{"list":"other","total":85,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"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":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"1807.03888","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","created":"2018-07-10","cited_by_count":1485},{"id":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"1812.04606","title":"Deep Anomaly Detection with Outlier Exposure","created":"2018-12-11","cited_by_count":942},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860},{"id":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"1412.1897","title":"Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images","created":"2014-12-05","cited_by_count":776},{"id":"1802.10501","title":"Predictive Uncertainty Estimation via Prior Networks","created":"2018-02-28","cited_by_count":557},{"id":"1511.06233","title":"Towards Open Set Deep Networks","created":"2015-11-19","cited_by_count":538},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2111.12797","title":"ReAct: Out-of-distribution Detection With Rectified Activations","created":"2021-11-24","cited_by_count":486},{"id":"2007.08176","title":"CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances","created":"2020-07-16","cited_by_count":441},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"2406.11794","title":"DataComp-LM: In search of the next generation of training sets for language models","created":"2024-06-17","cited_by_count":398},{"id":"1711.09325","title":"Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples","created":"2017-11-26","cited_by_count":389},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"1901.09192","title":"SelectiveNet: A Deep Neural Network with an Integrated Reject Option","created":"2019-01-26","cited_by_count":350},{"id":"2106.03004","title":"Exploring the Limits of Out-of-Distribution Detection","created":"2021-06-06","cited_by_count":283},{"id":"2210.07242","title":"OpenOOD: Benchmarking Generalized Out-of-Distribution Detection","created":"2022-10-13","cited_by_count":268},{"id":"2205.09310","title":"Mitigating Neural Network Overconfidence with Logit Normalization","created":"2022-05-19","cited_by_count":252},{"id":"1802.05300","title":"Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise","created":"2018-02-14","cited_by_count":216},{"id":"2209.09858","title":"Extremely Simple Activation Shaping for Out-of-Distribution Detection","created":"2022-09-20","cited_by_count":212},{"id":"2106.09022","title":"A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection","created":"2021-06-16","cited_by_count":207},{"id":"2007.05566","title":"Contrastive Training for Improved Out-of-Distribution Detection","created":"2020-07-10","cited_by_count":186},{"id":"2308.15366","title":"AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models","created":"2023-08-29","cited_by_count":171},{"id":"2111.09805","title":"DICE: Leveraging Sparsification for Out-of-Distribution Detection","created":"2021-11-18","cited_by_count":166},{"id":"2303.04360","title":"Does Synthetic Data Generation of LLMs Help Clinical Text Mining?","created":"2023-03-08","cited_by_count":154},{"id":"2112.05135","title":"PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures","created":"2021-12-09","cited_by_count":131},{"id":"2203.04450","title":"How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?","created":"2022-03-08","cited_by_count":128},{"id":"2210.14707","title":"Is Out-of-Distribution Detection Learnable?","created":"2022-10-26","cited_by_count":109},{"id":"2206.13687","title":"POEM: Out-of-Distribution Detection with Posterior Sampling","created":"2022-06-28","cited_by_count":108},{"id":"2108.11941","title":"Semantically Coherent Out-of-Distribution Detection","created":"2021-08-26","cited_by_count":107},{"id":"1905.13472","title":"Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness","created":"2019-05-31","cited_by_count":104},{"id":"2109.14162","title":"Can multi-label classification networks know what they don't know?","created":"2021-09-29","cited_by_count":100},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97},{"id":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96},{"id":"2202.03299","title":"Training OOD Detectors in their Natural Habitats","created":"2022-02-07","cited_by_count":86},{"id":"2309.13415","title":"Dream the Impossible: Outlier Imagination with Diffusion Models","created":"2023-09-23","cited_by_count":77},{"id":"2203.03800","title":"Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild","created":"2022-03-08","cited_by_count":70},{"id":"2302.02914","title":"Energy-based Out-of-Distribution Detection for Graph Neural Networks","created":"2023-02-06","cited_by_count":68},{"id":"2106.03917","title":"Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments","created":"2021-06-07","cited_by_count":66},{"id":"2311.00453","title":"CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection","created":"2023-11-01","cited_by_count":58},{"id":"2306.09158","title":"Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection","created":"2023-06-15","cited_by_count":57},{"id":"2111.00980","title":"Mixture Proportion Estimation and PU Learning: A Modern Approach","created":"2021-11-01","cited_by_count":52},{"id":"2307.12375","title":"In-Context Learning Learns Label Relationships but Is Not Conventional Learning","created":"2023-07-23","cited_by_count":51},{"id":"2205.12679","title":"Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning","created":"2022-05-25","cited_by_count":50},{"id":"2303.05033","title":"Out-of-distribution Detection with Implicit Outlier Transformation","created":"2023-03-09","cited_by_count":43},{"id":"1603.03130","title":"Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning","created":"2016-03-10","cited_by_count":41},{"id":"2310.19070","title":"Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection","created":"2023-10-29","cited_by_count":39},{"id":"2306.06048","title":"How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?","created":"2023-06-09","cited_by_count":38},{"id":"2310.13923","title":"Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation","created":"2023-10-21","cited_by_count":38},{"id":"2311.01796","title":"Learning to Augment Distributions for Out-of-Distribution Detection","created":"2023-11-03","cited_by_count":38},{"id":"1911.00459","title":"Positive-Unlabeled Reward Learning","created":"2019-11-01","cited_by_count":37},{"id":"2402.03502","title":"How Does Unlabeled Data Provably Help Out-of-Distribution Detection?","created":"2024-02-05","cited_by_count":36},{"id":"2207.13048","title":"Domain Adaptation under Open Set Label Shift","created":"2022-07-26","cited_by_count":32},{"id":"2302.11893","title":"A framework for benchmarking class-out-of-distribution detection and its application to ImageNet","created":"2023-02-23","cited_by_count":31},{"id":"2311.03236","title":"Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources","created":"2023-11-06","cited_by_count":31},{"id":"1411.6081","title":"PU Learning for Matrix Completion","created":"2014-11-22","cited_by_count":30},{"id":"2409.01980","title":"Large Language Models for Anomaly and Out-of-Distribution Detection: A Survey","created":"2024-09-03","cited_by_count":27},{"id":"2312.14452","title":"How to Overcome Curse-of-Dimensionality for Out-of-Distribution Detection?","created":"2023-12-22","cited_by_count":15},{"id":"2406.16308","title":"Anomaly Detection of Tabular Data Using LLMs","created":"2024-06-24","cited_by_count":12},{"id":"2308.15939","title":"Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization","created":"2023-08-30","cited_by_count":10},{"id":"2406.12629","title":"SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation","created":"2024-06-18","cited_by_count":10},{"id":"2404.00323","title":"CLIP-driven Outliers Synthesis for few-shot OOD detection","created":"2024-03-30","cited_by_count":6},{"id":"2312.00351","title":"Manipulating the Label Space for In-Context Classification","created":"2023-12-01","cited_by_count":5},{"id":"2209.07837","title":"Topological Structure Learning for Weakly-Supervised Out-of-Distribution Detection","created":"2022-09-16","cited_by_count":4},{"id":"2403.04224","title":"Aligners: Decoupling LLMs and Alignment","created":"2024-03-07","cited_by_count":4}],"next_cursor":null}