{"list":"other","total":64,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2309.03409","title":"Large Language Models as Optimizers","created":"2023-09-07","cited_by_count":864},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571},{"id":"2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","created":"2023-09-28","cited_by_count":551},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"1604.00772","title":"The CMA Evolution Strategy: A Tutorial","created":"2016-04-04","cited_by_count":377},{"id":"2305.16367","title":"Role-Play with Large Language Models","created":"2023-05-25","cited_by_count":294},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256},{"id":"1912.12854","title":"Pareto Multi-Task Learning","created":"2019-12-30","cited_by_count":224},{"id":"2302.06692","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models","created":"2023-02-13","cited_by_count":187},{"id":"2103.11790","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","created":"2021-03-08","cited_by_count":178},{"id":"2212.10789","title":"Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing","created":"2022-12-21","cited_by_count":166},{"id":"1909.00015","title":"Adaptively Sparse Transformers","created":"2019-08-30","cited_by_count":155},{"id":"2309.01446","title":"Open Sesame! Universal Black Box Jailbreaking of Large Language Models","created":"2023-09-04","cited_by_count":134},{"id":"2302.14838","title":"EvoPrompting: Language Models for Code-Level Neural Architecture Search","created":"2023-02-28","cited_by_count":131},{"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":"2310.19046","title":"Large Language Models as Evolutionary Optimizers","created":"2023-10-29","cited_by_count":124},{"id":"2302.12170","title":"Language Model Crossover: Variation through Few-Shot Prompting","created":"2023-02-23","cited_by_count":122},{"id":"2110.14378","title":"Towards artificial general intelligence via a multimodal foundation model","created":"2021-10-27","cited_by_count":112},{"id":"2002.07028","title":"Low-Rank Bottleneck in Multi-head Attention Models","created":"2020-02-17","cited_by_count":89},{"id":"2308.04748","title":"Fuzz4All: Universal Fuzzing with Large Language Models","created":"2023-08-09","cited_by_count":88},{"id":"2306.01102","title":"LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization","created":"2023-06-01","cited_by_count":87},{"id":"2306.06283","title":"14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon","created":"2023-06-09","cited_by_count":86},{"id":"2305.02499","title":"AutoML-GPT: Automatic Machine Learning with GPT","created":"2023-05-04","cited_by_count":81},{"id":"2304.10970","title":"Can GPT-4 Perform Neural Architecture Search?","created":"2023-04-21","cited_by_count":74},{"id":"2312.04528","title":"Using Large Language Models for Hyperparameter Optimization","created":"2023-12-07","cited_by_count":71},{"id":"1911.04474","title":"TENER: Adapting Transformer Encoder for Named Entity Recognition","created":"2019-11-10","cited_by_count":69},{"id":"2302.05981","title":"MarioGPT: Open-Ended Text2Level Generation through Large Language Models","created":"2023-02-12","cited_by_count":64},{"id":"2205.11200","title":"BBTv2: Towards a Gradient-Free Future with Large Language Models","created":"2022-05-23","cited_by_count":53},{"id":"1911.12809","title":"Greed is Good: Exploration and Exploitation Trade-offs in Bayesian Optimisation","created":"2019-11-28","cited_by_count":51},{"id":"2211.11260","title":"Discovering Evolution Strategies via Meta-Black-Box Optimization","created":"2022-11-21","cited_by_count":44},{"id":"2310.13032","title":"Quality-Diversity through AI Feedback","created":"2023-10-19","cited_by_count":40},{"id":"2304.03995","title":"Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization","created":"2023-04-08","cited_by_count":33},{"id":"2304.05818","title":"Gradient-Free Textual Inversion","created":"2023-04-12","cited_by_count":29},{"id":"2310.12541","title":"Large Language Model for Multi-objective Evolutionary Optimization","created":"2023-10-19","cited_by_count":29},{"id":"2310.01467","title":"FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models","created":"2023-10-02","cited_by_count":26},{"id":"2310.13127","title":"Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models","created":"2023-10-19","cited_by_count":21},{"id":"2105.15089","title":"Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model","created":"2021-05-31","cited_by_count":20},{"id":"2303.02155","title":"ChatGPT and Other Large Language Models as Evolutionary Engines for Online Interactive Collaborative Game Design","created":"2023-02-09","cited_by_count":20},{"id":"2310.12774","title":"Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning","created":"2023-10-19","cited_by_count":17},{"id":"2304.11787","title":"B2Opt: Learning to Optimize Black-box Optimization with Little Budget","created":"2023-04-24","cited_by_count":15},{"id":"2310.01260","title":"SPELL: Semantic Prompt Evolution based on a LLM","created":"2023-10-02","cited_by_count":15},{"id":"2306.03263","title":"Efficient automatic design of robots","created":"2023-06-05","cited_by_count":14},{"id":"2310.19813","title":"Enhancing Genetic Improvement Mutations Using Large Language Models","created":"2023-10-18","cited_by_count":13},{"id":"2307.02839","title":"Enhancing LLM with Evolutionary Fine Tuning for News Summary Generation","created":"2023-07-06","cited_by_count":10},{"id":"2305.00593","title":"Reliable Gradient-free and Likelihood-free Prompt Tuning","created":"2023-04-30","cited_by_count":8},{"id":"2205.00671","title":"Jack and Masters of all Trades: One-Pass Learning Sets of Model Sets From Large Pre-Trained Models","created":"2022-05-02","cited_by_count":5},{"id":"2304.08503","title":"A Scalable Test Problem Generator for Sequential Transfer Optimization","created":"2023-04-17","cited_by_count":5},{"id":"2305.03518","title":"Black-box Prompt Tuning with Subspace Learning","created":"2023-05-04","cited_by_count":5},{"id":"2305.08088","title":"Make Prompt-based Black-Box Tuning Colorful: Boosting Model Generalization from Three Orthogonal Perspectives","created":"2023-05-14","cited_by_count":5},{"id":"2305.10013","title":"When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario","created":"2023-05-17","cited_by_count":5},{"id":"2105.09045","title":"Do Models Learn the Directionality of Relations? A New Evaluation: Relation Direction Recognition","created":"2021-05-19","cited_by_count":2},{"id":"2312.06125","title":"Enhancing Generalization and Scalability for Multi-Objective Optimization with Population Pre-Training","created":"2023-12-11","cited_by_count":2},{"id":"2006.05676","title":"Position Masking for Language Models","created":"2020-06-02","cited_by_count":1},{"id":"2302.01435","title":"Target specific peptide design using latent space approximate trajectory collector","created":"2023-02-02","cited_by_count":1}],"next_cursor":null}