{"list":"other","total":54,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1805.06085","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","created":"2018-05-16","cited_by_count":467},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263},{"id":"1903.05662","title":"Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets","created":"2019-03-13","cited_by_count":231},{"id":"2102.08127","title":"Learning curves of generic features maps for realistic datasets with a teacher-student model","created":"2021-02-16","cited_by_count":126},{"id":"1702.00953","title":"Deep Learning with Low Precision by Half-wave Gaussian Quantization","created":"2017-02-03","cited_by_count":117},{"id":"2006.14709","title":"The Gaussian equivalence of generative models for learning with shallow neural networks","created":"2020-06-25","cited_by_count":113},{"id":"1906.08632","title":"Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup","created":"2019-06-18","cited_by_count":112},{"id":"2211.13609","title":"PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization","created":"2022-11-24","cited_by_count":76},{"id":"1706.02379","title":"Training Quantized Nets: A Deeper Understanding","created":"2017-06-07","cited_by_count":75},{"id":"2202.08832","title":"Universality of empirical risk minimization","created":"2022-02-17","cited_by_count":75},{"id":"2107.01959","title":"Universal Approximation of Functions on Sets","created":"2021-07-05","cited_by_count":62},{"id":"2202.00293","title":"Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks","created":"2022-02-01","cited_by_count":50},{"id":"2309.05516","title":"Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs","created":"2023-09-11","cited_by_count":50},{"id":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41},{"id":"2010.04838","title":"Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator","created":"2020-10-09","cited_by_count":37},{"id":"2304.08612","title":"Bridging Discrete and Backpropagation: Straight-Through and Beyond","created":"2023-04-17","cited_by_count":31},{"id":"2302.08933","title":"Universality laws for Gaussian mixtures in generalized linear models","created":"2023-02-17","cited_by_count":28},{"id":"2202.01653","title":"Learning strides in convolutional neural networks","created":"2022-02-03","cited_by_count":26},{"id":"2205.13303","title":"Gaussian Universality of Perceptrons with Random Labels","created":"2022-05-26","cited_by_count":26},{"id":"1906.00687","title":"Relation Embedding with Dihedral Group in Knowledge Graph","created":"2019-06-03","cited_by_count":25},{"id":"1801.06313","title":"BinaryRelax: A Relaxation Approach For Training Deep Neural Networks With Quantized Weights","created":"2018-01-19","cited_by_count":24},{"id":"2001.03371","title":"Data-Dependence of Plateau Phenomenon in Learning with Neural Network --- Statistical Mechanical Analysis","created":"2020-01-10","cited_by_count":23},{"id":"2209.07735","title":"Enhance the Visual Representation via Discrete Adversarial Training","created":"2022-09-16","cited_by_count":23},{"id":"1808.05240","title":"Blended Coarse Gradient Descent for Full Quantization of Deep Neural Networks","created":"2018-08-15","cited_by_count":21},{"id":"1910.08237","title":"Mirror Descent View for Neural Network Quantization","created":"2019-10-18","cited_by_count":16},{"id":"1712.04332","title":"Scaling Limit: Exact and Tractable Analysis of Online Learning Algorithms with Applications to Regularized Regression and PCA","created":"2017-12-08","cited_by_count":14},{"id":"1805.08349","title":"A Solvable High-Dimensional Model of GAN","created":"2018-05-22","cited_by_count":13},{"id":"2410.06020","title":"QT-DoG: Quantization-aware Training for Domain Generalization","created":"2024-10-08","cited_by_count":13},{"id":"1802.03646","title":"On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural Networks","created":"2018-02-10","cited_by_count":12},{"id":"2310.15440","title":"Learning Dynamics in Linear VAE: Posterior Collapse Threshold, Superfluous Latent Space Pitfalls, and Speedup with KL Annealing","created":"2023-10-24","cited_by_count":12},{"id":"2502.13178","title":"Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis","created":"2025-02-18","cited_by_count":12},{"id":"2110.13220","title":"Demystifying and Generalizing BinaryConnect","created":"2021-10-25","cited_by_count":11},{"id":"1907.00959","title":"Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization","created":"2019-07-01","cited_by_count":9},{"id":"2011.11256","title":"Learning Quantized Neural Nets by Coarse Gradient Method for Non-linear Classification","created":"2020-11-23","cited_by_count":8},{"id":"1910.02176","title":"Straight-Through Estimator as Projected Wasserstein Gradient Flow","created":"2019-10-05","cited_by_count":7},{"id":"2208.06124","title":"Gradient Estimation for Binary Latent Variables via Gradient Variance Clipping","created":"2022-08-12","cited_by_count":7},{"id":"2404.11769","title":"QGen: On the Ability to Generalize in Quantization Aware Training","created":"2024-04-17","cited_by_count":7},{"id":"1805.06834","title":"Subspace Estimation from Incomplete Observations: A High-Dimensional Analysis","created":"2018-05-17","cited_by_count":6},{"id":"1602.04129","title":"Learning may need only a few bits of synaptic precision","created":"2016-02-12","cited_by_count":5},{"id":"2503.15748","title":"PARQ: Piecewise-Affine Regularized Quantization","created":"2025-03-19","cited_by_count":5},{"id":"2401.17269","title":"Effect of Weight Quantization on Learning Models by Typical Case Analysis","created":"2024-01-30","cited_by_count":3},{"id":"2301.13584","title":"Straight-Through meets Sparse Recovery: the Support Exploration Algorithm","created":"2023-01-31","cited_by_count":2}],"next_cursor":null}