{"list":"other","total":54,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"id":"1910.09700","title":"Quantifying the Carbon Emissions of Machine Learning","created":"2019-10-21","cited_by_count":521},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"2002.10179","title":"HRank: Filter Pruning using High-Rank Feature Map","created":"2020-02-24","cited_by_count":292},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202},{"id":"2102.04010","title":"Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch","created":"2021-02-08","cited_by_count":179},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162},{"id":"2112.05135","title":"PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures","created":"2021-12-09","cited_by_count":131},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122},{"id":"2110.14739","title":"Generalized Shape Metrics on Neural Representations","created":"2021-10-27","cited_by_count":112},{"id":"2206.04040","title":"MobileOne: An Improved One millisecond Mobile Backbone","created":"2022-06-08","cited_by_count":109},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98},{"id":"1902.01996","title":"Are All Layers Created Equal?","created":"2019-02-06","cited_by_count":94},{"id":"2201.03529","title":"Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning","created":"2022-01-10","cited_by_count":83},{"id":"2402.02834","title":"Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods","created":"2024-02-05","cited_by_count":82},{"id":"2309.14393","title":"LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models","created":"2023-09-25","cited_by_count":72},{"id":"2310.16228","title":"On the Foundations of Shortcut Learning","created":"2023-10-24","cited_by_count":65},{"id":"1906.03728","title":"The Generalization-Stability Tradeoff In Neural Network Pruning","created":"2019-06-09","cited_by_count":54},{"id":"2103.06460","title":"Recent Advances on Neural Network Pruning at Initialization","created":"2021-03-11","cited_by_count":41},{"id":"2210.06659","title":"Structural Pruning via Latency-Saliency Knapsack","created":"2022-10-13","cited_by_count":41},{"id":"2305.19753","title":"The Tunnel Effect: Building Data Representations in Deep Neural Networks","created":"2023-05-31","cited_by_count":34},{"id":"2004.11627","title":"Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning","created":"2020-04-24","cited_by_count":30},{"id":"2102.03214","title":"Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning","created":"2021-02-05","cited_by_count":30},{"id":"2110.11395","title":"SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning","created":"2021-10-19","cited_by_count":30},{"id":"2106.06091","title":"DECORE: Deep Compression with Reinforcement Learning","created":"2021-06-11","cited_by_count":29},{"id":"2011.12641","title":"Auto Graph Encoder-Decoder for Neural Network Pruning","created":"2020-11-25","cited_by_count":26},{"id":"2108.04890","title":"On the Effect of Pruning on Adversarial Robustness","created":"2021-08-10","cited_by_count":23},{"id":"2104.11883","title":"Carrying out CNN Channel Pruning in a White Box","created":"2021-04-24","cited_by_count":22},{"id":"2310.01755","title":"ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms","created":"2023-10-03","cited_by_count":22},{"id":"2011.02166","title":"DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search","created":"2020-11-04","cited_by_count":21},{"id":"2403.14729","title":"Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch","created":"2024-03-21","cited_by_count":20},{"id":"2206.00843","title":"DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks","created":"2022-06-02","cited_by_count":19},{"id":"2211.11665","title":"Representational dissimilarity metric spaces for stochastic neural networks","created":"2022-11-21","cited_by_count":17},{"id":"2306.14306","title":"Adaptive Sharpness-Aware Pruning for Robust Sparse Networks","created":"2023-06-25","cited_by_count":17},{"id":"2202.07190","title":"Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters","created":"2022-02-15","cited_by_count":16},{"id":"2106.09309","title":"Layer Folding: Neural Network Depth Reduction using Activation Linearization","created":"2021-06-17","cited_by_count":14},{"id":"2206.07311","title":"Can pruning improve certified robustness of neural networks?","created":"2022-06-15","cited_by_count":14},{"id":"2107.05033","title":"Blending Pruning Criteria for Convolutional Neural Networks","created":"2021-07-11","cited_by_count":13},{"id":"2401.06426","title":"UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer","created":"2024-01-12","cited_by_count":9},{"id":"2403.19490","title":"Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment","created":"2024-03-28","cited_by_count":9},{"id":"2405.17081","title":"Effective Layer Pruning Through Similarity Metric Perspective","created":"2024-05-27","cited_by_count":6},{"id":"2405.20876","title":"Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Study","created":"2024-05-31","cited_by_count":5},{"id":"2212.01957","title":"CSTAR: Towards Compact and STructured Deep Neural Networks with Adversarial Robustness","created":"2022-12-04","cited_by_count":4},{"id":"2301.10835","title":"When Layers Play the Lottery, all Tickets Win at Initialization","created":"2023-01-25","cited_by_count":3}],"next_cursor":null}