{"list":"other","total":69,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"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":"1804.08598","title":"Black-box Adversarial Attacks with Limited Queries and Information","created":"2018-04-23","cited_by_count":501},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"2101.06840","title":"ZeRO-Offload: Democratizing Billion-Scale Model Training","created":"2021-01-18","cited_by_count":341},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"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":"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":"2108.02035","title":"Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification","created":"2021-08-04","cited_by_count":183},{"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":"2004.03829","title":"Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning","created":"2020-04-08","cited_by_count":139},{"id":"1608.05343","title":"Decoupled Neural Interfaces using Synthetic Gradients","created":"2016-08-18","cited_by_count":137},{"id":"1805.11770","title":"AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks","created":"2018-05-30","cited_by_count":137},{"id":"1901.06656","title":"Training Neural Networks with Local Error Signals","created":"2019-01-20","cited_by_count":136},{"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":"1909.10773","title":"Sign-OPT: A Query-Efficient Hard-label Adversarial Attack","created":"2019-09-24","cited_by_count":120},{"id":"1805.10367","title":"Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization","created":"2018-05-25","cited_by_count":111},{"id":"2007.08714","title":"Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources","created":"2020-07-17","cited_by_count":83},{"id":"1910.06513","title":"ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization","created":"2019-10-15","cited_by_count":76},{"id":"2310.02025","title":"DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training","created":"2023-10-03","cited_by_count":76},{"id":"2202.08587","title":"Gradients without Backpropagation","created":"2022-02-17","cited_by_count":73},{"id":"2302.08106","title":"Towards Efficient Visual Adaption via Structural Re-parameterization","created":"2023-02-16","cited_by_count":73},{"id":"2210.03310","title":"Scaling Forward Gradient With Local Losses","created":"2022-10-07","cited_by_count":65},{"id":"1710.10551","title":"Stochastic Zeroth-order Optimization in High Dimensions","created":"2017-10-29","cited_by_count":63},{"id":"2011.01921","title":"Optimizing Molecules using Efficient Queries from Property Evaluations","created":"2020-11-03","cited_by_count":50},{"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":"1906.00117","title":"Model Agnostic Contrastive Explanations for Structured Data","created":"2019-05-31","cited_by_count":41},{"id":"2008.08170","title":"Accelerated Zeroth-Order and First-Order Momentum Methods from Mini to Minimax Optimization","created":"2020-08-18","cited_by_count":40},{"id":"2203.14195","title":"How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective","created":"2022-03-27","cited_by_count":39},{"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":"2110.06609","title":"MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators","created":"2021-10-13","cited_by_count":35},{"id":"1901.11503","title":"Contrasting Exploration in Parameter and Action Space: A Zeroth-Order Optimization Perspective","created":"2019-01-31","cited_by_count":27},{"id":"2012.11148","title":"Efficient On-Chip Learning for Optical Neural Networks Through Power-Aware Sparse Zeroth-Order Optimization","created":"2020-12-21","cited_by_count":24},{"id":"2107.10110","title":"On the Convergence of Prior-Guided Zeroth-Order Optimization Algorithms","created":"2021-07-21","cited_by_count":23},{"id":"1907.11684","title":"On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method","created":"2019-07-26","cited_by_count":21},{"id":"2212.00824","title":"On-device Training: A First Overview on Existing Systems","created":"2022-12-01","cited_by_count":19},{"id":"1812.11377","title":"Hessian-Aware Zeroth-Order Optimization for Black-Box Adversarial Attack","created":"2018-12-29","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":"2102.09026","title":"Optimizing Large-Scale Hyperparameters via Automated Learning Algorithm","created":"2021-02-17","cited_by_count":13},{"id":"2106.08453","title":"How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective","created":"2021-06-15","cited_by_count":13},{"id":"2209.06302","title":"Optimization without Backpropagation","created":"2022-09-13","cited_by_count":11},{"id":"2304.06430","title":"Certified Zeroth-order Black-Box Defense with Robust UNet Denoiser","created":"2023-04-13","cited_by_count":11},{"id":"1910.05268","title":"Improving Gradient Estimation in Evolutionary Strategies With Past Descent Directions","created":"2019-10-11","cited_by_count":8},{"id":"2006.01759","title":"Sparse Perturbations for Improved Convergence in Stochastic Zeroth-Order Optimization","created":"2020-06-02","cited_by_count":8},{"id":"2202.00774","title":"Accelerating DNN Training with Structured Data Gradient Pruning","created":"2022-02-01","cited_by_count":8},{"id":"2109.13391","title":"Curvature-Aware Derivative-Free Optimization","created":"2021-09-27","cited_by_count":7},{"id":"2304.11153","title":"Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single","created":"2023-04-21","cited_by_count":7},{"id":"2312.04709","title":"How to guess a gradient","created":"2023-12-07","cited_by_count":7},{"id":"2206.02785","title":"Zeroth-Order SciML: Non-intrusive Integration of Scientific Software with Deep Learning","created":"2022-06-04","cited_by_count":4},{"id":"1811.03733","title":"Universal Decision-Based Black-Box Perturbations: Breaking Security-Through-Obscurity Defenses","created":"2018-11-09","cited_by_count":3}],"next_cursor":null}