{"list":"other","total":62,"rows":[{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"2004.05937","title":"Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks","created":"2020-04-13","cited_by_count":316},{"id":"2307.15190","title":"f-Divergence Minimization for Sequence-Level Knowledge Distillation","created":"2023-07-27","cited_by_count":114},{"id":"2002.03532","title":"Understanding and Improving Knowledge Distillation","created":"2020-02-10","cited_by_count":83},{"id":"2404.02657","title":"Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models","created":"2024-04-03","cited_by_count":65},{"id":"2402.12030","title":"Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs","created":"2024-02-19","cited_by_count":63},{"id":"1908.01851","title":"Self-Knowledge Distillation in Natural Language Processing","created":"2019-08-02","cited_by_count":60},{"id":"2407.01885","title":"Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application","created":"2024-07-02","cited_by_count":56},{"id":"2102.12252","title":"Localization Distillation for Dense Object Detection","created":"2021-02-24","cited_by_count":55},{"id":"2112.04840","title":"Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation","created":"2021-12-09","cited_by_count":40},{"id":"2109.08359","title":"Distilling Linguistic Context for Language Model Compression","created":"2021-09-17","cited_by_count":33},{"id":"2007.09029","title":"Knowledge Distillation in Deep Learning and its Applications","created":"2020-07-17","cited_by_count":29},{"id":"2008.01458","title":"Prime-Aware Adaptive Distillation","created":"2020-08-04","cited_by_count":28},{"id":"2108.07482","title":"G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation","created":"2021-08-17","cited_by_count":28},{"id":"2410.16215","title":"Pre-training Distillation for Large Language Models: A Design Space Exploration","created":"2024-10-21","cited_by_count":27},{"id":"2002.12620","title":"TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing","created":"2020-02-28","cited_by_count":26},{"id":"2104.08448","title":"Data Distillation for Text Classification","created":"2021-04-17","cited_by_count":25},{"id":"2302.09632","title":"HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers","created":"2023-02-19","cited_by_count":25},{"id":"2009.09152","title":"Weight Distillation: Transferring the Knowledge in Neural Network Parameters","created":"2020-09-19","cited_by_count":23},{"id":"2006.01683","title":"Channel Distillation: Channel-Wise Attention for Knowledge Distillation","created":"2020-06-02","cited_by_count":21},{"id":"2305.12954","title":"Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?","created":"2023-05-22","cited_by_count":21},{"id":"2012.15495","title":"Towards Zero-Shot Knowledge Distillation for Natural Language Processing","created":"2020-12-31","cited_by_count":20},{"id":"2112.02505","title":"Causal Distillation for Language Models","created":"2021-12-05","cited_by_count":19},{"id":"2106.04563","title":"XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation","created":"2021-06-08","cited_by_count":18},{"id":"2203.05469","title":"Prediction-Guided Distillation for Dense Object Detection","created":"2022-03-10","cited_by_count":14},{"id":"2208.14143","title":"FAKD: Feature Augmented Knowledge Distillation for Semantic Segmentation","created":"2022-08-30","cited_by_count":14},{"id":"2302.00444","title":"Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selection","created":"2023-02-01","cited_by_count":12},{"id":"2404.14827","title":"Sentence-Level or Token-Level? A Comprehensive Study on Knowledge Distillation","created":"2024-04-23","cited_by_count":12},{"id":"1912.13179","title":"Modeling Teacher-Student Techniques in Deep Neural Networks for Knowledge Distillation","created":"2019-12-31","cited_by_count":11},{"id":"2410.12259","title":"Optimizing YOLOv5s Object Detection through Knowledge Distillation algorithm","created":"2024-10-16","cited_by_count":11},{"id":"2308.09105","title":"Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation","created":"2023-08-17","cited_by_count":10},{"id":"1912.10850","title":"The State of Knowledge Distillation for Classification","created":"2019-12-20","cited_by_count":9},{"id":"2004.08116","title":"Triplet Loss for Knowledge Distillation","created":"2020-04-17","cited_by_count":9},{"id":"2305.15032","title":"How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives","created":"2023-05-24","cited_by_count":9},{"id":"1912.01540","title":"QUEST: Quantized embedding space for transferring knowledge","created":"2019-12-03","cited_by_count":7},{"id":"2110.04741","title":"Enhance Long Text Understanding via Distilled Gist Detector from Abstractive Summarization","created":"2021-10-10","cited_by_count":6},{"id":"2402.09282","title":"Leveraging Large Language Models for Enhanced NLP Task Performance through Knowledge Distillation and Optimized Training Strategies","created":"2024-02-14","cited_by_count":6},{"id":"2006.00844","title":"Distilling Neural Networks for Greener and Faster Dependency Parsing","created":"2020-06-01","cited_by_count":5},{"id":"2208.10169","title":"Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation","created":"2022-08-22","cited_by_count":5},{"id":"2211.01071","title":"Gradient Knowledge Distillation for Pre-trained Language Models","created":"2022-11-02","cited_by_count":5},{"id":"2406.13114","title":"Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation","created":"2024-06-19","cited_by_count":5},{"id":"2407.13254","title":"Make a Strong Teacher with Label Assistance: A Novel Knowledge Distillation Approach for Semantic Segmentation","created":"2024-07-18","cited_by_count":5},{"id":"1703.07131","title":"Knowledge distillation using unlabeled mismatched images","created":"2017-03-21","cited_by_count":4},{"id":"2201.11097","title":"Adaptive Instance Distillation for Object Detection in Autonomous Driving","created":"2022-01-26","cited_by_count":4},{"id":"2401.01234","title":"Mixture cure semiparametric additive hazard models under partly interval censoring -- a penalized likelihood approach","created":"2024-01-02","cited_by_count":4},{"id":"2406.16524","title":"The Privileged Students: On the Value of Initialization in Multilingual Knowledge Distillation","created":"2024-06-24","cited_by_count":4},{"id":"2408.11407","title":"Domain-invariant Progressive Knowledge Distillation for UAV-based Object Detection","created":"2024-08-21","cited_by_count":4},{"id":"2409.12345","title":"Wing Optimisation for a tractor propeller driven Micro Aerial Vehicle","created":"2024-09-18","cited_by_count":4},{"id":"2307.01878","title":"KDSTM: Neural Semi-supervised Topic Modeling with Knowledge Distillation","created":"2023-07-04","cited_by_count":3},{"id":"1812.11587","title":"Sentiment Classification of Customer Reviews about Automobiles in Roman Urdu","created":"2018-12-30","cited_by_count":2},{"id":"2011.14554","title":"A Selective Survey on Versatile Knowledge Distillation Paradigm for Neural Network Models","created":"2020-11-30","cited_by_count":2},{"id":"2407.13952","title":"Knowledge Distillation Approaches for Accurate and Efficient Recommender System","created":"2024-07-19","cited_by_count":2},{"id":"2103.14337","title":"Hands-on Guidance for Distilling Object Detectors","created":"2021-03-26","cited_by_count":1},{"id":"2301.08130","title":"A Cohesive Distillation Architecture for Neural Language Models","created":"2023-01-12","cited_by_count":1},{"id":"2309.03659","title":"Towards Comparable Knowledge Distillation in Semantic Image Segmentation","created":"2023-09-07","cited_by_count":1},{"id":"2404.01699","title":"Task Integration Distillation for Object Detectors","created":"2024-04-02","cited_by_count":1},{"id":"2406.06999","title":"Teaching with Uncertainty: Unleashing the Potential of Knowledge Distillation in Object Detection","created":"2024-06-11","cited_by_count":1},{"id":"2407.02775","title":"MLKD-BERT: Multi-level Knowledge Distillation for Pre-trained Language Models","created":"2024-07-03","cited_by_count":1}],"next_cursor":null}