{"list":"other","total":66,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"1907.09682","title":"Similarity-Preserving Knowledge Distillation","created":"2019-07-23","cited_by_count":516},{"id":"1312.6184","title":"Do Deep Nets Really Need to be Deep?","created":"2013-12-21","cited_by_count":474},{"id":"1912.08795","title":"Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion","created":"2019-12-18","cited_by_count":423},{"id":"2306.04751","title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","created":"2023-06-07","cited_by_count":408},{"id":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388},{"id":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"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":"2012.09816","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","created":"2020-12-17","cited_by_count":297},{"id":"1812.02766","title":"Knockoff Nets: Stealing Functionality of Black-Box Models","created":"2018-12-06","cited_by_count":292},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279},{"id":"2009.07888","title":"Transfer Learning in Deep Reinforcement Learning: A Survey","created":"2020-09-16","cited_by_count":265},{"id":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260},{"id":"1911.03437","title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","created":"2019-11-08","cited_by_count":254},{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247},{"id":"1511.03643","title":"Unifying distillation and privileged information","created":"2015-11-11","cited_by_count":233},{"id":"2002.05715","title":"Self-Distillation Amplifies Regularization in Hilbert Space","created":"2020-02-13","cited_by_count":173},{"id":"2105.13093","title":"Towards Understanding Knowledge Distillation","created":"2021-05-27","cited_by_count":158},{"id":"2306.08543","title":"MiniLLM: On-Policy Distillation of Large Language Models","created":"2023-06-14","cited_by_count":139},{"id":"1710.07535","title":"Data-Free Knowledge Distillation for Deep Neural Networks","created":"2017-10-19","cited_by_count":136},{"id":"2105.08919","title":"Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation","created":"2021-05-19","cited_by_count":134},{"id":"1905.08114","title":"Zero-Shot Knowledge Distillation in Deep Networks","created":"2019-05-20","cited_by_count":121},{"id":"2102.00650","title":"Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective","created":"2021-02-01","cited_by_count":119},{"id":"2306.05544","title":"BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping","created":"2023-06-08","cited_by_count":98},{"id":"2009.05990","title":"Toward the Fundamental Limits of Imitation Learning","created":"2020-09-13","cited_by_count":96},{"id":"2210.01351","title":"Less is More: Task-aware Layer-wise Distillation for Language Model Compression","created":"2022-10-04","cited_by_count":93},{"id":"2010.11723","title":"Learning from Suboptimal Demonstration via Self-Supervised Reward Regression","created":"2020-10-17","cited_by_count":84},{"id":"2002.03532","title":"Understanding and Improving Knowledge Distillation","created":"2020-02-10","cited_by_count":83},{"id":"1803.00443","title":"Knowledge Transfer with Jacobian Matching","created":"2018-03-01","cited_by_count":76},{"id":"2003.03622","title":"Explaining Knowledge Distillation by Quantifying the Knowledge","created":"2020-03-07","cited_by_count":66},{"id":"2306.02231","title":"Fine-Tuning Language Models with Advantage-Induced Policy Alignment","created":"2023-06-04","cited_by_count":48},{"id":"2206.06067","title":"Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation","created":"2022-06-13","cited_by_count":41},{"id":"2302.00219","title":"Knowledge Distillation on Graphs: A Survey","created":"2023-02-01","cited_by_count":38},{"id":"2106.03310","title":"Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model","created":"2021-06-07","cited_by_count":37},{"id":"2104.05641","title":"Generalization bounds via distillation","created":"2021-04-12","cited_by_count":34},{"id":"2007.04239","title":"A Survey on Transfer Learning in Natural Language Processing","created":"2020-05-31","cited_by_count":33},{"id":"2010.10090","title":"Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher","created":"2020-10-20","cited_by_count":33},{"id":"2104.09732","title":"Knowledge Distillation as Semiparametric Inference","created":"2021-04-20","cited_by_count":29},{"id":"2003.13960","title":"Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model","created":"2020-03-31","cited_by_count":28},{"id":"2002.03936","title":"Subclass Distillation","created":"2020-02-10","cited_by_count":23},{"id":"2005.10419","title":"Why distillation helps: a statistical perspective","created":"2020-05-21","cited_by_count":21},{"id":"2301.12245","title":"Supervision Complexity and its Role in Knowledge Distillation","created":"2023-01-28","cited_by_count":19},{"id":"2207.12106","title":"Black-box Few-shot Knowledge Distillation","created":"2022-07-25","cited_by_count":14},{"id":"1901.09421","title":"Information-Theoretic Understanding of Population Risk Improvement with Model Compression","created":"2019-01-27","cited_by_count":11},{"id":"2305.15734","title":"On the Impact of Knowledge Distillation for Model Interpretability","created":"2023-05-25","cited_by_count":8},{"id":"2003.13438","title":"Analysis of Knowledge Transfer in Kernel Regime","created":"2020-03-30","cited_by_count":3}],"next_cursor":null}