{"list":"other","total":79,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1708.03999","title":"ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models","created":"2017-08-14","cited_by_count":666},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"id":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403},{"id":"1808.09121","title":"WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations","created":"2018-08-28","cited_by_count":372},{"id":"1804.08838","title":"Measuring the Intrinsic Dimension of Objective Landscapes","created":"2018-04-24","cited_by_count":370},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366},{"id":"1901.10159","title":"An Investigation into Neural Net Optimization via Hessian Eigenvalue Density","created":"2019-01-29","cited_by_count":292},{"id":"1912.07145","title":"PyHessian: Neural Networks Through the Lens of the Hessian","created":"2019-12-16","cited_by_count":292},{"id":"1706.04454","title":"Empirical Analysis of the Hessian of Over-Parametrized Neural Networks","created":"2017-06-14","cited_by_count":290},{"id":"2202.01279","title":"PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts","created":"2022-02-02","cited_by_count":289},{"id":"2212.13345","title":"The Forward-Forward Algorithm: Some Preliminary Investigations","created":"2022-12-27","cited_by_count":266},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256},{"id":"2004.08249","title":"Understanding the Difficulty of Training Transformers","created":"2020-04-17","cited_by_count":210},{"id":"1810.12885","title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","created":"2018-10-30","cited_by_count":200},{"id":"1312.2139","title":"Optimal rates for zero-order convex optimization: the power of two function evaluations","created":"2013-12-07","cited_by_count":198},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180},{"id":"2006.06224","title":"A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning","created":"2020-06-11","cited_by_count":162},{"id":"2203.07281","title":"GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models","created":"2022-03-14","cited_by_count":127},{"id":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121},{"id":"1507.08752","title":"An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback","created":"2015-07-31","cited_by_count":111},{"id":"1805.10367","title":"Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization","created":"2018-05-25","cited_by_count":111},{"id":"2008.11865","title":"Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra","created":"2020-08-27","cited_by_count":94},{"id":"2102.12470","title":"On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)","created":"2021-02-24","cited_by_count":73},{"id":"2010.03648","title":"A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks","created":"2020-10-07","cited_by_count":72},{"id":"2201.08531","title":"Black-box Prompt Learning for Pre-trained Language Models","created":"2022-01-21","cited_by_count":70},{"id":"1710.10551","title":"Stochastic Zeroth-order Optimization in High Dimensions","created":"2017-10-29","cited_by_count":63},{"id":"2205.11200","title":"BBTv2: Towards a Gradient-Free Future with Large Language Models","created":"2022-05-23","cited_by_count":53},{"id":"1910.12166","title":"Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization","created":"2019-10-27","cited_by_count":47},{"id":"2003.13001","title":"Zeroth-Order Regularized Optimization (ZORO): Approximately Sparse Gradients and Adaptive Sampling","created":"2020-03-29","cited_by_count":46},{"id":"2102.10707","title":"A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization","created":"2021-02-21","cited_by_count":46},{"id":"2010.04261","title":"Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks","created":"2020-10-08","cited_by_count":45},{"id":"1911.06317","title":"Gradientless Descent: High-Dimensional Zeroth-Order Optimization","created":"2019-11-14","cited_by_count":43},{"id":"1809.06474","title":"Zeroth-order Nonconvex Stochastic Optimization: Handling Constraints, High-Dimensionality and Saddle-Points","created":"2018-09-17","cited_by_count":37},{"id":"2212.09257","title":"PromptBoosting: Black-Box Text Classification with Ten Forward Passes","created":"2022-12-19","cited_by_count":36},{"id":"2303.03751","title":"Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles","created":"2023-03-07","cited_by_count":35},{"id":"1706.06197","title":"meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting","created":"2017-06-19","cited_by_count":34},{"id":"1710.11258","title":"Adaptive Sampling Strategies for Stochastic Optimization","created":"2017-10-30","cited_by_count":30},{"id":"2202.00980","title":"Robust Training of Neural Networks Using Scale Invariant Architectures","created":"2022-02-02","cited_by_count":29},{"id":"2007.10412","title":"Randomized Automatic Differentiation","created":"2020-07-20","cited_by_count":23},{"id":"2305.13016","title":"Iterative Forward Tuning Boosts In-Context Learning in Language Models","created":"2023-05-22","cited_by_count":15},{"id":"1805.08079","title":"Faster Neural Network Training with Approximate Tensor Operations","created":"2018-05-21","cited_by_count":14},{"id":"1812.11377","title":"Hessian-Aware Zeroth-Order Optimization for Black-Box Adversarial Attack","created":"2018-12-29","cited_by_count":14},{"id":"2006.10820","title":"A New One-Point Residual-Feedback Oracle For Black-Box Learning and Control","created":"2020-06-18","cited_by_count":14},{"id":"2210.12050","title":"Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards","created":"2022-10-21","cited_by_count":14},{"id":"1709.05804","title":"Minimal Effort Back Propagation for Convolutional Neural Networks","created":"2017-09-18","cited_by_count":7},{"id":"1904.04650","title":"Gradient-Free Multi-Agent Nonconvex Nonsmooth Optimization","created":"2019-04-09","cited_by_count":4},{"id":"1908.11444","title":"Distributed Zero-Order Algorithms for Nonconvex Multi-Agent Optimization","created":"2019-08-29","cited_by_count":4}],"next_cursor":null}