{"list":"other","total":51,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1603.04467","title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","created":"2016-03-14","cited_by_count":664},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415},{"id":"2211.06220","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","created":"2022-11-10","cited_by_count":328},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322},{"id":"1511.05641","title":"Net2Net: Accelerating Learning via Knowledge Transfer","created":"2015-11-18","cited_by_count":250},{"id":"1911.13299","title":"What's Hidden in a Randomly Weighted Neural Network?","created":"2019-11-29","cited_by_count":237},{"id":"1711.05908","title":"NISP: Pruning Networks using Neuron Importance Score Propagation","created":"2017-11-16","cited_by_count":228},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"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":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183},{"id":"2407.14679","title":"Compact Language Models via Pruning and Knowledge Distillation","created":"2024-07-19","cited_by_count":148},{"id":"2402.11187","title":"LaCo: Large Language Model Pruning via Layer Collapse","created":"2024-02-17","cited_by_count":126},{"id":"2312.11983","title":"Fluctuation-based Adaptive Structured Pruning for Large Language Models","created":"2023-12-19","cited_by_count":111},{"id":"2210.06707","title":"Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer","created":"2022-10-13","cited_by_count":108},{"id":"2310.19444","title":"One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation","created":"2023-10-30","cited_by_count":78},{"id":"2110.04869","title":"Global Vision Transformer Pruning with Hessian-Aware Saliency","created":"2021-10-10","cited_by_count":70},{"id":"2303.04935","title":"X-Pruner: eXplainable Pruning for Vision Transformers","created":"2023-03-08","cited_by_count":68},{"id":"2302.02210","title":"Oscillation-free Quantization for Low-bit Vision Transformers","created":"2023-02-04","cited_by_count":57},{"id":"2205.13574","title":"Pruning has a disparate impact on model accuracy","created":"2022-05-26","cited_by_count":44},{"id":"2412.18110","title":"SlimGPT: Layer-wise Structured Pruning for Large Language Models","created":"2024-12-24","cited_by_count":44},{"id":"2203.12217","title":"Training-free Transformer Architecture Search","created":"2022-03-23","cited_by_count":33},{"id":"2403.12422","title":"Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization","created":"2024-03-19","cited_by_count":31},{"id":"2210.02412","title":"Why Random Pruning Is All We Need to Start Sparse","created":"2022-10-05","cited_by_count":26},{"id":"2501.01709","title":"MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders","created":"2025-01-03","cited_by_count":26},{"id":"2405.17245","title":"Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer Inference","created":"2024-05-27","cited_by_count":25},{"id":"2412.06647","title":"Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset","created":"2024-12-09","cited_by_count":25},{"id":"2412.12441","title":"Numerical Pruning for Efficient Autoregressive Models","created":"2024-12-17","cited_by_count":25},{"id":"2010.13160","title":"Neuron Merging: Compensating for Pruned Neurons","created":"2020-10-25","cited_by_count":24},{"id":"2407.06794","title":"Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction","created":"2024-07-09","cited_by_count":23},{"id":"2308.06619","title":"Can Unstructured Pruning Reduce the Depth in Deep Neural Networks?","created":"2023-08-12","cited_by_count":20},{"id":"2303.07129","title":"AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments","created":"2023-03-13","cited_by_count":19},{"id":"2308.06689","title":"Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training","created":"2023-08-13","cited_by_count":19},{"id":"2308.10561","title":"Spatial Transform Decoupling for Oriented Object Detection","created":"2023-08-21","cited_by_count":12},{"id":"2408.04413","title":"Deeploy: Enabling Energy-Efficient Deployment of Small Language Models On Heterogeneous Microcontrollers","created":"2024-08-08","cited_by_count":11},{"id":"2403.18708","title":"Dense Vision Transformer Compression with Few Samples","created":"2024-03-27","cited_by_count":9},{"id":"2305.07772","title":"Monitoring and Adapting ML Models on Mobile Devices","created":"2023-05-12","cited_by_count":6},{"id":"2504.02168","title":"MDP: Multidimensional Vision Model Pruning with Latency Constraint","created":"2025-04-02","cited_by_count":5},{"id":"2502.10047","title":"Janus: Collaborative Vision Transformer Under Dynamic Network Environment","created":"2025-02-14","cited_by_count":4}],"next_cursor":null}