{"total":46,"rows":[{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815,"area":null},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251,"area":null},{"id":"2207.09353","title":"Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications","created":"2022-07-19","cited_by_count":175,"area":null},{"id":"2206.09557","title":"LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models","created":"2022-06-20","cited_by_count":105,"area":null},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2211.13609","title":"PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization","created":"2022-11-24","cited_by_count":76,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2505.07004","title":"GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance","created":"2025-05-11","cited_by_count":32,"area":null},{"id":"2108.12659","title":"DKM: Differentiable K-Means Clustering Layer for Neural Network Compression","created":"2021-08-28","cited_by_count":31,"area":null},{"id":"2203.17008","title":"It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher","created":"2022-03-31","cited_by_count":20,"area":null},{"id":"2507.18553","title":"The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm","created":"2025-07-24","cited_by_count":20,"area":null},{"id":"2104.15129","title":"Stealthy Backdoors as Compression Artifacts","created":"2021-04-30","cited_by_count":18,"area":null},{"id":"2109.04236","title":"ECQ$^{\\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs","created":"2021-09-09","cited_by_count":15,"area":null},{"id":"2211.03300","title":"HFedMS: Heterogeneous Federated Learning with Memorable Data Semantics in Industrial Metaverse","created":"2022-11-07","cited_by_count":14,"area":null},{"id":"2210.08502","title":"FIT: A Metric for Model Sensitivity","created":"2022-10-16","cited_by_count":11,"area":null},{"id":"2102.02147","title":"Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded Platforms","created":"2021-02-03","cited_by_count":7,"area":null},{"id":"2110.08271","title":"Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations","created":"2021-10-15","cited_by_count":7,"area":null},{"id":"2208.06064","title":"Mixed-Precision Neural Networks: A Survey","created":"2022-08-11","cited_by_count":7,"area":null},{"id":"2311.00447","title":"On the Opportunities of Green Computing: A Survey","created":"2023-11-01","cited_by_count":7,"area":null},{"id":"2410.19483","title":"Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth Quantization","created":"2024-10-25","cited_by_count":7,"area":null},{"id":"2103.11083","title":"Compacting Deep Neural Networks for Internet of Things: Methods and Applications","created":"2021-03-20","cited_by_count":6,"area":null},{"id":"2112.03690","title":"Low-rank Tensor Decomposition for Compression of Convolutional Neural Networks Using Funnel Regularization","created":"2021-12-07","cited_by_count":6,"area":null},{"id":"2308.04269","title":"Lossy and Lossless (L$^2$) Post-training Model Size Compression","created":"2023-08-08","cited_by_count":4,"area":null},{"id":"2107.04380","title":"Model compression as constrained optimization, with application to neural nets. Part V: combining compressions","created":"2021-07-09","cited_by_count":3,"area":null},{"id":"2401.17269","title":"Effect of Weight Quantization on Learning Models by Typical Case Analysis","created":"2024-01-30","cited_by_count":3,"area":null},{"id":"2505.20646","title":"Binarized Neural Networks Converge Toward Algorithmic Simplicity: Empirical Support for the Learning-as-Compression Hypothesis","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2102.02631","title":"Universal Approximation Theorems of Fully Connected Binarized Neural Networks","created":"2021-02-04","cited_by_count":2,"area":null},{"id":"2306.11800","title":"Inshrinkerator: Compressing Deep Learning Training Checkpoints via Dynamic Quantization","created":"2023-06-20","cited_by_count":2,"area":null},{"id":"2401.16760","title":"One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training","created":"2024-01-30","cited_by_count":2,"area":null},{"id":"2510.19105","title":"MetaCluster: Enabling Deep Compression of Kolmogorov-Arnold Network","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2111.02018","title":"Multi-Glimpse Network: A Robust and Efficient Classification Architecture based on Recurrent Downsampled Attention","created":"2021-11-03","cited_by_count":1,"area":null},{"id":"2303.14114","title":"Object Motion Sensitivity: A Bio-inspired Solution to the Ego-motion Problem for Event-based Cameras","created":"2023-03-24","cited_by_count":1,"area":null},{"id":"2310.00574","title":"YFlows: Systematic Dataflow Exploration and Code Generation for Efficient Neural Network Inference using SIMD Architectures on CPUs","created":"2023-10-01","cited_by_count":1,"area":null},{"id":"2504.16968","title":"BackSlash: Rate Constrained Optimized Training of Large Language Models","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2505.12988","title":"Optimal Formats for Weight Quantisation","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2509.14029","title":"Deep Learning-Driven Peptide Classification in Biological Nanopores","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2105.01868","title":"Q-Rater: Non-Convex Optimization for Post-Training Uniform Quantization","created":"2021-05-05","cited_by_count":0,"area":null},{"id":"2210.03671","title":"A Closer Look at Hardware-Friendly Weight Quantization","created":"2022-10-07","cited_by_count":0,"area":null},{"id":"2210.14392","title":"Zero-Shot Learning of a Conditional Generative Adversarial Network for Data-Free Network Quantization","created":"2022-10-26","cited_by_count":0,"area":null},{"id":"2405.01857","title":"TinySeg: Model Optimizing Framework for Image Segmentation on Tiny Embedded Systems","created":"2024-05-03","cited_by_count":0,"area":null},{"id":"2501.03095","title":"A Novel Structure-Agnostic Multi-Objective Approach for Weight-Sharing Compression in Deep Neural Networks","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2504.12513","title":"AdaVid: Adaptive Video-Language Pretraining","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2603.10540","title":"In-Memory ADC-Based Nonlinear Activation Quantization for Efficient In-Memory Computing","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2609.28997","title":"Only What Was Seen: Observation-Gram Compaction of View-Dependent Appearance in 3D Gaussian Splatting","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}