{"list":"other","total":62,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2211.15661","title":"What learning algorithm is in-context learning? Investigations with linear models","created":"2022-11-28","cited_by_count":684},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384},{"id":"1707.09835","title":"Meta-SGD: Learning to Learn Quickly for Few-Shot Learning","created":"2017-07-31","cited_by_count":379},{"id":"2109.01247","title":"Do Prompt-Based Models Really Understand the Meaning of their Prompts?","created":"2021-09-02","cited_by_count":326},{"id":"1707.09564","title":"A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks","created":"2017-07-29","cited_by_count":314},{"id":"2310.15916","title":"In-Context Learning Creates Task Vectors","created":"2023-10-24","cited_by_count":312},{"id":"2306.04637","title":"Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection","created":"2023-06-07","cited_by_count":298},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293},{"id":"2306.00297","title":"Transformers learn to implement preconditioned gradient descent for in-context learning","created":"2023-06-01","cited_by_count":279},{"id":"2404.02948","title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models","created":"2024-04-03","cited_by_count":269},{"id":"2305.14160","title":"Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning","created":"2023-05-23","cited_by_count":236},{"id":"2212.10559","title":"Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers","created":"2022-12-20","cited_by_count":204},{"id":"1809.04444","title":"Hate Speech Dataset from a White Supremacy Forum","created":"2018-09-12","cited_by_count":198},{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172},{"id":"2101.06395","title":"Free Lunch for Few-shot Learning: Distribution Calibration","created":"2021-01-16","cited_by_count":165},{"id":"1912.03432","title":"Improved Few-Shot Visual Classification","created":"2019-12-07","cited_by_count":115},{"id":"1902.04552","title":"Infinite Mixture Prototypes for Few-Shot Learning","created":"2019-02-12","cited_by_count":99},{"id":"1909.00025","title":"Meta-Learning with Warped Gradient Descent","created":"2019-08-30","cited_by_count":98},{"id":"2310.08391","title":"How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?","created":"2023-10-12","cited_by_count":96},{"id":"1902.03356","title":"Meta-Curvature","created":"2019-02-09","cited_by_count":70},{"id":"2406.08447","title":"The Impact of Initialization on LoRA Finetuning Dynamics","created":"2024-06-12","cited_by_count":54},{"id":"2405.15179","title":"VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks","created":"2024-05-24","cited_by_count":52},{"id":"2406.05223","title":"CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning","created":"2024-06-07","cited_by_count":44},{"id":"2408.01367","title":"Transformers are Universal In-context Learners","created":"2024-08-02","cited_by_count":43},{"id":"2408.12186","title":"Transformers are Minimax Optimal Nonparametric In-Context Learners","created":"2024-08-22","cited_by_count":37},{"id":"2002.07933","title":"Improving Generalization by Controlling Label-Noise Information in Neural Network Weights","created":"2020-02-19","cited_by_count":35},{"id":"2402.14951","title":"In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization","created":"2024-02-22","cited_by_count":33},{"id":"2408.10159","title":"Customizing Language Models with Instance-wise LoRA for Sequential Recommendation","created":"2024-08-19","cited_by_count":32},{"id":"2305.17040","title":"A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks","created":"2023-05-26","cited_by_count":17},{"id":"2503.11609","title":"Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages","created":"2025-03-14","cited_by_count":17},{"id":"2404.11225","title":"In-Context Learning State Vector with Inner and Momentum Optimization","created":"2024-04-17","cited_by_count":15},{"id":"2210.05956","title":"Towards Theoretically Inspired Neural Initialization Optimization","created":"2022-10-12","cited_by_count":11},{"id":"2203.02711","title":"Meta Mirror Descent: Optimiser Learning for Fast Convergence","created":"2022-03-05","cited_by_count":7},{"id":"2408.07410","title":"Aquila2 Technical Report","created":"2024-08-14","cited_by_count":5},{"id":"2505.03827","title":"MISE: Meta-knowledge Inheritance for Social Media-Based Stressor Estimation","created":"2025-05-03","cited_by_count":3}],"next_cursor":null}