{"list":"other","total":80,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"id":"1809.02736","title":"Joint Autoregressive and Hierarchical Priors for Learned Image Compression","created":"2018-09-08","cited_by_count":664},{"id":"2404.00456","title":"QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs","created":"2024-03-30","cited_by_count":634},{"id":"2004.10568","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","created":"2020-04-22","cited_by_count":621},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"id":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"1412.1193","title":"New insights and perspectives on the natural gradient method","created":"2014-12-03","cited_by_count":443},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"2203.10886","title":"ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding","created":"2022-03-21","cited_by_count":301},{"id":"2011.03029","title":"CompressAI: a PyTorch library and evaluation platform for end-to-end compression research","created":"2020-11-05","cited_by_count":276},{"id":"2007.08739","title":"Channel-wise Autoregressive Entropy Models for Learned Image Compression","created":"2020-07-17","cited_by_count":264},{"id":"2109.15047","title":"Deep Contextual Video Compression","created":"2021-09-30","cited_by_count":221},{"id":"2303.14978","title":"Learned Image Compression with Mixed Transformer-CNN Architectures","created":"2023-03-27","cited_by_count":211},{"id":"2103.15306","title":"Checkerboard Context Model for Efficient Learned Image Compression","created":"2021-03-29","cited_by_count":202},{"id":"1611.01232","title":"Deep Information Propagation","created":"2016-11-04","cited_by_count":195},{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","cited_by_count":192},{"id":"2011.14522","title":"Feature Learning in Infinite-Width Neural Networks","created":"2020-11-30","cited_by_count":190},{"id":"2203.08450","title":"The Devil Is in the Details: Window-based Attention for Image Compression","created":"2022-03-16","cited_by_count":147},{"id":"1602.01407","title":"A Kronecker-factored approximate Fisher matrix for convolution layers","created":"2016-02-03","cited_by_count":141},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141},{"id":"2206.03126","title":"Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse","created":"2022-06-07","cited_by_count":141},{"id":"1705.07774","title":"Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients","created":"2017-05-22","cited_by_count":139},{"id":"2007.03034","title":"Nonlinear Transform Coding","created":"2020-07-06","cited_by_count":136},{"id":"2402.17414","title":"Neural Video Compression with Feature Modulation","created":"2024-02-27","cited_by_count":123},{"id":"2202.05492","title":"Entroformer: A Transformer-based Entropy Model for Learned Image Compression","created":"2022-02-11","cited_by_count":107},{"id":"2108.03690","title":"Enhanced Invertible Encoding for Learned Image Compression","created":"2021-08-08","cited_by_count":105},{"id":"2211.07273","title":"MLIC: Multi-Reference Entropy Model for Learned Image Compression","created":"2022-11-14","cited_by_count":84},{"id":"2502.20762","title":"Towards Practical Real-Time Neural Video Compression","created":"2025-02-28","cited_by_count":80},{"id":"2306.03792","title":"FAMO: Fast Adaptive Multitask Optimization","created":"2023-06-06","cited_by_count":78},{"id":"2411.18704","title":"Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits","created":"2024-11-27","cited_by_count":71},{"id":"2406.17748","title":"A New Perspective on Shampoo's Preconditioner","created":"2024-06-25","cited_by_count":59},{"id":"2310.16387","title":"Frequency-Aware Transformer for Learned Image Compression","created":"2023-10-25","cited_by_count":58},{"id":"2304.09871","title":"A Theory on Adam Instability in Large-Scale Machine Learning","created":"2023-04-19","cited_by_count":56},{"id":"2502.00604","title":"Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective","created":"2025-02-02","cited_by_count":56},{"id":"2308.13985","title":"Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective","created":"2023-08-27","cited_by_count":51},{"id":"1512.04202","title":"Preconditioned Stochastic Gradient Descent","created":"2015-12-14","cited_by_count":50},{"id":"2302.05071","title":"EVC: Towards Real-Time Neural Image Compression with Mask Decay","created":"2023-02-10","cited_by_count":49},{"id":"2203.02452","title":"Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression","created":"2022-03-04","cited_by_count":45},{"id":"2203.10897","title":"Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression","created":"2022-03-21","cited_by_count":43},{"id":"2204.11326","title":"Beyond the Quadratic Approximation: the Multiscale Structure of Neural Network Loss Landscapes","created":"2022-04-24","cited_by_count":43},{"id":"2107.06463","title":"Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules","created":"2021-07-14","cited_by_count":35},{"id":"2302.08899","title":"QARV: Quantization-Aware ResNet VAE for Lossy Image Compression","created":"2023-02-16","cited_by_count":32},{"id":"2504.00496","title":"Learned Image Compression with Dictionary-based Entropy Model","created":"2025-04-01","cited_by_count":30},{"id":"2405.15413","title":"MambaVC: Learned Visual Compression with Selective State Spaces","created":"2024-05-24","cited_by_count":28},{"id":"2304.06244","title":"Computationally-Efficient Neural Image Compression with Shallow Decoders","created":"2023-04-13","cited_by_count":23},{"id":"2404.03605","title":"Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization","created":"2024-04-04","cited_by_count":23},{"id":"2502.05741","title":"Linear Attention Modeling for Learned Image Compression","created":"2025-02-09","cited_by_count":23},{"id":"2506.03595","title":"Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner","created":"2025-06-04","cited_by_count":23},{"id":"2507.19125","title":"Learned Image Compression with Hierarchical Progressive Context Modeling","created":"2025-07-25","cited_by_count":21},{"id":"2503.12461","title":"MambaIC: State Space Models for High-Performance Learned Image Compression","created":"2025-03-16","cited_by_count":20},{"id":"2304.12319","title":"LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compression","created":"2023-03-25","cited_by_count":19},{"id":"2402.07114","title":"Towards Quantifying the Preconditioning Effect of Adam","created":"2024-02-11","cited_by_count":19},{"id":"2410.04847","title":"Causal Context Adjustment Loss for Learned Image Compression","created":"2024-10-07","cited_by_count":19},{"id":"2506.07254","title":"A Stable Whitening Optimizer for Efficient Neural Network Training","created":"2025-06-08","cited_by_count":18},{"id":"2305.16025","title":"NVTC: Nonlinear Vector Transform Coding","created":"2023-05-25","cited_by_count":14},{"id":"2309.02529","title":"Fast and High-Performance Learned Image Compression With Improved Checkerboard Context Model, Deformable Residual Module, and Knowledge Distillation","created":"2023-09-05","cited_by_count":12},{"id":"2502.01763","title":"On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning","created":"2025-02-03","cited_by_count":12},{"id":"2103.02884","title":"A Cross Channel Context Model for Latents in Deep Image Compression","created":"2021-03-04","cited_by_count":11},{"id":"2211.02854","title":"Rate-Distortion Optimized Post-Training Quantization for Learned Image Compression","created":"2022-11-05","cited_by_count":10},{"id":"2311.12821","title":"Advancing The Rate-Distortion-Computation Frontier For Neural Image Compression","created":"2023-09-26","cited_by_count":9},{"id":"2402.18930","title":"Variable-Rate Learned Image Compression with Multi-Objective Optimization and Quantization-Reconstruction Offsets","created":"2024-02-29","cited_by_count":9},{"id":"2501.13751","title":"On Disentangled Training for Nonlinear Transform in Learned Image Compression","created":"2025-01-23","cited_by_count":9},{"id":"2403.07320","title":"Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding","created":"2024-03-12","cited_by_count":8},{"id":"2411.19320","title":"Generalized Gaussian Model for Learned Image Compression","created":"2024-11-28","cited_by_count":8},{"id":"2502.04988","title":"CMamba: Learned Image Compression with State Space Models","created":"2025-02-07","cited_by_count":5},{"id":"2502.20161","title":"Balanced Rate-Distortion Optimization in Learned Image Compression","created":"2025-02-27","cited_by_count":5},{"id":"2504.16586","title":"Learning Switchable Priors for Neural Image Compression","created":"2025-04-23","cited_by_count":5},{"id":"2410.00557","title":"STanH : Parametric Quantization for Variable Rate Learned Image Compression","created":"2024-10-01","cited_by_count":4},{"id":"2305.07678","title":"Exploring the Rate-Distortion-Complexity Optimization in Neural Image Compression","created":"2023-05-12","cited_by_count":2},{"id":"2408.17073","title":"Approximately Invertible Neural Network for Learned Image Compression","created":"2024-08-30","cited_by_count":2},{"id":"2505.18107","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","created":"2025-05-23","cited_by_count":1}],"next_cursor":null}