{"list":"other","total":51,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"2309.03409","title":"Large Language Models as Optimizers","created":"2023-09-07","cited_by_count":864},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500},{"id":"1811.09621","title":"GuacaMol: Benchmarking Models for De Novo Molecular Design","created":"2018-11-22","cited_by_count":297},{"id":"2111.09266","title":"GFlowNet Foundations","created":"2021-11-17","cited_by_count":290},{"id":"1704.07555","title":"Molecular De Novo Design through Deep Reinforcement Learning","created":"2017-04-25","cited_by_count":267},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"2307.04721","title":"Large Language Models as General Pattern Machines","created":"2023-07-10","cited_by_count":197},{"id":"2206.12411","title":"Sample Efficiency Matters: A Benchmark for Practical Molecular Optimization","created":"2022-06-22","cited_by_count":155},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148},{"id":"2402.03921","title":"Large Language Models to Enhance Bayesian Optimization","created":"2024-02-06","cited_by_count":135},{"id":"2206.08896","title":"Evolution through Large Models","created":"2022-06-17","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":"2207.04179","title":"Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling","created":"2022-07-09","cited_by_count":127},{"id":"2302.12170","title":"Language Model Crossover: Variation through Few-Shot Prompting","created":"2023-02-23","cited_by_count":122},{"id":"1901.10060","title":"Conditioning by adaptive sampling for robust design","created":"2019-01-29","cited_by_count":111},{"id":"1801.07299","title":"Multi-Objective De Novo Drug Design with Conditional Graph Generative Model","created":"2018-01-18","cited_by_count":101},{"id":"2310.07276","title":"BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations","created":"2023-10-11","cited_by_count":100},{"id":"2205.13320","title":"Towards Learning Universal Hyperparameter Optimizers with Transformers","created":"2022-05-26","cited_by_count":81},{"id":"1509.01066","title":"Safe Controller Optimization for Quadrotors with Gaussian Processes","created":"2015-09-03","cited_by_count":78},{"id":"2306.07180","title":"Diffusion Models for Black-Box Optimization","created":"2023-06-12","cited_by_count":76},{"id":"2312.04528","title":"Using Large Language Models for Hyperparameter Optimization","created":"2023-12-07","cited_by_count":71},{"id":"2406.16976","title":"Efficient Evolutionary Search Over Chemical Space with Large Language Models","created":"2024-06-23","cited_by_count":61},{"id":"2401.10334","title":"DrugAssist: A Large Language Model for Molecule Optimization","created":"2023-12-28","cited_by_count":59},{"id":"2402.05015","title":"A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?","created":"2024-02-07","cited_by_count":48},{"id":"2206.10786","title":"Generative Pretraining for Black-Box Optimization","created":"2022-06-22","cited_by_count":36},{"id":"2302.05738","title":"Cross-Modal Fine-Tuning: Align then Refine","created":"2023-02-11","cited_by_count":34},{"id":"2402.10980","title":"ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback","created":"2024-02-15","cited_by_count":33},{"id":"2305.18090","title":"ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback","created":"2023-05-29","cited_by_count":31},{"id":"2310.12541","title":"Large Language Model for Multi-objective Evolutionary Optimization","created":"2023-10-19","cited_by_count":29},{"id":"1905.01334","title":"Data-efficient Learning of Morphology and Controller for a Microrobot","created":"2019-05-03","cited_by_count":26},{"id":"2311.12410","title":"nach0: Multimodal Natural and Chemical Languages Foundation Model","created":"2023-11-21","cited_by_count":26},{"id":"2405.16434","title":"The Importance of Directional Feedback for LLM-based Optimizers","created":"2024-05-26","cited_by_count":26},{"id":"2310.19961","title":"ExPT: Synthetic Pretraining for Few-Shot Experimental Design","created":"2023-10-30","cited_by_count":22},{"id":"2305.16160","title":"Augmented Memory: Capitalizing on Experience Replay to Accelerate De Novo Molecular Design","created":"2023-05-10","cited_by_count":8}],"next_cursor":null}