{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265},{"id":"2010.15875","title":"Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning","created":"2020-10-29","cited_by_count":216},{"id":"2405.18392","title":"Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations","created":"2024-05-28","cited_by_count":170},{"id":"1910.00643","title":"SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum","created":"2019-10-01","cited_by_count":121},{"id":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121},{"id":"1810.13243","title":"A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation","created":"2018-10-29","cited_by_count":110},{"id":"2402.11548","title":"KMMLU: Measuring Massive Multitask Language Understanding in Korean","created":"2024-02-18","cited_by_count":91},{"id":"2102.03315","title":"Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge","created":"2021-02-05","cited_by_count":80},{"id":"1412.7457","title":"Global convergence of the Heavy-ball method for convex optimization","created":"2014-12-23","cited_by_count":61},{"id":"1803.05591","title":"On the insufficiency of existing momentum schemes for Stochastic Optimization","created":"2018-03-15","cited_by_count":49},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41},{"id":"2405.20233","title":"Grokfast: Accelerated Grokking by Amplifying Slow Gradients","created":"2024-05-30","cited_by_count":41},{"id":"2407.07972","title":"Deconstructing What Makes a Good Optimizer for Language Models","created":"2024-07-10","cited_by_count":41},{"id":"1804.00325","title":"Aggregated Momentum: Stability Through Passive Damping","created":"2018-04-01","cited_by_count":36},{"id":"2002.10376","title":"The Two Regimes of Deep Network Training","created":"2020-02-24","cited_by_count":30},{"id":"2302.00849","title":"Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent","created":"2023-02-02","cited_by_count":25},{"id":"1504.01577","title":"From Averaging to Acceleration, There is Only a Step-size","created":"2015-04-07","cited_by_count":24},{"id":"1603.04136","title":"On the Influence of Momentum Acceleration on Online Learning","created":"2016-03-14","cited_by_count":24},{"id":"2307.11291","title":"Provable non-accelerations of the heavy-ball method","created":"2023-07-21","cited_by_count":12},{"id":"2403.05293","title":"Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks","created":"2024-03-08","cited_by_count":9},{"id":"2307.00631","title":"Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers","created":"2023-07-02","cited_by_count":6}],"next_cursor":null}