{"list":"other","total":51,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"1603.06560","title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","created":"2016-03-21","cited_by_count":699},{"id":"1804.05685","title":"A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents","created":"2018-04-16","cited_by_count":478},{"id":"1807.01774","title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale","created":"2018-07-04","cited_by_count":470},{"id":"2210.14896","title":"DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models","created":"2022-10-26","cited_by_count":379},{"id":"2302.12813","title":"Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback","created":"2023-02-24","cited_by_count":353},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336},{"id":"2309.00941","title":"Emergent Linear Representations in World Models of Self-Supervised Sequence Models","created":"2023-09-02","cited_by_count":319},{"id":"2310.11564","title":"Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging","created":"2023-10-17","cited_by_count":280},{"id":"2011.10369","title":"ONION: A Simple and Effective Defense Against Textual Backdoor Attacks","created":"2020-11-20","cited_by_count":263},{"id":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260},{"id":"2312.01552","title":"The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning","created":"2023-12-04","cited_by_count":257},{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234},{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208},{"id":"2402.17193","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","created":"2024-02-27","cited_by_count":204},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202},{"id":"2301.12314","title":"Progressive Prompts: Continual Learning for Language Models","created":"2023-01-29","cited_by_count":197},{"id":"2010.05700","title":"Reformulating Unsupervised Style Transfer as Paraphrase Generation","created":"2020-10-12","cited_by_count":183},{"id":"2007.04074","title":"Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning","created":"2020-07-08","cited_by_count":174},{"id":"2011.00416","title":"Deep Learning for Text Style Transfer: A Survey","created":"2020-11-01","cited_by_count":162},{"id":"2004.03329","title":"MedDialog: Two Large-scale Medical Dialogue Datasets","created":"2020-04-07","cited_by_count":161},{"id":"2212.10375","title":"Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering","created":"2022-12-20","cited_by_count":161},{"id":"1710.00942","title":"Neural Trojans","created":"2017-10-03","cited_by_count":153},{"id":"2309.11325","title":"DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services","created":"2023-09-20","cited_by_count":120},{"id":"2002.12418","title":"MNN: A Universal and Efficient Inference Engine","created":"2020-02-27","cited_by_count":65},{"id":"2302.14233","title":"Goal Driven Discovery of Distributional Differences via Language Descriptions","created":"2023-02-28","cited_by_count":62},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62},{"id":"1906.00531","title":"Model selection for contextual bandits","created":"2019-06-03","cited_by_count":60},{"id":"2201.12323","title":"Describing Differences between Text Distributions with Natural Language","created":"2022-01-28","cited_by_count":54},{"id":"2203.02113","title":"FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context","created":"2022-03-04","cited_by_count":49},{"id":"2302.14383","title":"Linear Spaces of Meanings: Compositional Structures in Vision-Language Models","created":"2023-02-28","cited_by_count":48},{"id":"2310.16410","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","created":"2023-10-25","cited_by_count":42},{"id":"1703.02629","title":"Online Learning Without Prior Information","created":"2017-03-07","cited_by_count":36},{"id":"1801.00101","title":"Parameter-free online learning via model selection","created":"2017-12-30","cited_by_count":34},{"id":"2012.04371","title":"Efficient Automatic CASH via Rising Bandits","created":"2020-12-08","cited_by_count":31},{"id":"2403.19390","title":"Checkpoint Merging via Bayesian Optimization in LLM Pretraining","created":"2024-03-28","cited_by_count":27},{"id":"2010.09818","title":"Online Active Model Selection for Pre-trained Classifiers","created":"2020-10-19","cited_by_count":20},{"id":"2312.14229","title":"Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI","created":"2023-12-21","cited_by_count":17},{"id":"2309.13192","title":"Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation","created":"2023-09-22","cited_by_count":12},{"id":"2312.14227","title":"ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection","created":"2023-12-21","cited_by_count":12},{"id":"2404.12926","title":"MM-PhyRLHF: Reinforcement Learning Framework for Multimodal Physics Question-Answering","created":"2024-04-19","cited_by_count":6},{"id":"1411.6382","title":"Mid-level Deep Pattern Mining","created":"2014-11-24","cited_by_count":3},{"id":"2407.11059","title":"Was it Slander? Towards Exact Inversion of Generative Language Models","created":"2024-07-10","cited_by_count":3},{"id":"2503.01611","title":"In-context Learning vs. Instruction Tuning: The Case of Small and Multilingual Language Models","created":"2025-03-03","cited_by_count":3}],"next_cursor":null}