{"list":"other","total":64,"rows":[{"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"1902.06720","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","created":"2019-02-18","cited_by_count":738},{"id":"1711.00165","title":"Deep Neural Networks as Gaussian Processes","created":"2017-11-01","cited_by_count":622},{"id":"1906.03671","title":"Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds","created":"2019-06-09","cited_by_count":610},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"1707.02038","title":"A Tutorial on Thompson Sampling","created":"2017-07-07","cited_by_count":433},{"id":"1906.08158","title":"BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning","created":"2019-06-19","cited_by_count":432},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365},{"id":"1704.00445","title":"On Kernelized Multi-armed Bandits","created":"2017-04-03","cited_by_count":352},{"id":"2101.10382","title":"Curriculum Learning: A Survey","created":"2021-01-25","cited_by_count":259},{"id":"1704.03003","title":"Automated Curriculum Learning for Neural Networks","created":"2017-04-10","cited_by_count":257},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250},{"id":"1703.01968","title":"Max-value Entropy Search for Efficient Bayesian Optimization","created":"2017-03-06","cited_by_count":206},{"id":"2210.11466","title":"Surgical Fine-Tuning Improves Adaptation to Distribution Shifts","created":"2022-10-20","cited_by_count":205},{"id":"1406.2541","title":"Predictive Entropy Search for Efficient Global Optimization of Black-box Functions","created":"2014-06-10","cited_by_count":204},{"id":"2009.06966","title":"On Information Gain and Regret Bounds in Gaussian Process Bandits","created":"2020-09-15","cited_by_count":158},{"id":"1807.05614","title":"ANN-Benchmarks: A Benchmarking Tool for Approximate Nearest Neighbor Algorithms","created":"2018-07-15","cited_by_count":130},{"id":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121},{"id":"2210.15809","title":"Coverage-centric Coreset Selection for High Pruning Rates","created":"2022-10-28","cited_by_count":117},{"id":"1910.07153","title":"Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost","created":"2019-10-16","cited_by_count":114},{"id":"1906.08399","title":"Sequential Experimental Design for Transductive Linear Bandits","created":"2019-06-20","cited_by_count":91},{"id":"2203.06176","title":"More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize","created":"2022-03-11","cited_by_count":91},{"id":"2007.05864","title":"Bayesian Deep Ensembles via the Neural Tangent Kernel","created":"2020-07-11","cited_by_count":90},{"id":"1906.01930","title":"Approximate Inference Turns Deep Networks into Gaussian Processes","created":"2019-06-05","cited_by_count":89},{"id":"2305.18466","title":"Test-Time Training on Nearest Neighbors for Large Language Models","created":"2023-05-29","cited_by_count":88},{"id":"1711.00941","title":"Deep Active Learning over the Long Tail","created":"2017-11-02","cited_by_count":84},{"id":"2107.00717","title":"SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios","created":"2021-07-01","cited_by_count":84},{"id":"2102.03983","title":"Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning","created":"2021-02-08","cited_by_count":72},{"id":"2304.09355","title":"To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review","created":"2023-04-19","cited_by_count":72},{"id":"1509.07577","title":"A Review of Feature Selection Methods Based on Mutual Information","created":"2015-09-24","cited_by_count":67},{"id":"2304.08151","title":"Prediction-Oriented Bayesian Active Learning","created":"2023-04-17","cited_by_count":62},{"id":"2203.09410","title":"A Framework and Benchmark for Deep Batch Active Learning for Regression","created":"2022-03-17","cited_by_count":49},{"id":"2402.00396","title":"Efficient Exploration for LLMs","created":"2024-02-01","cited_by_count":45},{"id":"1610.07379","title":"Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation","created":"2016-10-24","cited_by_count":40},{"id":"2107.03144","title":"Neural Contextual Bandits without Regret","created":"2021-07-07","cited_by_count":40},{"id":"2204.08491","title":"Active Learning Helps Pretrained Models Learn the Intended Task","created":"2022-04-18","cited_by_count":33},{"id":"2206.08900","title":"Adapting the Linearised Laplace Model Evidence for Modern Deep Learning","created":"2022-06-17","cited_by_count":29},{"id":"2306.11589","title":"Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent","created":"2023-06-20","cited_by_count":27},{"id":"2007.00077","title":"Similarity Search for Efficient Active Learning and Search of Rare Concepts","created":"2020-06-30","cited_by_count":24},{"id":"2007.08949","title":"Probabilistic Active Meta-Learning","created":"2020-07-17","cited_by_count":23},{"id":"1911.03620","title":"Adaptivity in Adaptive Submodularity","created":"2019-11-09","cited_by_count":22},{"id":"2011.03178","title":"Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?","created":"2020-11-06","cited_by_count":21},{"id":"1703.02723","title":"Scalable Greedy Feature Selection via Weak Submodularity","created":"2017-03-08","cited_by_count":19},{"id":"2107.09912","title":"Design of Experiments for Stochastic Contextual Linear Bandits","created":"2021-07-21","cited_by_count":18},{"id":"1907.07384","title":"Feature Selection via Mutual Information: New Theoretical Insights","created":"2019-07-17","cited_by_count":17},{"id":"2303.17051","title":"Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentation","created":"2023-03-29","cited_by_count":17},{"id":"2210.00762","title":"Meta-Learning Priors for Safe Bayesian Optimization","created":"2022-10-03","cited_by_count":14},{"id":"2311.04402","title":"Likelihood Ratio Confidence Sets for Sequential Decision Making","created":"2023-11-08","cited_by_count":10},{"id":"2009.12820","title":"Experimental Design for Overparameterized Learning with Application to Single Shot Deep Active Learning","created":"2020-09-27","cited_by_count":9},{"id":"2205.13627","title":"Experimental Design for Linear Functionals in Reproducing Kernel Hilbert Spaces","created":"2022-05-26","cited_by_count":9},{"id":"2401.05193","title":"Experiment Planning with Function Approximation","created":"2024-01-10","cited_by_count":5}],"next_cursor":null}