Mixed-Precision Quantization

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 40

All topics

From Attention Sensitivity to Layer Role: Revisiting Mixed-Precision Quantization of Transformers
Sep 28, 2026Nafiseh HosseinpourFardi, Negar Alihadi, Mahmoudreza Babaei +2Post-Training Quantization Mixed-Precision Quantization
Sharif University of Technology, Tehran, Iran · GISMA University of Applied Sciences, Potsdam, Germany · BRAINS, Brandenburg Research Center for Applied Intelligent Systems, Potsdam, Germany +3
Quantization Error Is Spectrally Flat: A Single Random Probe Is a Calibrated, Data-Free Sensitivity Estimator, with Application to Budget-Targeted Mixed-Precision Quantization
Sep 27, 2026I Kennedy, T KennedyMixed-Precision Quantization Mean Squared Error
baa.ai Auckland, New Zealand
RAMP: Robust Adaptive Mixed-Precision Quantization for Edge CPU Vision Models
Sep 23, 2026David Población-Criado, Dario Garcia-Gasulla, Eduardo QuinonesMixed-Precision Quantization Neural Network Inference
Barcelona Supercomputing Center (BSC) · Universitat Politècnica de Catalunya - BarcelonaTech (UPC)
Beyond Scalar Sensitivity: Activation-Aware Mixed-Precision LLM Quantization with Cross-Layer Refinement
Sep 22, 2026Akihiro Yoshida, Yuma IchikawaMixed-Precision Quantization Large Language Model Quantization
Fujitsu Limited, Institute of Science Tokyo · Fujitsu Limited, RIKEN Center for AIP
Task-Aware QUBO Allocation for Mixed-Precision Quantization
Sep 4, 2026Osama Orabi, Artur Zagitov, Hadi Salloum +2Mixed-Precision Quantization Quadratic Unconstrained Binary Optimization
Laboratory of Quantum Computing, Innopolis University, 420500 Innopolis, Russia · Q Deep, Laboratory of Quantum Computing, 420502 Innopolis, Russia · Moscow Independent Research Institute of Artificial Intelligence (MIRAI), 117218 Moscow, Russia +2
Q-Strata: Hierarchical Bit Allocation for Mixed-Precision Quantization of Mixture-of-Experts LLMs
Aug 31, 2026Deokjae Lee, Sihun Chu, Hyun Oh SongMixed-Precision Quantization Mixture-Of-Experts Large Language Models
Department of Computer Science and Engineering, Seoul National University · Neural Processing Research Center · 3Neural Processing Research Center +2
FAMPWQ: Fisher Information-based Adaptive Mixed Precision Weight Quantization for Effective LLM Inference
Aug 24, 2026Gongwei Lee, Ji Liu, Juncheng Jia +1Mixed-Precision Quantization LLM Inference Optimization
School of Computer Science and Technology, Soochow University, Suzhou, China · Hithink Research, Hangzhou, China · Electronic Engineering, Tsinghua University, Beijing, China
MiCoPro: End-to-End Mixed Precision HW/SW Co-design with HW-aware Proxy Model
Aug 7, 2026Zijun Jiang, Yangdi LyuMixed-Precision Quantization Artificial Intelligence Systems
Microelectronics Thrust, the Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, China
APQF: Agentic Profiling-Guided Structured Pruning and Mixed-Precision Quantization with Adaptive Fine-Tuning
Aug 6, 2026Sadegh Jafari, Mohiuddin Bilwal, Fan Zhou +2Mixed-Precision Quantization Structured Pruning
Department of Computer Science Iowa State University Ames, IA, USA · Department of Agricultural and Biosystems Engineering Iowa State University Ames, IA, USA
NANQ: Noise-Floor-Aware Mixed-Precision Non-Uniform Quantization for Analog Compute-in-Memory
Aug 3, 2026Yizhe Chen, Wenshuai Yao, Saiya Wang +6In-Memory Computing Mixed-Precision Quantization
School of Integrated Circuit Science and Engineering, Beihang University, Beijing, China · School of Integrated Circuits, Peking University, Beijing, China · Department of Electrical and Computer Engineering, The University of Hong Kong, Hong Kong SAR, China
MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformers
Jul 30, 2026Md. Mehrab Hossain Opi, Robiul Islam Ryad, Md. Umar FarukMixed-Precision Quantization Self-Supervised Vision Transformers
Department of Computer Science and Engineering Khulna University of Engineering & Technology (KUET) Khulna 9203, Bangladesh
MixQuant: Adaptive Mixed-Precision Quantization for Large Language Models
Jul 25, 2026Ashitabh Misra, Madhav Agrawal, Arham Jain +1Mixed-Precision Quantization Mix
University of Illinois at Urbana-Champaign
MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference
Jul 20, 2026Simla Burcu Harma, Danila Mishin, Zhengyuan Su +7Large Language Model Quantization Mixed-Precision Quantization
EcoCloud, EPFL · Tsinghua University · MangoBoost Inc. +2
Saturation Makes Quantization Error Additive: A Coverage Model with a Certificate
Jul 14, 2026Joshua HillMixed-Precision Quantization Saturation
Baseten Labs, Inc. · David R. Cheriton School of Computer Science, University of Waterloo
M+Adam: Low-Precision Training via Additive-Multiplicative Optimization
Jul 12, 2026Xiaoyuan Liang, Sebastian Loeschcke, Mads Toftrup +1Mixed-Precision Quantization Adam
California Institute of Technology · University of Copenhagen · Aarhus University
Beyond Activation Alignment:The Alignment-Diversity Tradeoff in Task-Aware LLM Quantization
Jul 1, 2026Fei Wang, Chao Xue, Taoran Liu +3Large Language Model Quantization Mixed-Precision Quantization
South China University of Technology · Ocean University of China · Shenzhen Campus of Sun Yat-sen University +1
Minimizing Quantized Semantic Age of Information (QSAoI) in Foundation Model-Based Semantic Communications
Jun 30, 2026Huanyu Zhang, Yulin Hu, Xiaopeng Yuan +2Semantic Communications Source-Channel Coding
INDA Chair, RWTH Aachen University, Germany · School of Electronic Information, Wuhan University, China · Department of Digital Communication Systems, Ruhr University Bochum, Germany
SEADA: An efficient methodology for optimizing mixed-precision DNNs on multi-precision spatial architectures
Jun 26, 2026Leandro Fiorin, Marco Ronzani, Cristina SilvanoMixed-Precision Quantization Efficient Planning
Indipendent Researcher Groningen, The Netherlands · Dipartimento di Elettronica e Informazione, Politecnico di Milano. Milano, Italy
Efficient Network Inference via Hardware-Aware Architecture Search, Model Pruning & Quantization
Jun 22, 2026Lucas Heublein, Mark Deutel, Axel Plinge +1Neural Network Inference Hardware-Aware
Fraunhofer Institute for Integrated Circuits IIS, 90411 Nürnberg, Germany
Hybrid Compression: Integrating Pruning and Quantization for Optimized Neural Networks
Jun 22, 2026Minh-Loi Nguyen, Long-Bao Nguyen, Van-Hieu Huynh +2Compressed Model Neural Network Inference
University of Science, Ho Chi Minh city, Vietnam · Vietnam National University, Ho Chi Minh city, Vietnam
Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models
Jun 17, 2026Navin Ranjan, Andreas SavakisMixed-Precision Quantization Post-Training Quantization
Rochester Institute of Technology Rochester, New York 14623, USA
Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression
Jun 16, 2026Yifu Ding, Jiacheng Wang, Ge Yang +4Mixture-Of-Expert Inference Mixture-Of-Experts
State Key Laboratory of Complex & Critical Software Environment, Beihang University · School of Computer Science and Engineering, Beihang University · Nanyang Technological University +1
DynamicPTQ: Mitigating Activation Quantization Collapse via Residual-Stream Dynamics
Jun 10, 2026Zimo Zhao, Maolin Wang, Bowen Yu +3Post-Training Quantization Mixed-Precision Quantization
City University of Hong Kong · Hong Kong, China · Zhejiang University of Technology +1
STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control
Jun 7, 2026Priyansh Bhatnagar, Ashkan Moradifirouzabadi, Se-Hyun Yang +3Key-Value Cache Compression Key-Value Cache
University of California San Diego, San Diego, CA, USA · Dnotitia Inc., Seoul, Republic of Korea · Hanyang University, Seoul, Republic of Korea
Joint Structural Pruning and Mixed-Precision Quantization for LLM Compression
Jun 5, 2026Hoang-Loc La, Truong-Thanh Le, Amir Taherkordi +1Mixed-Precision Quantization Large Language Model Compression
UiT The Arctic University of Norway · University of Oslo, Norway
AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization
Jun 3, 2026Wanqi Yang, Yuexiao Ma, Alexander Conzelmann +4Mixed-Precision Quantization
Max Planck Institute for Intelligent Systems · ELLIS Institute Tübingen · Tübingen AI Center +5
dMX: Differentiable Mixed-Precision Assignment for Low-Precision Floating-Point Formats
Jun 2, 2026Giuseppe Franco, Ian Colbert, Pablo Monteagudo-Lago +2Mixed-Precision Quantization Full-Precision Performance
AMD
Dense2MoE: Pushing the Pareto Frontier of On-Device LLMs via Unified Pruning and Upcycling
May 26, 2026Fengfa Li, Hongjin Ji, Yifeng Ding +2Mixture-Of-Expert Inference Mixed-Precision Quantization
Li Auto · The Chinese University of Hong Kong, Shenzhen
Scale When Needed: Adaptive Neuron-level Mixed Precision Quantization Aware Training
May 24, 2026Ayush K. Varshney, Konstantinos Vandikas, Šarūnas Girdzijauskas +2Mixed-Precision Quantization Quantization-Aware Training
Ericsson Research, Ericsson AB, Stockholm, Sweden · KTH Royal Institute of Technology, Stockholm, Sweden · RISE Research Institutes of Sweden, Stockholm, Sweden
MX-SAFE: Versatile Inference- and Training-Proof Microscaling Format with On-the-Fly Exponent and Mantissa Bit Allocation
May 23, 2026Dahoon Park, Jahyun Koo, Sangwoo Hwang +1Mixed-Precision Quantization Neural Network Inference
† School of Electrical Engineering, Korea University, South Korea · ‡ Department of Electrical Engineering and Computer Science, DGIST, South Korea
GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs
May 21, 2026Jianing Deng, Song Wang, Dongwei Wang +4Mixed-Precision Quantization Mixture-Of-Experts Large Language Models
University of Pittsburgh · University of Central Florida · University of Arizona +1
GAMMA: Global Bit Allocation for Mixed-Precision Models under Arbitrary Budgets
May 18, 2026Zhangyang Yao, Haiyan Zhao, Haoyu Wang +3Mixed-Precision Quantization Token Budget Allocation
Beihang University · Tsinghua University · ByteDance Inc
Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection
May 4, 2026Joydeep ChandraSpeaker Mixed-Precision Quantization
Department of Computer Science & Technology, Tsinghua University, Beijing, China.
MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching
Apr 29, 2026Shuzhao Xie, Junchen Ge, Weixiang Zhang +103D Gaussian Large-Scale 3D Editing Dataset
Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · The Hong Kong University of Science and Technology, Hong Kong SAR, China · Harbin Institute of Technology, Shenzhen, China +6
FED-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices
Apr 28, 2026Changyu Li, Shuanghong Huang, Jiashen Liu +5Large Language Model Quantization Fedavg
School of Computing and Information Technology, Great Bay University, Dongguan, China · Beijing Institute of Technology, Beijing, China · University of Warwick, Coventry, U.K. +3
Focus Session: Hardware and Software Techniques for Accelerating Multimodal Foundation Models
Apr 23, 2026Muhammad Shafique, Abdul Basit, Muhammad Abdullah Hanif +3Multimodal Foundation Model Inference Workloads
eBRAIN Lab, New York University (NYU) Abu Dhabi, Abu Dhabi, United Arab Emirates
Bitwise Systolic Array Architecture for Runtime-Reconfigurable Multi-precision Quantized Multiplication on Hardware Accelerators
Feb 26, 2026Yuhao Liu, Salim Ullah, Akash KumarMixed-Precision Quantization Field-Programmable Gate Arrays
Dresden University of Technology, Germany · Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI Dresden/Leipzig), Germany · Ruhr University Bochum, Germany
Towards Training-free Automatic Proxy Discovery via Large Language Models for Mixed Precision Quantization
Dec 8, 2025Haidong Kang, Jun Du, Guo YuMixed-Precision Quantization Evolutionary Search
School of Computer and Communication Engineering, Northeastern University · School of Software Engineering, Beijing Jiaotong University
Squeeze10-LLM: Squeezing LLMs' Weights by 10 Times via a Staged Mixed-Precision Quantization Method
Jul 24, 2025Qingcheng Zhu, Yangyang Ren, Linlin Yang +6Large Language Model Quantization Mixed-Precision Quantization
Beihang University · Communication University of China · Beijing Jiaotong University
Dynamic Expert Quantization for Scalable Mixture-of-Experts Inference
Date pendingKexin Chu, Dawei Xiang, Zixu Shen +3Mixture-Of-Expert Inference Mixed-Precision Quantization
University of Connecticut · University of California, Santa Cruz · Independent Researcher

Sep 28, 2026, cs.LGJ/K move · Enter open · S save

From Attention Sensitivity to Layer Role: Revisiting Mixed-Precision Quantization of Transformers

Nafiseh HosseinpourFardi, Negar Alihadi, Mahmoudreza Babaei, Milad Hosseini+1

Sharif University of Technology, Tehran, Iran · GISMA University of Applied Sciences, Potsdam, Germany · BRAINS, Brandenburg Research Center for Applied Intelligent Systems, Potsdam, Germany+3

Post-Training Quantization Mixed-Precision Quantization Dynamic Attention Transformer Architectures Role

Open paper AskPDF arXiv

Most post-training quantization pipelines fit each weight matrix to its pretrained counterpart, one matrix at a time. Whether that proxy tracks what an attention block actually computes, or how errors in the Q, K and V projections compound inside the softmax, is rarely checked. We write the objective on the attention output instead, over all three projections at once, and reuse it throughout the pipeline. JAB defines one scalar loss over the joint Q, K, V weights of a block, evaluated against the block's real causally-masked attention output, and uses it twice: to fit the quantized weights (GPTQ warm start, then STE with learnable scales), and to score the block for a multiple-choice knapsack allocation. On attention-only quantization of Mistral-7B this works. At 3 bits JAB recovers 77-90% of the gap between uniform GPTQ and full precision, and its sensitivity estimate tracks an oracle costing 73 forward passes to within a fraction of a point. It stops working once MLP layers enter the allocation. A role-aware offset rule needing no sensitivity estimate at all beats JAB on GPT-2's MLP and on the full Mistral-7B model: with a 3-bit floor it quantizes 96.4% of the weights to 4.5 bits per parameter at 6.933 perplexity, within 4.4% of full precision (6.643) at 3.56x compression, against 7.158 for JAB at the same budget. Which matrix a weight sits in matters more than any sensitivity estimate we computed. Two things came out sideways. Block-local reconstruction is an unreliable proxy for end-to-end perplexity: one run improved a block's own objective 4.6x while perplexity rose 32x, which is why every allocation here is validated end-to-end. And on attention-only quantization, fine-tuning moved weights farther from their pretrained values while pulling attention outputs closer, with net gains. Post-training seems to recover attention behavior, not weights.

Momentum

Related topics

Latest papers 40