of the work is that final quantization states of the network based on nearest neighbour rounding does not guarantee optimal accuracy. In the presented work, the evolution strategy is used as an optimization approach. The evolution in each iteration changes the values of the small percentage of weights. It shifts theirs values to different quantization states. The work shows that proposed evolution with an appropriate set of operators and parameters can fast improve the accuracy of the quantized models. The results are presented for popular architectures such as VGG and Resnet for image classification and detection. Additionally, simulations were carried out for the autoencoder architecture.

Marcin Pietroń

AGH University Kraków, Poland

Fine-Tuning Convolutional Neural Networks Post-Training Quantization Neural Network Quantization

Apr 16, 2026cs.LG

When Flat Minima Fail: Characterizing INT4 Quantization Collapse After FP32 Convergence

Post-training quantization (PTQ) assumes that a well-converged model is a quantization-ready model. We show this assumption fails in a structured, measurable, and previously uncharacterized way. Using a calibration-free per-group INT4 probe applied to all 154 publicly available Pythia-160m training checkpoints, we identify a three-phase divergence structure: a rapid-learning phase where both FP32 perplexity and quantization robustness improve together, a meta-stable plateau lasting roughly 70,000 steps where FP32 perplexity stagnates but INT4 gap remains bounded, and an explosive divergence phase where the INT4 gap compounds from 11% to 517% while FP32 perplexity barely moves. Critically, this divergence begins not when the learning rate starts decaying, but precisely when FP32 perplexity converges a finer-grained onset predictor that implies post-convergence weight updates, rather than decay magnitude alone, are the proximate cause. We further show that INT8 quantization is entirely immune throughout all three phases, constraining the mechanism to the coarseness of the 16-level INT4 grid specifically, and rule out weight outlier accumulation as the mechanism via direct kurtosis measurement. Finally, we conduct a controlled fork experiment from the pre-divergence checkpoint comparing three learning rate schedules (cosine continuation, SGDR warm restarts, and our proposed Oscillatory Lock-In) across nine independent runs. SGDR uniformly accelerates divergence (0/9 pairwise wins against cosine), while OLI's settled cool phases reduce the INT4 gap by 2.2 percentage points on average (t = -5.46, p < 0.0001), demonstrating that schedule amplitude calibration, not oscillation alone, determines whether perturbation helps or hurts. Our code, probe implementation, and all 154-checkpoint audit results are released publicly.

Marcus Armstrong

Department of Computer Science University of Houston Houston, TX 77004

LLM Quantization 4-Bit Quantization Post-Training Quantization Neural Network Quantization

Apr 16, 2026cs.AI

A Comparative Study of CNN Optimization Methods for Edge AI: Exploring the Role of Early Exits

Deploying deep neural networks on edge devices requires balancing accuracy, latency, and resource constraints under realistic execution conditions. To fit models within these constraints, two broad strategies have emerged: static compression techniques such as pruning and quantization, which permanently reduce model size, and dynamic approaches such as early-exit mechanisms, which adapt computational cost at runtime. While both families are widely studied in isolation, they are rarely compared under identical conditions on physical hardware. This paper presents a unified deployment-oriented comparison of static compression and dynamic early-exit mechanisms, evaluated on real edge devices using ONNX based inference pipelines. Our results show that static and dynamic techniques offer fundamentally different trade-offs for edge deployment. While pruning and quantization deliver consistent memory footprint reduction, early-exit mechanisms enable input-adaptive computation savings that static methods cannot match. Their combination proves highly effective, simultaneously reducing inference latency and memory usage with minimal accuracy loss, expanding what is achievable at the edge.

Nekane Fernandez, Ivan Valdes, Steven Van Vaerenbergh +2

Nekane Fernandez, Ivan Valdes, Idoia de la Iglesia and Julen Arratibel are with the Dept. of Connected and Distributed Intelligence, Ikerlan Technology Research Centre, Arrasate, Spain · Nekane Fernandez and Steven Van Vaerenbergh are with the Dept. of Mathematics, Statistics and Computation, Universidad de Cantabria, Santander, Spain

Efficient Inference Edge Inference Neural Network Quantization Neural Network Compression Early-Exit Neural Networks Neural Network Pruning

Apr 15, 2026cs.LG

Robust Ultra Low-Bit Post-Training Quantization via Stable Diagonal Curvature Estimate

Large Language Models (LLMs) are widely used across many domains, but their scale makes deployment challenging. Post-Training Quantization (PTQ) reduces memory footprint without retraining by leveraging a small calibration set. Recent Hessian-based PTQ methods compensate quantization error via cross-channel dependencies, but such approaches degrade at low bit-widths due to noisy curvature estimates from limited calibration data. We propose DASH-Q, a robust PTQ framework using diagonal Hessian approximation and iterative weighted least squares. By discarding noise-prone dependencies, DASH-Q filters sampling noise while prioritizing the preservation of salient feature power. We outperform other PTQ baselines in ultra low-bit regime, improving zero-shot accuracy by 7.01% on average and up to 14.01% over the strongest baselines across five baseline LLM models, while showing robust and stable performance with very small calibration data.

Jaemin Kim, Sungkyun Kim, Junyeol Lee +1

Seoul National University · Hanyang University

LLM Quantization Language Model Calibration Post-Training Quantization Low-Bit Quantization Neural Network Quantization

Mar 24, 2026cs.LG

From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips

The deployment of deep neural networks (DNNs) in safety-critical edge environments necessitates robustness against hardware-induced bit-flip errors. While empirical studies indicate that reducing numerical precision can improve fault tolerance, the theoretical basis of this phenomenon remains underexplored. In this work, we study resilience as a structural property of neural architectures rather than solely as a property of a dataset-specific trained solution. By deriving the expected squared error (MSE) under independent parameter bit flips across multiple numerical formats and layer primitives, we show that lower precision, higher sparsity, bounded activations, and shallow depth are consistently favored under this corruption model. We then argue that logic and lookup-based neural networks realize the joint limit of these design trends. Through ablation studies on the MLPerf Tiny benchmark suite, we show that the observed empirical trends are consistent with the theoretical predictions, and that LUT-based models remain highly stable in corruption regimes where standard floating-point models fail sharply. Furthermore, we identify a novel even-layer recovery effect unique to logic-based architectures and analyze the structural conditions under which it emerges. Overall, our results suggest that shifting from continuous arithmetic weights to discrete Boolean lookups can provide a favorable accuracy-resilience trade-off for hardware fault tolerance.

Alan T. L. Bacellar, Sathvik Chemudupati, Shashank Nag +4

The University of Texas at Austin · Federal University of Rio de Janeiro · Instituto de Telecomunicações, Porto, Portugal

Neural Network Robustness Neural Network Quantization

Mar 18, 2026cs.CV

Q-Drift: Quantization-Aware Drift Correction for Diffusion Model Sampling

Post-training quantization (PTQ) is a practical path to deploy large diffusion models, but quantization noise can accumulate over the denoising trajectory and degrade generation quality. We propose Q-Drift, a sampler-side correction that aims to preserve the intended sampling marginals through a deterministic drift adjustment motivated by generalized marginal-preserving SDEs. Q-Drift uses the calibrated conditional residual variance of quantization error to determine a correction factor at each step. Our SDXL study shows that calibration with as few as 10 paired full-precision/quantized runs remains effective. The resulting sampler correction is plug-and-play with common samplers, diffusion models, and PTQ methods, while incurring negligible overhead at inference. Across six diverse text-to-image models (spanning DiT and U-Net), three samplers (Euler, flow-matching, DPM-Solver++), and two PTQ methods (SVDQuant, MixDQ), Q-Drift improves FID over the corresponding quantized baseline in all seven settings of our main evaluation, with up to 4.79 FID reduction on PixArt-Sigma (SVDQuant W3A4), while preserving CLIP scores. Code is available at https://github.com/sooyoung-ryu/Q-Drift.

Sooyoung Ryu, Mathieu Salzmann, Saqib Javed

Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea · School of Computer and Communication Sciences, EPFL, Lausanne, Switzerland · Meta Reality Labs, Redmond, USA

Diffusion Model Quantization Diffusion Model Sampling Post-Training Quantization Neural Network Quantization T2I Diffusion Models

Mar 9, 2026cs.LG

DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models

Vision-language-action (VLA) models achieve favorable task performance, yet runtime errors in closed-loop execution evolve with alternating updates of actions and observations. Existing VLA quantization methods mainly trade off inference speed and model performance while rarely investigating how quantization alters runtime errors. By comparing error distributions between full-precision and quantized models, we identify distinct evolutionary patterns for the two types of errors: quantization enlarges the variance of translation error distributions and increases their dispersion, whereas the distribution center of rotation errors gradually shifts across execution steps, demonstrating cumulative drift. Motivated by this observation, we rethink the optimal quantization strategy for VLA models and propose \textit{DyQ-VLA}, a runtime-error-aware quantization framework, which dynamically selects activation precision according to execution steps and tracks as well as compensates rotation errors via accumulated quantization residuals. Corresponding operators and runtime adaptation strategies are devised within the framework to enable dynamic-precision execution. Experiments show that \textit{DyQ-VLA} achieves a 1.88 to 1.93 inference speedups while maintaining comparable or higher average task success rates. Moreover, it reduces mean execution steps by 17.7% to 19.8%. Our code is here: https://anonymous.4open.science/r/DyQ-VLA-7F51/.

Zihao Zheng, Hangyu Cao, Chibang Tao +9

School of Computer Science, Peking University, Beijing, China. · School of Software Engineering, South China University of Technology, Guangzhou, China. · School of Artificial Intelligence, Beijing Normal University, Beijing, China. +1

VLM Quantization Efficient VLA Model Inference Efficient VLA Models Activation Quantization Vision-Language-Action Models Neural Network Quantization

Mar 4, 2026cs.LG

Dissecting Quantization Error: A Concentration-Alignment Perspective

Quantization can drastically increase the efficiency of large language and vision models, but typically incurs an accuracy drop. Recently, function-preserving transforms (e.g. rotations, Hadamard transform, channel-wise scaling) have been successfully applied to reduce post-training quantization error, yet a principled explanation remains elusive. We analyze linear-layer quantization via the signal-to-quantization-noise ratio (SQNR), showing that for uniform integer quantization at a fixed bit width, SQNR decomposes into (i) the concentration of weights and activations (capturing spread and outliers), and (ii) the alignment of their dominant variation directions. This reveals an actionable insight: beyond concentration - the focus of most prior transforms (e.g. rotations or Hadamard) - improving alignment between weight and activation can further reduce quantization error. Motivated by this, we introduce block Concentration-Alignment Transforms (CAT), a lightweight linear transformation that uses a covariance estimate from a small calibration set to jointly improve concentration and alignment, approximately maximizing SQNR. Experiments across several LLMs show that CAT consistently matches or outperforms prior transform-based quantization methods at 4-bit precision, confirming the insights gained in our framework.

Marco Federici, Boris van Breugel, Paul Whatmough +1

Qualcomm AI Research

LLM Quantization 4-Bit Quantization Post-Training Quantization Neural Network Quantization

Feb 26, 2026cs.AR

Bitwise Systolic Array Architecture for Runtime-Reconfigurable Multi-precision Quantized Multiplication on Hardware Accelerators

Neural network accelerators have been widely applied to edge devices for complex tasks like object tracking, image recognition, etc. Previous works have explored the quantization technologies in related lightweight accelerator designs to reduce hardware resource consumption. However, low precision leads to high accuracy loss in inference. Therefore, mixed-precision quantization becomes an alternative solution by applying different precision in different layers to trade off resource consumption and accuracy. Because regular designs for multiplication on hardware cannot support the precision reconfiguration for a multi-precision Quantized Neural Network (QNN) model in runtime, we propose a runtime reconfigurable multi-precision multi-channel bitwise systolic array design for QNN accelerators. We have implemented and evaluated our work on the Ultra96 FPGA platform. Results show that our work can achieve 1.3185 to 3.5671 times speedup in inferring mixed-precision models and has less critical path delay, supporting a higher clock frequency (250MHz).

Yuhao Liu, Salim Ullah, Akash Kumar

Dresden University of Technology, Germany · Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI Dresden/Leipzig), Germany · Ruhr University Bochum, Germany

Mixed-Precision Quantization FPGA-Based Neural Network Acceleration Neural Network Quantization

Feb 9, 2026cs.LG

DynamiQ: Accelerating Gradient Synchronization using Compressed Multi-hop All-reduce

Multi-hop all-reduce is the de facto backbone of large model training. As the training scale increases, the network often becomes a bottleneck, motivating the reduction of the volume of transmitted data. Accordingly, recent systems have demonstrated significant acceleration of the training process using gradient quantization. However, these systems are not optimized for multi-hop aggregation, where entries are partially summed multiple times along their aggregation topology. We present DynamiQ, a quantization framework that bridges the gap between quantization best practices and multi-hop aggregation. DynamiQ introduces novel techniques to better represent partial sums, codesigned with a decompress accumulate recompress fused kernel to facilitate fast execution. We extend PyTorch DDP to support DynamiQ over NCCL P2P, and across different LLMs, tasks, and scales, we demonstrate consistent improvement of up to 34.2% over the best among state-of-the-art methods such as Omni-Reduce, THC, and emerging standards such as MXFP4, MXFP6, and MXFP8. Further, DynamiQ is the only evaluated method that consistently reaches near-baseline accuracy (e.g., 99.9% of the BF16 baseline) and does so while significantly accelerating the training.

Wenchen Han, Shay Vargaftik, Michael Mitzenmacher +1

University College London · VMware Research by Broadcom · Harvard University +1

Communication-Efficient Distributed Training High-Performance Computing Gradient Compression Neural Network Quantization

Feb 5, 2026cs.CL

Investigating Social Bias Changes in Quantized Language Models

Post-training quantization reduces the memory needed to run large language models but alters their social biases in ways that aggregate metrics fail to capture. We present the first large-scale study of 50 quantized models evaluated on PostTrainingBiasBench, a unified benchmark of 13 closed- and open-ended bias datasets. We identify a phenomenon we term quantization-induced bias flipping, in which quantization causes models to change responses from biased to unbiased and vice versa, up to 21% of the time, despite no change in aggregate bias scores. These flips are strongly associated with model uncertainty, where the responses with high uncertainty are 3-11x more likely to change than the confident ones. Quantization strength amplifies this effect, with 4-bit quantized models exhibiting 4-6x more behavioral changes than 8-bit quantized models. Critically, these changes create asymmetric impacts across demographic groups, where bias can worsen by up to 18.6% for some groups while improving by 14.1% for others, yielding misleadingly neutral aggregate outcomes. Larger models show no consistent robustness advantage, and group-specific shifts vary unpredictably across model families. Our findings demonstrate that compression fundamentally alters bias patterns, requiring crucial post-quantization evaluation and interventions to ensure reliability in practice.

Stanley Z. Hua, Sanae Lotfi, Irene Y. Chen

UC Berkeley & UCSF · Meta Superintelligence Labs

LLM Quantization Social Bias in Language Models Language Model Bias Evaluation Linguistic Bias in Language Models Post-Training Quantization Neural Network Quantization

Feb 3, 2026cs.LG

MatGPTQ: Efficient and Accurate Inference over Nested Quantized Models

Matryoshka Quantization (MatQuant), Any-Precision-LLM (AP) and AnyBCQ (AB) are recent quantization approaches showing that a single integer-quantized model can be served across multiple precisions. In this paradigm, lower-precision models are extracted from a higher-precision model by simply reading fewer bits of the weights. This enables a single checkpoint to cover a wide range of memory and latency budgets, but makes both quantization and efficient execution substantially harder. Existing methods rely on expensive quantization-aware training (QAT) or gradient-based post-training quantization (PTQ) rather than fast one-shot PTQ, and offer limited system support: dedicated kernels are either missing or restricted to single- or small-batch decoding. We address these limitations with Post-Training Matryoshka Quantization (MatGPTQ), an end-to-end pipeline for nested-model quantization and inference. MatGPTQ casts Matryoshka quantization as multi-precision error compensation, producing a single "sliceable" parent model jointly optimized for multiple target precisions in one pass over a small calibration set. We further refine the MatQuant representation so that an

r

-bit model reads exactly

r

bits, and introduce the first dedicated inference kernels for this format, supporting batch sizes beyond one and integrated into vLLM. Across standard LLMs and benchmarks, MatGPTQ outperforms MatQuant while remaining competitive with AP and AB at the smallest checkpoint size, and our kernels achieve end-to-end speedups of up to 3.5

\times

over BF16 at the low-bit regime. Overall, MatGPTQ makes nested quantized models practical to serve from a single, compact checkpoint. Code is available at https://github.com/IST-DASLab/MatGPTQ.

Maximilian Kleinegger, Elvir Crnčević, Dan Alistarh

1Vienna University of Technology, Vienna, Austria · Institute of Science & Technology Austria (ISTA), Vienna, Austria · 3Red Hat AI, Boston, USA

LLM Quantization LLM Inference Acceleration Post-Training Quantization Low-Bit Quantization Neural Network Quantization

Jan 17, 2026cs.CL

Preserving Fairness and Safety in Quantized LLMs Through Critical Weight Protection

Quantization is widely adopted to reduce the computational cost of large language models (LLMs); however, its implications for fairness and safety, particularly in dynamic quantization and multilingual contexts, remain underexplored. In this work, we conduct a systematic study of how static and dynamic quantization methods impact fairness and safety across benchmarks measuring intrinsic and extrinsic bias and safety alignment. For fairness, we evaluate English, French, Dutch, Spanish, and Turkish; for safety, we focus on English, Korean, and Arabic. Our findings reveal that quantization consistently degrades fairness and safety, with dynamic methods demonstrating greater stability than static ones. Moreover, fairness degradation varies across languages, while safety deterioration is especially pronounced in non-English settings. To address these risks, we introduce Critical Weight Protection, a novel technique that identifies and preserves fairness- and safety-critical weights during quantization. This approach effectively mitigates bias and safety deterioration without costly retraining or alignment, maintaining trustworthiness while retaining efficiency.

Muhammad Alif Al Hakim, Alfan Farizki Wicaksono, Fajri Koto

Faculty of Computer Science, Universitas Indonesia · Mohamed bin Zayed University of Artificial Intelligence

LLM Quantization Multilingual Language Model Evaluation Language Model Safety Evaluation Language Model Bias Evaluation Neural Network Quantization

Jan 12, 2026cs.LG

ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs

The emergence of fine-grained numerical formats like NVFP4 presents new opportunities for efficient Large Language Model (LLM) inference. However, it is difficult to adapt existing Post-Training Quantization (PTQ) strategies to these formats: rotation-based methods compromise fine-grained block isolation; smoothing techniques struggle with significant 4-bit quantization errors; and mixed-precision approaches often conflict with hardware constraints on unified-precision computation. To address these challenges, we propose ARCQuant, a framework that boosts NVFP4 performance via Augmented Residual Channels. Distinct from methods that compromise block isolation or hardware uniformity, ARCQuant maintains a strictly unified NVFP4 format by augmenting the activation matrix with quantized residual channels. This design integrates the error compensation process directly into the matrix reduction dimension, enabling the use of standard, highly optimized GEMM kernels with minimal overhead. Theoretical analysis confirms that the worst-case error bound of our dual-stage NVFP4 quantization is comparable to that of standard 8-bit formats such as MXFP8. Extensive experiments on LLaMA and Qwen models demonstrate that ARCQuant achieves state-of-the-art accuracy, comparable to full-precision baselines in perplexity and downstream tasks. Furthermore, deployment on RTX 5090 and RTX PRO 6000 GPUs confirms practical benefits, achieving up to 3x speedup over FP16. Our code is available at https://github.com/actypedef/ARCQuant.

Haoqian Meng, Yilun Luo, Yafei Zhao +3

School of Computer Science and Technology, Tianjin University

LLM Quantization 4-Bit Quantization LLM Inference Acceleration Post-Training Quantization Neural Network Quantization