{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"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":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1910.09457","title":"Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods","created":"2019-10-21","cited_by_count":913},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"2107.07511","title":"A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification","created":"2021-07-15","cited_by_count":792},{"id":"1806.01768","title":"Evidential Deep Learning to Quantify Classification Uncertainty","created":"2018-06-05","cited_by_count":732},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"2006.10108","title":"Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness","created":"2020-06-17","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":"1704.00109","title":"Snapshot Ensembles: Train 1, get M for free","created":"2017-04-01","cited_by_count":350},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328},{"id":"2102.11582","title":"Deep Deterministic Uncertainty: A Simple Baseline","created":"2021-02-23","cited_by_count":200},{"id":"2010.06610","title":"Training independent subnetworks for robust prediction","created":"2020-10-13","cited_by_count":177},{"id":"2110.14051","title":"A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges","created":"2021-10-26","cited_by_count":154},{"id":"2110.01786","title":"MoEfication: Transformer Feed-forward Layers are Mixtures of Experts","created":"2021-10-05","cited_by_count":152},{"id":"1404.1100","title":"A Tutorial on Principal Component Analysis","created":"2014-04-03","cited_by_count":141},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139},{"id":"1803.04386","title":"Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches","created":"2018-03-12","cited_by_count":133},{"id":"2209.03302","title":"Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?","created":"2022-09-07","cited_by_count":125},{"id":"2008.05105","title":"Local Temperature Scaling for Probability Calibration","created":"2020-08-12","cited_by_count":95},{"id":"2105.05246","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","created":"2021-05-11","cited_by_count":65},{"id":"2111.01395","title":"Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds","created":"2021-11-02","cited_by_count":65},{"id":"2107.00649","title":"On the Practicality of Deterministic Epistemic Uncertainty","created":"2021-07-01","cited_by_count":62},{"id":"2105.02723","title":"Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet","created":"2021-05-06","cited_by_count":61},{"id":"2504.17674","title":"Energy Considerations of Large Language Model Inference and Efficiency Optimizations","created":"2025-04-24","cited_by_count":55},{"id":"2402.12264","title":"Uncertainty quantification in fine-tuned LLMs using LoRA ensembles","created":"2024-02-19","cited_by_count":37},{"id":"2105.04290","title":"Meta-Cal: Well-controlled Post-hoc Calibration by Ranking","created":"2021-05-10","cited_by_count":33},{"id":"1708.00088","title":"Learning Algorithms for Active Learning","created":"2017-07-31","cited_by_count":30},{"id":"2201.10801","title":"When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism","created":"2022-01-26","cited_by_count":30},{"id":"2008.03033","title":"Evaluating probabilistic classifiers: Reliability diagrams and score decompositions revisited","created":"2020-08-07","cited_by_count":26},{"id":"2212.12053","title":"On Calibrating Semantic Segmentation Models: Analyses and An Algorithm","created":"2022-12-22","cited_by_count":25},{"id":"2301.02240","title":"Skip-Attention: Improving Vision Transformers by Paying Less Attention","created":"2023-01-05","cited_by_count":24},{"id":"2405.03425","title":"Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models","created":"2024-05-06","cited_by_count":20},{"id":"2405.14438","title":"LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks","created":"2024-05-23","cited_by_count":20},{"id":"2410.07170","title":"Parameter Efficient Fine-tuning via Explained Variance Adaptation","created":"2024-10-09","cited_by_count":20},{"id":"2501.19047","title":"Understanding Model Calibration -- A gentle introduction and visual exploration of calibration and the expected calibration error (ECE)","created":"2025-01-31","cited_by_count":20},{"id":"2502.09376","title":"LoRA Training Provably Converges to a Low-Rank Global Minimum or It Fails Loudly (But it Probably Won't Fail)","created":"2025-02-13","cited_by_count":20},{"id":"2507.13338","title":"Training Transformers with Enforced Lipschitz Constants","created":"2025-07-17","cited_by_count":20},{"id":"2010.16272","title":"PATHoBot: A Robot for Glasshouse Crop Phenotyping and Intervention","created":"2020-10-30","cited_by_count":18},{"id":"2107.10384","title":"Ensemble-based Uncertainty Quantification: Bayesian versus Credal Inference","created":"2021-07-21","cited_by_count":16},{"id":"2503.06982","title":"Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization","created":"2025-03-10","cited_by_count":13},{"id":"2407.01985","title":"The Epistemic Uncertainty Hole: an issue of Bayesian Neural Networks","created":"2024-07-02","cited_by_count":11},{"id":"2406.00427","title":"You Only Need Less Attention at Each Stage in Vision Transformers","created":"2024-06-01","cited_by_count":7},{"id":"2405.17494","title":"Transitional Uncertainty with Layered Intermediate Predictions","created":"2024-05-25","cited_by_count":4},{"id":"2501.17917","title":"Deep Ensembles Secretly Perform Empirical Bayes","created":"2025-01-29","cited_by_count":4},{"id":"2312.03415","title":"Run LoRA Run: Faster and Lighter LoRA Implementations","created":"2023-12-06","cited_by_count":3},{"id":"2409.17085","title":"Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation","created":"2024-09-25","cited_by_count":3},{"id":"2312.03443","title":"Data-driven Crop Growth Simulation on Time-varying Generated Images using Multi-conditional Generative Adversarial Networks","created":"2023-12-06","cited_by_count":2},{"id":"2412.12740","title":"Open-World Panoptic Segmentation","created":"2024-12-17","cited_by_count":2},{"id":"2505.22538","title":"Uncertainty Quantification with Proper Scoring Rules: Adjusting Measures to Prediction Tasks","created":"2025-05-28","cited_by_count":1}],"next_cursor":null}