{"total":231,"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":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300,"area":"mechinterp"},{"id":"2302.12249","title":"MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes","created":"2023-02-23","cited_by_count":218,"area":null},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183,"area":null},{"id":"2102.04010","title":"Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch","created":"2021-02-08","cited_by_count":179,"area":null},{"id":"2203.11086","title":"Overcoming Oscillations in Quantization-Aware Training","created":"2022-03-21","cited_by_count":119,"area":null},{"id":"2107.04562","title":"The Bayesian Learning Rule","created":"2021-07-09","cited_by_count":99,"area":null},{"id":"2104.00903","title":"Network Quantization with Element-wise Gradient Scaling","created":"2021-04-02","cited_by_count":87,"area":null},{"id":"2401.17264","title":"Proactive Detection of Voice Cloning with Localized Watermarking","created":"2024-01-30","cited_by_count":78,"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":"2205.07877","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","created":"2022-05-14","cited_by_count":65,"area":null},{"id":"2107.01959","title":"Universal Approximation of Functions on Sets","created":"2021-07-05","cited_by_count":62,"area":null},{"id":"2405.14852","title":"PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression","created":"2024-05-23","cited_by_count":61,"area":null},{"id":"2501.17116","title":"Optimizing Large Language Model Training Using FP4 Quantization","created":"2025-01-28","cited_by_count":56,"area":null},{"id":"2104.05168","title":"Soft then Hard: Rethinking the Quantization in Neural Image Compression","created":"2021-04-12","cited_by_count":51,"area":null},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"area":null},{"id":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41,"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":"2205.15213","title":"Backpropagation through Combinatorial Algorithms: Identity with Projection Works","created":"2022-05-30","cited_by_count":29,"area":"lr"},{"id":"2308.10134","title":"AutoReP: Automatic ReLU Replacement for Fast Private Network Inference","created":"2023-08-20","cited_by_count":29,"area":null},{"id":"2406.00800","title":"MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization","created":"2024-06-02","cited_by_count":28,"area":null},{"id":"2309.14331","title":"LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference","created":"2023-09-25","cited_by_count":27,"area":null},{"id":"2202.01653","title":"Learning strides in convolutional neural networks","created":"2022-02-03","cited_by_count":26,"area":null},{"id":"2209.07735","title":"Enhance the Visual Representation via Discrete Adversarial Training","created":"2022-09-16","cited_by_count":23,"area":null},{"id":"2409.10568","title":"On the limits of agency in agent-based models","created":"2024-09-14","cited_by_count":21,"area":"agents"},{"id":"2207.12577","title":"Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution","created":"2022-07-25","cited_by_count":20,"area":null},{"id":"2305.16044","title":"Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networks","created":"2023-05-25","cited_by_count":18,"area":null},{"id":"2412.06234","title":"Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction","created":"2024-12-09","cited_by_count":18,"area":null},{"id":"2205.12268","title":"Wavelet Feature Maps Compression for Image-to-Image CNNs","created":"2022-05-24","cited_by_count":16,"area":null},{"id":"2506.16349","title":"Watermarking Autoregressive Image Generation","created":"2025-06-19","cited_by_count":16,"area":"safety"},{"id":"2306.01385","title":"Task-Agnostic Structured Pruning of Speech Representation Models","created":"2023-06-02","cited_by_count":15,"area":null},{"id":"2306.06446","title":"ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer","created":"2023-06-10","cited_by_count":15,"area":"moe"},{"id":"2306.09124","title":"DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks","created":"2023-06-15","cited_by_count":15,"area":"diffusion"},{"id":"2304.14271","title":"A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2202.05302","title":"Trust in AI: Interpretability is not necessary or sufficient, while black-box interaction is necessary and sufficient","created":"2022-02-10","cited_by_count":13,"area":null},{"id":"2410.12876","title":"In-context KV-Cache Eviction for LLMs via Attention-Gate","created":"2024-10-15","cited_by_count":13,"area":"inference"},{"id":"2307.04347","title":"Injecting Logical Constraints into Neural Networks via Straight-Through Estimators","created":"2023-07-10","cited_by_count":12,"area":null},{"id":"2403.07134","title":"COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization","created":"2024-03-11","cited_by_count":12,"area":null},{"id":"2110.13220","title":"Demystifying and Generalizing BinaryConnect","created":"2021-10-25","cited_by_count":11,"area":null},{"id":"2112.02880","title":"AdaSTE: An Adaptive Straight-Through Estimator to Train Binary Neural Networks","created":"2021-12-06","cited_by_count":11,"area":null},{"id":"2201.12965","title":"Inverse design of photonic devices with strict foundry fabrication constraints","created":"2022-01-31","cited_by_count":11,"area":null},{"id":"2206.04864","title":"Binarizing Split Learning for Data Privacy Enhancement and Computation Reduction","created":"2022-06-10","cited_by_count":11,"area":null},{"id":"2502.12346","title":"QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models","created":"2025-02-17","cited_by_count":11,"area":null},{"id":"2212.00325","title":"HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning","created":"2022-12-01","cited_by_count":10,"area":null},{"id":"2310.03004","title":"Soft Convex Quantization: Revisiting Vector Quantization with Convex Optimization","created":"2023-10-04","cited_by_count":10,"area":null},{"id":"2212.01076","title":"Are Straight-Through gradients and Soft-Thresholding all you need for Sparse Training?","created":"2022-12-02","cited_by_count":9,"area":null},{"id":"2303.03382","title":"Globally Optimal Training of Neural Networks with Threshold Activation Functions","created":"2023-03-06","cited_by_count":9,"area":null},{"id":"2406.00431","title":"SpaFL: Communication-Efficient Federated Learning with Sparse Models and Low computational Overhead","created":"2024-06-01","cited_by_count":9,"area":null},{"id":"2407.15540","title":"Differentiable Product Quantization for Memory Efficient Camera Relocalization","created":"2024-07-22","cited_by_count":9,"area":null},{"id":"2107.13490","title":"Adaptive Precision Training (AdaPT): A dynamic fixed point quantized training approach for DNNs","created":"2021-07-28","cited_by_count":8,"area":null},{"id":"2209.03487","title":"A simple approach for quantizing neural networks","created":"2022-09-07","cited_by_count":8,"area":null},{"id":"2304.10618","title":"ULEEN: A Novel Architecture for Ultra Low-Energy Edge Neural Networks","created":"2023-04-20","cited_by_count":8,"area":null},{"id":"2307.15712","title":"Quantum-limited stochastic optical neural networks operating at a few quanta per activation","created":"2023-07-28","cited_by_count":8,"area":null},{"id":"2312.05272","title":"GenQ: Quantization in Low Data Regimes with Generative Synthetic Data","created":"2023-12-07","cited_by_count":8,"area":null},{"id":"2603.00040","title":"Attn-QAT: 4-Bit Attention With Quantization-Aware Training","created":"2026-02-09","cited_by_count":8,"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":"2207.14200","title":"CrAM: A Compression-Aware Minimizer","created":"2022-07-28","cited_by_count":7,"area":null},{"id":"2208.06124","title":"Gradient Estimation for Binary Latent Variables via Gradient Variance Clipping","created":"2022-08-12","cited_by_count":7,"area":null},{"id":"2402.02328","title":"Sample Complexity of Algorithm Selection Using Neural Networks and Its Applications to Branch-and-Cut","created":"2024-02-04","cited_by_count":7,"area":null},{"id":"2407.18930","title":"Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition","created":"2024-07-10","cited_by_count":7,"area":null},{"id":"2111.00153","title":"RMSMP: A Novel Deep Neural Network Quantization Framework with Row-wise Mixed Schemes and Multiple Precisions","created":"2021-10-30","cited_by_count":6,"area":null},{"id":"2201.06126","title":"Control of Dual-Sourcing Inventory Systems using Recurrent Neural Networks","created":"2022-01-16","cited_by_count":6,"area":null},{"id":"2204.05669","title":"An Analysis of Discretization Methods for Communication Learning with Multi-Agent Reinforcement Learning","created":"2022-04-12","cited_by_count":6,"area":null},{"id":"2206.08594","title":"Principled Acceleration of Iterative Numerical Methods Using Machine Learning","created":"2022-06-17","cited_by_count":6,"area":null},{"id":"2208.08562","title":"Restructurable Activation Networks","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2403.06457","title":"Ensemble Quadratic Assignment Network for Graph Matching","created":"2024-03-11","cited_by_count":6,"area":null},{"id":"2501.15377","title":"Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation","created":"2025-01-26","cited_by_count":6,"area":null},{"id":"2510.08757","title":"LOTION: Smoothing the Optimization Landscape for Quantized Training","created":"2025-10-09","cited_by_count":6,"area":null},{"id":"2109.06094","title":"Single-stream CNN with Learnable Architecture for Multi-source Remote Sensing Data","created":"2021-09-13","cited_by_count":5,"area":null},{"id":"2204.11189","title":"PUERT: Probabilistic Under-sampling and Explicable Reconstruction Network for CS-MRI","created":"2022-04-24","cited_by_count":5,"area":null},{"id":"2212.05122","title":"All-in-One: A Highly Representative DNN Pruning Framework for Edge Devices with Dynamic Power Management","created":"2022-12-09","cited_by_count":5,"area":null},{"id":"2302.10899","title":"Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks on Label-Free Data","created":"2023-02-10","cited_by_count":5,"area":"distill"},{"id":"2402.05013","title":"Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth","created":"2024-02-07","cited_by_count":5,"area":null},{"id":"2403.01922","title":"FlowPrecision: Advancing FPGA-Based Real-Time Fluid Flow Estimation with Linear Quantization","created":"2024-03-04","cited_by_count":5,"area":null},{"id":"2403.11090","title":"Brain-on-Switch: Towards Advanced Intelligent Network Data Plane via NN-Driven Traffic Analysis at Line-Speed","created":"2024-03-17","cited_by_count":5,"area":null},{"id":"2409.09406","title":"Real-world Adversarial Defense against Patch Attacks based on Diffusion Model","created":"2024-09-14","cited_by_count":5,"area":"diffusion"},{"id":"2501.18475","title":"CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization","created":"2025-01-30","cited_by_count":5,"area":null},{"id":"2502.09003","title":"RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2503.06921","title":"Task Vector Quantization for Memory-Efficient Model Merging","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2503.15748","title":"PARQ: Piecewise-Affine Regularized Quantization","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2510.23926","title":"Improving the Straight-Through Estimator with Zeroth-Order Information","created":"2025-10-27","cited_by_count":5,"area":null},{"id":"2110.01532","title":"Differentiable Spline Approximations","created":"2021-10-04","cited_by_count":4,"area":null},{"id":"2201.05020","title":"Automatic Sparse Connectivity Learning for Neural Networks","created":"2022-01-13","cited_by_count":4,"area":null},{"id":"2212.12653","title":"Hyperspherical Quantization: Toward Smaller and More Accurate Models","created":"2022-12-24","cited_by_count":4,"area":null},{"id":"2308.05035","title":"Expert load matters: operating networks at high accuracy and low manual effort","created":"2023-08-09","cited_by_count":4,"area":null},{"id":"2310.04469","title":"Taming Binarized Neural Networks and Mixed-Integer Programs","created":"2023-10-05","cited_by_count":4,"area":null},{"id":"2411.01663","title":"Unlocking the Theory Behind Scaling 1-Bit Neural Networks","created":"2024-11-03","cited_by_count":4,"area":null},{"id":"2510.10693","title":"High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator","created":"2025-10-12","cited_by_count":4,"area":null},{"id":"2510.18784","title":"CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2510.21879","title":"TernaryCLIP: Efficiently Compressing Vision-Language Models with Ternary Weights and Distilled Knowledge","created":"2025-10-23","cited_by_count":4,"area":"mllm"},{"id":"2511.06174","title":"LUT-LLM: Efficient Large Language Model Inference with Memory-based Computations on FPGAs","created":"2025-11-09","cited_by_count":4,"area":"inference"},{"id":"2104.05124","title":"A Bop and Beyond: A Second Order Optimizer for Binarized Neural Networks","created":"2021-04-11","cited_by_count":3,"area":null},{"id":"2203.11323","title":"Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm","created":"2022-03-21","cited_by_count":3,"area":null},{"id":"2212.13468","title":"Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods","created":"2022-12-27","cited_by_count":3,"area":null},{"id":"2302.00286","title":"Jointist: Simultaneous Improvement of Multi-instrument Transcription and Music Source Separation via Joint Training","created":"2023-02-01","cited_by_count":3,"area":null},{"id":"2303.08253","title":"R2 Loss: Range Restriction Loss for Model Compression and Quantization","created":"2023-03-14","cited_by_count":3,"area":null},{"id":"2311.08170","title":"Neural Lattice Reduction: A Self-Supervised Geometric Deep Learning Approach","created":"2023-11-14","cited_by_count":3,"area":null},{"id":"2312.13211","title":"DSFormer: Effective Compression of Text-Transformers by Dense-Sparse Weight Factorization","created":"2023-12-20","cited_by_count":3,"area":null},{"id":"2405.04098","title":"Binarized Simplicial Convolutional Neural Networks","created":"2024-05-07","cited_by_count":3,"area":null},{"id":"2405.07748","title":"Neural Network Compression for Reinforcement Learning Tasks","created":"2024-05-13","cited_by_count":3,"area":"deeprl"}],"next_cursor":"100"}