{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"1811.02508","title":"SDR - half-baked or well done?","created":"2018-11-06","cited_by_count":423},{"id":"1809.07454","title":"Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation","created":"2018-09-20","cited_by_count":406},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"1602.01528","title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network","created":"2016-02-04","cited_by_count":295},{"id":"2002.10179","title":"HRank: Filter Pruning using High-Rank Feature Map","created":"2020-02-24","cited_by_count":292},{"id":"1903.10258","title":"MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning","created":"2019-03-25","cited_by_count":227},{"id":"2010.13154","title":"Attention is All You Need in Speech Separation","created":"2020-10-25","cited_by_count":185},{"id":"1810.11809","title":"Discrimination-aware Channel Pruning for Deep Neural Networks","created":"2018-10-28","cited_by_count":171},{"id":"1907.01160","title":"WHAM!: Extending Speech Separation to Noisy Environments","created":"2019-07-02","cited_by_count":156},{"id":"2005.11262","title":"LibriMix: An Open-Source Dataset for Generalizable Speech Separation","created":"2020-05-22","cited_by_count":155},{"id":"2206.08312","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","created":"2022-06-16","cited_by_count":95},{"id":"2001.08565","title":"Channel Pruning via Automatic Structure Search","created":"2020-01-23","cited_by_count":85},{"id":"2202.02643","title":"The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training","created":"2022-02-05","cited_by_count":85},{"id":"2002.08933","title":"Wavesplit: End-to-End Speech Separation by Speaker Clustering","created":"2020-02-20","cited_by_count":75},{"id":"2209.15174","title":"Music Source Separation with Band-split RNN","created":"2022-09-30","cited_by_count":70},{"id":"2005.03354","title":"DMCP: Differentiable Markov Channel Pruning for Neural Networks","created":"2020-05-07","cited_by_count":69},{"id":"2007.13975","title":"Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation","created":"2020-07-28","cited_by_count":68},{"id":"2007.06833","title":"Sudo rm -rf: Efficient Networks for Universal Audio Source Separation","created":"2020-07-14","cited_by_count":51},{"id":"2409.17481","title":"MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models","created":"2024-09-26","cited_by_count":50},{"id":"2209.03952","title":"TF-GridNet: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separation","created":"2022-09-08","cited_by_count":48},{"id":"2403.18257","title":"Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation","created":"2024-03-27","cited_by_count":45},{"id":"2412.01199","title":"TinyFusion: Diffusion Transformers Learned Shallow","created":"2024-12-02","cited_by_count":45},{"id":"2412.18110","title":"SlimGPT: Layer-wise Structured Pruning for Large Language Models","created":"2024-12-24","cited_by_count":44},{"id":"2103.06460","title":"Recent Advances on Neural Network Pruning at Initialization","created":"2021-03-11","cited_by_count":41},{"id":"1608.01409","title":"Faster CNNs with Direct Sparse Convolutions and Guided Pruning","created":"2016-08-04","cited_by_count":39},{"id":"2209.15200","title":"An efficient encoder-decoder architecture with top-down attention for speech separation","created":"2022-09-30","cited_by_count":38},{"id":"2112.02321","title":"Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network","created":"2021-12-04","cited_by_count":32},{"id":"2304.02840","title":"NTK-SAP: Improving neural network pruning by aligning training dynamics","created":"2023-04-06","cited_by_count":30},{"id":"2203.04248","title":"Dual Lottery Ticket Hypothesis","created":"2022-03-08","cited_by_count":27},{"id":"2111.12485","title":"Understanding the Dynamics of DNNs Using Graph Modularity","created":"2021-11-24","cited_by_count":26},{"id":"2503.04992","title":"Wanda++: Pruning Large Language Models via Regional Gradients","created":"2025-03-06","cited_by_count":26},{"id":"2410.14720","title":"SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Models","created":"2024-10-14","cited_by_count":25},{"id":"2411.15558","title":"Reassessing Layer Pruning in LLMs: New Insights and Methods","created":"2024-11-23","cited_by_count":24},{"id":"2406.07929","title":"A Generic Layer Pruning Method for Signal Modulation Recognition Deep Learning Models","created":"2024-06-12","cited_by_count":18},{"id":"2303.07677","title":"SR-init: An interpretable layer pruning method","created":"2023-03-14","cited_by_count":13},{"id":"2410.01469","title":"TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation","created":"2024-10-02","cited_by_count":11},{"id":"2102.09978","title":"TransMask: A Compact and Fast Speech Separation Model Based on Transformer","created":"2021-02-19","cited_by_count":9},{"id":"2312.03464","title":"Subnetwork-to-go: Elastic Neural Network with Dynamic Training and Customizable Inference","created":"2023-12-06","cited_by_count":9},{"id":"2411.06463","title":"RL-Pruner: Structured Pruning Using Reinforcement Learning for CNN Compression and Acceleration","created":"2024-11-10","cited_by_count":9},{"id":"2110.10812","title":"REAL-M: Towards Speech Separation on Real Mixtures","created":"2021-10-20","cited_by_count":7},{"id":"2412.17741","title":"Reasoning to Attend: Try to Understand How <SEG> Token Works","created":"2024-12-23","cited_by_count":2}],"next_cursor":null}