{"list":"other","total":54,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1902.08153","title":"Learned Step Size Quantization","created":"2019-02-21","cited_by_count":628},{"id":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"1806.08342","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","created":"2018-06-21","cited_by_count":521},{"id":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472},{"id":"1906.04721","title":"Data-Free Quantization Through Weight Equalization and Bias Correction","created":"2019-06-11","cited_by_count":336},{"id":"1803.00885","title":"Essentially No Barriers in Neural Network Energy Landscape","created":"2018-03-02","cited_by_count":330},{"id":"1903.05662","title":"Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets","created":"2019-03-13","cited_by_count":231},{"id":"1412.6544","title":"Qualitatively characterizing neural network optimization problems","created":"2014-12-19","cited_by_count":188},{"id":"1909.13144","title":"Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks","created":"2019-09-28","cited_by_count":148},{"id":"2009.11551","title":"Residual Feature Distillation Network for Lightweight Image Super-Resolution","created":"2020-09-24","cited_by_count":122},{"id":"2203.11086","title":"Overcoming Oscillations in Quantization-Aware Training","created":"2022-03-21","cited_by_count":119},{"id":"1611.01540","title":"Topology and Geometry of Half-Rectified Network Optimization","created":"2016-11-04","cited_by_count":102},{"id":"2406.04836","title":"Revisiting Catastrophic Forgetting in Large Language Model Tuning","created":"2024-06-07","cited_by_count":99},{"id":"1911.07190","title":"Loss Aware Post-training Quantization","created":"2019-11-17","cited_by_count":97},{"id":"2104.00903","title":"Network Quantization with Element-wise Gradient Scaling","created":"2021-04-02","cited_by_count":87},{"id":"1706.10239","title":"Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes","created":"2017-06-30","cited_by_count":84},{"id":"2102.10472","title":"Learning Neural Network Subspaces","created":"2021-02-20","cited_by_count":82},{"id":"2002.07686","title":"Robust Quantization: One Model to Rule Them All","created":"2020-02-18","cited_by_count":63},{"id":"2304.08612","title":"Bridging Discrete and Backpropagation: Straight-Through and Beyond","created":"2023-04-17","cited_by_count":31},{"id":"2007.12927","title":"Neural networks with late-phase weights","created":"2020-07-25","cited_by_count":29},{"id":"2111.12273","title":"Sharpness-aware Quantization for Deep Neural Networks","created":"2021-11-24","cited_by_count":25},{"id":"2310.19103","title":"Proving Linear Mode Connectivity of Neural Networks via Optimal Transport","created":"2023-10-29","cited_by_count":25},{"id":"2012.06898","title":"Revisiting \"Qualitatively Characterizing Neural Network Optimization Problems\"","created":"2020-12-12","cited_by_count":24},{"id":"2306.16788","title":"Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging","created":"2023-06-29","cited_by_count":20},{"id":"2108.06983","title":"Distance-aware Quantization","created":"2021-08-16","cited_by_count":19},{"id":"2305.19510","title":"Mildly Overparameterized ReLU Networks Have a Favorable Loss Landscape","created":"2023-05-31","cited_by_count":17},{"id":"2204.12322","title":"RAPQ: Rescuing Accuracy for Power-of-Two Low-bit Post-training Quantization","created":"2022-04-26","cited_by_count":15},{"id":"2410.06020","title":"QT-DoG: Quantization-aware Training for Domain Generalization","created":"2024-10-08","cited_by_count":13},{"id":"2412.13573","title":"Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes","created":"2024-12-18","cited_by_count":10},{"id":"2210.07171","title":"SQuAT: Sharpness- and Quantization-Aware Training for BERT","created":"2022-10-13","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":"2412.15846","title":"Improving Quantization-aware Training of Low-Precision Network via Block Replacement on Full-Precision Counterpart","created":"2024-12-20","cited_by_count":6},{"id":"2206.05916","title":"Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks","created":"2022-06-13","cited_by_count":5},{"id":"2510.10693","title":"High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator","created":"2025-10-12","cited_by_count":4},{"id":"2203.11323","title":"Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm","created":"2022-03-21","cited_by_count":3},{"id":"2406.16988","title":"MD tree: a model-diagnostic tree grown on loss landscape","created":"2024-06-24","cited_by_count":3},{"id":"2502.08355","title":"Loss Landscape Analysis for Reliable Quantized ML Models for Scientific Sensing","created":"2025-02-12","cited_by_count":3},{"id":"2503.11078","title":"Understanding Flatness in Generative Models: Its Role and Benefits","created":"2025-03-14","cited_by_count":3},{"id":"2505.04877","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","created":"2025-05-08","cited_by_count":3},{"id":"2511.04808","title":"Sharp Minima Can Generalize: A Loss Landscape Perspective On Data","created":"2025-11-06","cited_by_count":3},{"id":"2509.00859","title":"Quantization Meets OOD: Generalizable Quantization-aware Training from a Flatness Perspective","created":"2025-08-31","cited_by_count":2},{"id":"2506.10463","title":"Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization","created":"2025-06-12","cited_by_count":1},{"id":"2511.01462","title":"Efficiently Training A Flat Neural Network Before It has been Quantizated","created":"2025-11-03","cited_by_count":1}],"next_cursor":null}