Awesome-Model-Quantization

This repository contains low-bit quantization papers from 2020 to 2026.

Table of Contents

• Awesome-Model-Quantization
  • Table of Contents
  • Survey
  • Papers
    • 2026
    • 2025
    • 2024
    • 2023
    • 2022
    • 2021
    • 2020

Survey

• arXiv 2025 Low-bit Model Quantization for Deep Neural Networks: A Survey
• Claude Survey A Chinese model quantization survey from claude concerning ICLR 2026.

Papers

2026

• ICLR 2026 Channel-Aware Mixed-Precision Quantization for Efficient Long-Context Inference

• ICLR 2026 CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts

• ICLR 2026 QeRL: Beyond Efficiency - Quantization-enhanced Reinforcement Learning for LLMs [code]

• ICLR 2026 AutoQVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantization

• ICLR 2026 Achieving low-bit Muon through subspace preservation and grid quantization

• ICLR 2026 Shift-and-Sum Quantization for Visual Autoregressive Models

• ICLR 2026 Inlier-Centric Post-Training Quantization for Object Detection Models

• ICLR 2026 Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees

• ICLR 2026 BBQ: Boosting Quantization Entropy with Bell Box Quantization

• ICLR 2026 Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations [code]

• ICLR 2026 Learning under Quantization for High-Dimensional Linear Regression

• ICLR 2026 On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs

• ICLR 2026 Bridging the Gap Between Promise and Performance for FP4 Quantization [code]

• ICLR 2026 KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models [code]

• ICLR 2026 ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

• ICLR 2026 Post-Training Quantization for Video Matting [code]

• ICLR 2026 Tequila: Deadzone-free Ternary Quantization for Large Language Models [code]

• ICLR 2026 Q&C: When Quantization Meets Cache in Efficient Generation

• ICLR 2026 LogART: Pushing the Limit of Efficient Logarithmic Post-Training Quantization

• ICLR 2026 Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models [code]

• ICLR 2026 SliderQuant: Accurate Post-Training Quantization for LLMs

• ICLR 2026 AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs [code]

• ICLR 2026 UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs [code]

• ICLR 2026 The Lattice Geometry of Neural Network Quantization: A Short Equivalence Proof of GPTQ and Babai's algorithm

• ICLR 2026 DPQuant: Efficient and Private Model Training via Dynamic Quantization Scheduling

• ICLR 2026 Towards Quantization-Aware Training for Ultra-Low-Bit Reasoning LLMs

• ICLR 2026 A Convergence Analysis of Adaptive Optimizers under Floating-point Quantization

• ICLR 2026 Training Dynamics Impact Post-Training Quantization Robustness [code]

• ICLR 2026 SSDi8: Accurate and Efficient 8-bit Quantization for State Space Duality

• ICLR 2026 The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm

• ICLR 2026 PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models [code]

• ICLR 2026 Inlier-Centric Post-Training Quantization for Object Detection Models

• ICLR 2026 QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models [code]

• ICLR 2026 Gradient-Aligned Calibration for Post-Training Quantization of Diffusion Models

• ICLR 2026 SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization

• ICLR 2026 Compute-Optimal Quantization-Aware Training

• ICLR 2026 PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs [code]

• ICLR 2026 Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs [code]

• ICLR 2026 Beyond Outliers: A Study of Optimizers Under Quantization

• ICLR 2026 Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization

• ICLR 2026 MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models [code]

• ICLR 2026 TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation

• ICLR 2026 DVD-Quant: Data-free Video Diffusion Transformers Quantization [code]

• ICLR 2026 Beyond Uniformity: Sample and Frequency Meta Weighting for Post-Training Quantization of Diffusion Models

• ICLR 2026 Rethinking Residual Errors in Compensation-based LLM Quantization

• ICLR 2026 SPR²Q: Static Priority-based Rectifier Routing Quantization for Image Super-Resolution [code]

• ICLR 2026 STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization

• ICLR 2026 PT²-LLM: Post-Training Ternarization for Large Language Models [code]

• CVPR 2026 Quant Experts: Token-aware Adaptive Error Reconstruction with Mixture of Experts for Large Vision-Language Models Quantization

• CVPR 2026 Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients [code]

• CVPR 2026 MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models

• CVPR 2026 SegQuant: A Semantics-Aware and Generalizable Quantization Framework for Diffusion Models

• CVPR 2026 VLM-PTQ: Efficient Post-Training Quantization for Large Vision-Language Models

• CVPR 2026 Rethinking Asymmetric Quantization: Hidden Symmetry in Vision Model Weights

• CVPR 2026 Gradient Knows Best: Mixed-Precision Quantization via Gradient-Guided Bit Allocation for Super-Resolution

• CVPR 2026 DeltaQuant: 4-bit Video Diffusion Models with Spatiotemporal Delta Smoothing

• CVPR 2026 LS-ViT: Least-Squares Hessian Based Block Reconstruction for Low-Bit Post-Training Quantization of Vision Transformers

• CVPR 2026 QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models [code]

• CVPR 2026 TWEO: Transformers Without Extreme Outliers Enables FP8 Training And Quantization For Dummies

• CVPR 2026 S2D: Selective Spectral Decay for Quantization-Friendly Conditioning of Neural Activations

• CVPR 2026 Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration

• CVPR 2026 FraQAT: Quantization Aware Training with Fractional Bits

• CVPR 2026 Sampling-Aware Quantization for Diffusion Models

• CVPR 2026 D4C: Data-Free Quantization for Contrastive Language-Image Pre-Training Models [code]

• CVPR 2026 CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model

• CVPR 2026 QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer

• CVPR 2026 Modality-Aware Bit Allocation for Mixed-Precision Quantization of Vision-Language Models

• CVPR 2026 BinaryAttention: One-Bit QK-Attention for Vision and Diffusion Transformers [code]

• ICML 2026 LO-BCQ: Locally Optimal Block Clustered Quantization for 4-bit (W4A4) LLM Inference

• ICML 2026 ReQAT: Achieving Full-Precision Reasoning Accuracy with 4-bit Floating-Point Quantization-Aware Training

• ICML 2026 MixQuant: Pushing the Limits of Block Rotations in Post-Training Quantization

• ICML 2026 S-Quant: Rethinking Weight Quantization with Seed-Based Generation

• ICML 2026 BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models

• ICML 2026 No Retraining at Edge: Efficient Resource-Aware Mixed-Precision Quantization via Federated Supernet Learning

• ICML 2026 WaterSIC: Information-Theoretically (Near) Optimal Linear Layer Quantization

• ICML 2026 Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-Resolution

• ICML 2026 High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator

• ICML 2026 LiftQuant: Continuous Bit-Width Control for Pareto-Optimal LLM Deployment [code]

• ICML 2026 Block Rotation is All You Need for MXFP4 Quantization

• ICML 2026 AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning

• ICML 2026 1-Bit Wonder: Improving QAT Performance in the Low-Bit Regime through K-Means Quantization

• ICML 2026 Attn-QAT: 4-Bit Attention With Quantization-Aware Training

• ICML 2026 AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs

• ICML 2026 ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation

• ICML 2026 NanoQuant: Efficient Sub-1-bit Quantization of Large Language Models

• ICML 2026 Proteus: Lookup-Free Trellis-Coded Quantization by Lattice-Breaking Compute Codes for 2-Bit LLMs

• ICML 2026 WinQ: Accelerating Quantization-Aware Training of Large Language Models around Saddle Points [code]

• ICML 2026 Toward Safe Quantization-Aware Fine-tuning: Understanding and Mitigating Safety Alignment Degradation

• ICML 2026 Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs

• ICML 2026 GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache

• ICML 2026 ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression

• ICML 2026 STLA: Spatiotemporal Lookahead Alignment for Post-Training Quantization

• ICML 2026 FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models

• ICML 2026 TileQ: Efficient Low-Rank Quantization of Mixture-of-Experts with 2D Tiling

• ICML 2026 LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs

• ICML 2026 DLLMQuant: A Post-Training Quantization Framework Tailored for Diffusion-Based Large Language Models

• ICML 2026 SHARP-Q: Spectral Hessian Alignment and Rectification for Post-training Quantization

• ICML 2026 Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers

• ICML 2026 TWLA: Breaking the Barrier to W1.58A4 Post-Training Quantization for LLMs

• ICML 2026 FPTQuant: Function-Preserving Transforms for LLM Quantization

• ICML 2026 INT vs. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats [code]

• ICML 2026 Unveiling the Potential of Quantization with MXFP4: Strategies for Quantization Error Reduction

• ICML 2026 Scaling Law for Quantization-Aware Training

• ICML 2026 Error Propagation Mechanisms and Compensation Strategies for Quantized Diffusion Models

• ICML 2026 Condition Number Based Low-Bit Quantization for Image Super-Resolution [code]

• ICML 2026 ECO: Quantized Training without Full-Precision Master Weights

• ICML 2026 LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs

• ICML 2026 RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization [code]

• ICML 2026 QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs

• ICML 2026 TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM Quantization

• ICML 2026 NeUQI: Near-Optimal Uniform Quantization Parameter Initialization for Low-Bit LLMs

• ICML 2026 VEQ: Modality-Adaptive Quantization for MoE Vision-Language Models

• ICML 2026 Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization [code]

• ICML 2026 OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization

• ICML 2026 Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling [code]

• ICML 2026 SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights [code]

• ICML 2026 Dissecting Quantization Error: A Concentration-Alignment Perspective

• ICML 2026 Principled SVD-based Delta Compression via Quantization Error Minimization

• ICML 2026 PatternKV: Flattening KV Representation Expands Quantization Headroom

• ICML 2026 GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs

• ICML 2026 WUSH: Near-Optimal Adaptive Transforms for LLM Quantization [code]

• ICML 2026 LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization

• ICML 2026 LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-Resolution [code]

• ICML 2026 CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs

• ICML 2026 Precision-Induced Miscalibration: Understanding and Correcting Confidence Distortion in Quantized Neural Networks

• ICML 2026 CoCoQuant: Breaking the Bandwidth Wall via Co-Optimized Communication and Computation Quantization

• ICML 2026 RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference

• ICML 2026 ImpQuant: Fine-Grained Importance-Aware Quantization for Large Vision-Language Models

• ICML 2026 Absorbing Quantization Error by Deformable Noise Scheduler for Diffusion Models

• ICML 2026 PsumQuant: In-line Post-training Partial Sum Quantizer for Energy Efficient NPU Inference

• ICML 2026 Towards Sub-second Biological Foundation Model Infrastructure: A Quantized Consistency Diffusion Framework for Molecular Docking

• ICML 2026 MixFP4: Extending NVFP4 to Mixed Micro-Format via Scale-Bit Reuse and Tensor Core Co-design

• AAAI 2026 InfoQ: Mixed-Precision Quantization via Global Information Flow

• AAAI 2026 BIQ: Bisection Interval Quantization for Communication-efficient Federated Learning

• AAAI 2026 Bi-VLM: Binary Post-Training Quantization for Vision-Language Models

• AAAI 2026 BD-Net: Has Depth-Wise Convolution Ever Been Applied in Binary Neural Networks?

2025

• NeurIPS 2025 QBasicVSR: Temporal Awareness Adaptation Quantization for Video Super-Resolution

• NeurIPS 2025 ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization

• NeurIPS 2025 Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization

• NeurIPS 2025 DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization

• NeurIPS 2025 Point4Bit: Post Training 4-bit Quantization for Point Cloud 3D Detection

• NeurIPS 2025 Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression

• NeurIPS 2025 PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement [code]

• NeurIPS 2025 VETA-DiT: Variance-Equalized and Temporally Adaptive Quantization for Efficient 4-bit Diffusion Transformers

• NeurIPS 2025 LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning [code]

• NeurIPS 2025 LittleBit: Ultra Low-Bit Quantization via Latent Factorization

• NeurIPS 2025 HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs

• NeurIPS 2025 Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling

• NeurIPS 2025 Efficient and Generalizable Mixed-Precision Quantization via Topological Entropy

• NeurIPS 2025 QSCA: Quantization with Self-Compensating Auxiliary for Monocular Depth Estimation

• NeurIPS 2025 Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment

• ICCV 2025 Scheduling Weight Transitions for Quantization-Aware Training [code]

• ICCV 2025 Task-Specific Zero-shot Quantization-Aware Training for Object Detection [code]

• ICCV 2025 OuroMamba: A Data-Free Quantization Framework for Vision Mamba

• ICCV 2025 Allowing Oscillation Quantization: Overcoming Solution Space Limitation in Low Bit-Width Quantization [code]

• ICCV 2025 FedWSQ: Efficient Federated Learning with Weight Standardization and Distribution-Aware Non-Uniform Quantization [code]

• ICCV 2025 Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers [code]

• ICCV 2025 QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation [code]

• ICCV 2025 MixA-Q: Revisiting Activation Sparsity for Vision Transformers from a Mixed-Precision Quantization Perspective

• ICCV 2025 DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization [code]

• ICCV 2025 AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment Anything Model

• ICCV 2025 MSQ: Memory-Efficient Bit Sparsification Quantization

• ICCV 2025 QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning [code]

• ICML 2025 MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design [code]

• ICML 2025 Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning

• ICML 2025 ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals [code]

• ICML 2025 SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models [code]

• ICML 2025 PARQ: Piecewise-Affine Regularized Quantization [code]

• ICML 2025 Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models [code]

• ICML 2025 LRA-QViT: Integrating Low-Rank Approximation and Quantization for Robust and Efficient Vision Transformers

• ICML 2025 BoA: Attention-aware Post-training Quantization without Backpropagation

• ICML 2025 MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance [code]

• ICML 2025 NestQuant: nested lattice quantization for matrix products and LLMs

• ICML 2025 FlatQuant: Flatness Matters for LLM Quantization [code]

• ICML 2025 Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models [code]

• ICML 2025 SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression [code]

• ICML 2025 QT-DoG: Quantization-Aware Training for Domain Generalization [code]

• ICML 2025 Matryoshka Quantization

• ICML 2025 Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation [code]

• ICML 2025 Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantization [code]

• ICML 2025 Layer-wise Quantization for Quantized Optimistic Dual Averaging

• ICML 2025 Outlier-Aware Post-Training Quantization for Discrete Graph Diffusion Models

• ICML 2025 BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference

• ICML 2025 GPTAQ: Efficient Finetuning-Free Quantization with Asymmetric Calibration [code]

• ICML 2025 Optimizing Large Language Model Training Using FP4 Quantization

• ICML 2025 SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization

• ICML 2025 SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization [code]

• ICML 2025 Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers [code]

• ICML 2025 GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models [code]

• ICML 2025 GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance [code]

• AAAI 2025 Qua$^2$SeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models [code]

• AAAI 2025 Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues [code]

• AAAI 2025 D2-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models [code]

• AAAI 2025 MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models [code]

• CVPR 2025 Quantization without Tears

• CVPR 2025 APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformer [code]

• ICLR 2025 SpinQuant: LLM quantization with learned rotations [code]

• ICLR 2025 LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid

• ICLR 2025 CBQ: Cross-Block Quantization for Large Language Models

• ICLR 2025 OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting [code]

• ICLR 2025 QERA: an Analytical Framework for Quantization Error Reconstruction [code]

• ICLR 2025 Svdquant: Absorbing outliers by low-rank components for 4-bit diffusion models [code]

• ICLR 2025 DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models [code]

• ICLR 2025 SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning [code]

• ICLR 2025 ViDiT-Q: Efficient and accurate quantization of diffusion transformers for image and video generation [code]

2024

• AAAI 2024 MetaMix: meta-state precision searcher for mixed-precision activation quantization
• AAAI 2024 Norm Tweaking: High-Performance Low-Bit Quantization of Large Language Models [code]
• AAAI 2024 Make RepVGG Greater Again: A Quantization-aware Approach [code]
• AAAI 2024 Bi-ViT: Pushing the Limit of Vision Transformer Quantization [code]
• AAAI 2024 Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge
• AAAI 2024 AQ-DETR: Low-Bit Quantized Detection Transformer with Auxiliary Queries
• AAAI 2024 OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models [code]
• AAAI 2024 One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training
• AAAI 2024 ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation [code]
• CVPR 2024 TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models [code]
• CVPR 2024 Retraining-free Model Quantization via One-Shot Weight-Coupling Learning [code]
• CVPR 2024 Enhancing Post-training Quantization Calibration through Contrastive Learning
• CVPR 2024 PTQ4SAM: Post-Training Quantization for Segment Anything [code]
• CVPR 2024 CL-Calib: Enhancing Post-training Quantization Calibration through Contrastive Learning
• CVPR 2024 PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution [code]
• CVPR 2024 Mixed-precision quantization for federated learning on resource-constrained heterogeneous devices
• CVPR 2024 Instance-Aware Group Quantization for Vision Transformers
• CVPR 2024 Data-Free Quantization via Pseudo-label Filtering
• CVPR 2024 Reg-PTQ: Regression-specialized Post-training Quantization for Fully Quantized Object Detector
• CVPR 2024 Towards Accurate Post-training Quantization for Diffusion Models [code]
• ECCV 2024 CLAMP-ViT: Contrastive data-free learning for adaptive post-training quantization of vits [code]
• ECCV 2024 AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer [code]
• ECCV 2024 Post-training quantization with progressive calibration and activation relaxing for text-to-image diffusion models [code]
• ECCV 2024 Memory-Efficient Fine-Tuning for Quantized Diffusion Model [code]
• ECCV 2024 Mixdq: Memory-efficient few-step text-to-image diffusion models with metric-decoupled mixed precision quantization [code]
• ECCV 2024 Timestep-aware correction for quantized diffusion models
• ECCV 2024 Clamp-vit: Contrastive data-free learning for adaptive post-training quantization of vits [code]
• ICLR 2024 AffineQuant: Affine Transformation Quantization for Large Language Models [code]
• ICLR 2024 LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models [code]
• ICLR 2024 Loftq: Lora-fine-tuning-aware quantization for large language models [code]
• ICLR 2024 OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models [code]
• ICLR 2024 QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Model [code]
• ICML 2024 SqueezeLLM: Dense-and-Sparse Quantization [code]
• ICML 2024 A2Q+: Improving Accumulator-Aware Weight Quantization
• ICML 2024 Learning from students: Applying t-distributions to explore accurate and efficient formats for llms [code]
• ICML 2024 LQER:Low-Rank Quantization Error Reconstruction for LLMs [code]
• ICML 2024 Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization
• ICML 2024 Reshape and Adapt for Output Quantization (RAOQ): Quantization-aware Training for In-memory Computing Systems
• ICML 2024 ERQ: Error Reduction for Post-Training Quantization of Vision Transformers
• ICML 2024 KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache [code]
• ICML 2024 BiLLM: Pushing the Limit of Post-Training Quantization for LLMs [code]
• ICML 2024 QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks [code]
• ICML 2024 Extreme Compression of Large Language Models via Additive Quantization [code]
• ICML 2024 Outlier-aware Slicing for Post-Training Quantization in Vision Transformer
• ICML 2024 BiE: Bi-Exponent Block Floating-Point for Large Language Models Quantization
• ICML 2024 Reshape and Adapt for Output Quantization ({RAOQ}): Quantization-aware Training for In-memory Computing Systems
• NeurIPS 2024 Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers [code]
• NeurIPS 2024 QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs [code]
• NeurIPS 2024 2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution [code]
• NeurIPS 2024 MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization [code]
• NeurIPS 2024 Exploiting LLM Quantization
• NeurIPS 2024 Efficient Multi-task LLM Quantization and Serving for Multiple LoRA Adapters
• NeurIPS 2024 QTIP: Quantization with Trellises and Incoherence Processing [code]
• NeurIPS 2024 Generalizing CNNs to graphs with learnable neighborhood quantization [code]
• NeurIPS 2024 SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training [code]
• NeurIPS 2024 Optimal and Approximate Adaptive Stochastic Quantization [code]
• NeurIPS 2024 BitsFusion: 1.99 bits Weight Quantization of Diffusion Model [code]
• NeurIPS 2024 BiDM: Pushing the Limit of Quantization for Diffusion Models [code]
• NeurIPS 2024 MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization [code]
• NeurIPS 2024 DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs [code]
• NeurIPS 2024 Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models
• NeurIPS 2024 Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers
• NeurIPS 2024 BiDM: Pushing the Limit of Quantization for Diffusion Models [code]
• NeurIPS 2024 StepbaQ: Stepping backward as Correction for Quantized Diffusion Models
• NeurIPS 2024 Cherry on top: Parameter heterogeneity and quantization in large language models
• NeurIPS 2024 QBB: Quantization with Binary Bases for LLMs

2023

• AAAI 2023 OMPQ: Orthogonal Mixed Precision Quantization [code]
• AAAI 2023 Rethinking Data-Free Quantization as a Zero-Sum Game [code]
• AAAI 2023 Quantized Feature Distillation for Network Quantization
• AAAI 2023 Quantization-Aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks [code]
• CVPR 2023 Boost Vision Transformer with GPU-Friendly Sparsity and Quantization
• CVPR 2023 NIPQ: Noise proxy-based Integrated Pseudo-Quantization [code]
• CVPR 2023 GENIE: Show Me the Data for Quantization [code]
• CVPR 2023 Hard Sample Matters a Lot in Zero-Shot Quantization [code]
• CVPR 2023 One-Shot Model for Mixed-Precision Quantization
• CVPR 2023 PD-Quant: Post-Training Quantization based on Prediction Difference Metric [code]
• CVPR 2023 Post-training Quantization on Diffusion Models [code]
• CVPR 2023 Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective [code]
• CVPR 2023 NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
• CVPR 2023 Adaptive Data-Free Quantization [code]
• CVPR 2023 Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization
• CVPR 2023 Q-DETR: An Efficient Low-Bit Quantized Detection Transformer [code]
• ICCV 2023 I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference [code]
• ICCV 2023 RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers [code]
• ICCV 2023 Causal-dfq: Causality guided data-free network quantization [code]
• ICCV 2023 Q-Diffusion: Quantizing Diffusion Models [code]
• ICCV 2023 Unified data-free compression: Pruning and quantization without fine-tuning
• ICLR 2023 $\rm{A}^{2} Q$: Aggregation-Aware Quantization for Graph Neural Networks
• ICLR 2023 GPTQ: Accurate Post-training Quantization For Generative Pre-trained Transformers [code]
• ICLR 2023 PowerQuant:Automorphism Search For Non-Uniform Quantization
• ICLR 2023 Block and Subword-Scaling Floating-Point (BSFP) : An Efficient Non-Uniform Quantization For Low Precision Inference
• ICLR 2023 A$^{2}$Q:Aggregation-Aware Quantization For Graph Nueral Networks [code]
• ICLR 2023 PowerQuant: Automorphism Search for Non-Uniform Quantization
• ICML 2023 SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models [code]
• ICML 2023 FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization [code]
• ICML 2023 Oscillation-free Quantization for Low-bit Vision Transformers [code]
• ICML 2023 Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases [code]
• ICML 2023 Quantized Distributed Training of Large Models with Convergence Guarantees
• NeurIPS 2023 QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution [code]
• NeurIPS 2023 Q-DM: An Efficient Low-bit Quantized Diffusion Model
• NeurIPS 2023 REx: Data-Free Residual Quantization Error Expansion
• NeurIPS 2023 PTQD: Accurate Post-Training Quantization for Diffusion Models [code]
• NeurIPS 2023 TexQ: Zero-shot Network Quantization with Texture Feature Distribution Calibration
• NeurIPS 2023 PackQViT: Faster Sub-8-bit Vision Transformers via Full and Packed Quantization on the Mobile [code]
• NeurIPS 2023 Intriguing Properties of Quantization at Scale
• NeurIPS 2023 QLORA: Efficient Finetuning of Quantized LLMs [code]
• NeurIPS 2023 Training Transformers with 4-bit Integers [code]
• NeurIPS 2023 QuIP: 2-Bit Quantization of Large Language Models With Guarantees [code]
• NeurIPS 2023 Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization
• NeurIPS 2023 Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers
• NeurIPS 2023 Towards Efficient and Accurate Winograd Convolution via Full Quantization
• NeurIPS 2023 Temporal Dynamic Quantization for Diffusion Models [code]
• NeurIPS 2023 Pruning vs Quantization: Which is Better? [code]

2022

• CVPR 2022 Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation [code]
• CVPR 2022 Learnable Lookup Table for Neural Network Quantization [code]
• CVPR 2022 Mr.BiQ: Post-Training Non-Uniform Quantization based on Minimizing the Reconstruction Error
• CVPR 2022 Data-Free Network Compression via Parametric Non-uniform Mixed Precision Quantization
• CVPR 2022 Instance-Aware Dynamic Neural Network Quantization [code]
• CVPR 2022 IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization [code]
• ECCV 2022 CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution
• ECCV 2022 PTQ4ViT: Post-training Quantization for Vision Transformers with Twin Uniform Quantization [code]
• ECCV 2022 Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach [code]
• ECCV 2022 Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance [code]
• ECCV 2022 Patch Similarity Aware Data-Free Quantization for Vision Transformers [code]
• ECCV 2022 Fine-grained Data Distribution Alignment for Post-Training Quantization [code]
• ECCV 2022 Non-Uniform Step Size Quantization for Accurate Post-Training Quantization [code]
• ICLR 2022 8-bit Optimizers via Block-wise Quantization
• ICLR 2022 F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization [code]
• ICLR 2022 SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation [code]
• ICLR 2022 QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization [code]
• ICLR 2022 Toward Efficient Low-Precision Training: Data Format Optimization and Hysteresis Quantization
• ICLR 2022 VC dimension of partially quantized neural networks in the overparametrized regime. [code]
• ICML 2022 Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training
• ICML 2022 Overcoming Oscillations in Quantization-Aware Training [code]
• ICML 2022 Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training
• ICML 2022 SDQ:Stochastic Differentiable Quantization with Mixed Precision
• IJCAI 2022 RAPQ: Rescuing Accuracy for Power-of-Two Low-bit Post-training Quantization [code]
• IJCAI 2022 MultiQuant: Training Once for Multi-bit Quantization of Neural Networks
• IJCAI 2022 FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer [code]
• NeurIPS 2022 Entropy-driven mixed-precision quantization for deep network design [code]
• NeurIPS 2022 Towards Efficient Post-training Quantization of Pre-trained Language Models
• NeurIPS 2022 Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer [code]
• NeurIPS 2022 ClimbQ: Class Imbalanced Quantization Enabling Robustness on Efficient Inferences [code]
• NeurIPS 2022 Redistribution of Weights and Activations for AdderNet Quantization
• NeurIPS 2022 Leveraging inter-layer dependency for post-training quantization
• NeurIPS 2022 ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers
• NeurIPS 2022 Leveraging Inter-Layer Dependency for Post -Training Quantization

2021

• AAAI 2021 Optimizing information theory based bitwise bottlenecks for efficient mixed-precision activation quantization
• AAAI 2021 Distribution Adaptive INT8 Quantization for Training CNNs [code]
• AAAI 2021 Stochastic Precision Ensemble: Self‐Knowledge Distillation for Quantized Deep Neural Networks
• AAAI 2021 FracBits: Mixed Precision Quantization via Fractional Bit-Widths [code]
• AAAI 2021 Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision
• AAAI 2021 Training Binary Neural Network without Batch Normalization for Image Super-Resolution
• AAAI 2021 SA-BNN: State-­Aware Binary Neural Network
• CVPR 2021 Permute, Quantize, and Fine-tune: Efficient Compression of Neural Networks. [code]
• CVPR 2021 Diversifying Sample Generation for Accurate Data-Free Quantization
• CVPR 2021 Learnable Companding Quantization for Accurate Low-bit Neural Networks
• CVPR 2021 Zero-shot Adversarial Quantization
• CVPR 2021 Network Quantization with Element-wise Gradient Scaling [code]
• CVPR 2021 Automated Log-Scale Quantization for Low-Cost Deep Neural Networks
• CVPR 2021 QPP: Real-Time Quantization Parameter Prediction for Deep Neural Networks
• ICLR 2021 Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming [code]
• ICLR 2021 BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction [code]
• ICLR 2021 Neural gradients are near-lognormal: improved quantized and sparse training
• ICLR 2021 Training with Quantization Noise for Extreme Model Compression
• ICLR 2021 Incremental few-shot learning via vector quantization in deep embedded space
• ICLR 2021 Degree-Quant: Quantization-Aware Training for Graph Neural Networks [code]
• ICLR 2021 BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization
• ICLR 2021 Simple Augmentation Goes a Long Way: ADRL for DNN Quantization
• ICML 2021 Differentiable dynamic quantization with mixed precision and adaptive resolution
• ICML 2021 HAWQV3: Dyadic Neural Network Quantization [code]
• ICML 2021 Accurate Post Training Quantization With Small Calibration Sets
• ICML 2021 I-BERT: Integer-only BERT Quantization [code]
• NeurIPS 2021 Post-Training Quantization for Vision Transformer
• NeurIPS 2021 Post-Training Sparsity-Aware Quantization [code]
• NeurIPS 2021 BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer
• NeurIPS 2021 Qimera: Data-free quantization with synthetic boundary supporting samples [code]

2020

• AAAI 2020 Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT [code]
• AAAI 2020 Towards Accurate Low Bit-Width Quantization with Multiple Phase Adaptations
• CVPR 2020 ZeroQ: A Novel Zero Shot Quantization Framework [code]
• CVPR 2020 LSQ+: Improving Low-bit Quantization Through Learnable Offsets and Better Initialization
• CVPR 2020 AdaBits: Neural Network Quantization With Adaptive Bit-Widths [code]
• CVPR 2020 Adaptive Loss-aware Quantization for Multi-bit Networks [code]
• ECCV 2020 HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNs [code]
• ECCV 2020 Generative Low-bitwidth Data Free Quantization [code]
• ICML 2020 Towards Accurate Post-training Quantization for Reparameterized Models [code]
• ICML 2020 Up or Down? Adaptive Rounding for Post-Training Quantization [code]
• NeurIPS 2020 Searching for Low-Bit Weights in Quantized Neural Networks [code]
• NeurIPS 2020 Robust Quantization: One Model to Rule Them All [code]