{"total":102,"rows":[{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830,"area":null},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694,"area":null},{"id":"2303.03846","title":"Larger language models do in-context learning differently","created":"2023-03-07","cited_by_count":394,"area":null},{"id":"2209.15558","title":"Out-of-Distribution Detection and Selective Generation for Conditional Language Models","created":"2022-09-30","cited_by_count":197,"area":null},{"id":"2311.09469","title":"Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs","created":"2023-11-16","cited_by_count":98,"area":null},{"id":"2212.10445","title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","created":"2022-12-20","cited_by_count":97,"area":null},{"id":"2402.19460","title":"Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks","created":"2024-02-29","cited_by_count":78,"area":null},{"id":"2310.00035","title":"LoRA ensembles for large language model fine-tuning","created":"2023-09-29","cited_by_count":67,"area":null},{"id":"2402.00809","title":"Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI","created":"2024-02-01","cited_by_count":62,"area":null},{"id":"2207.09239","title":"Assaying Out-Of-Distribution Generalization in Transfer Learning","created":"2022-07-19","cited_by_count":53,"area":null},{"id":"2211.15259","title":"A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification","created":"2022-11-28","cited_by_count":52,"area":null},{"id":"2305.20028","title":"A Study of Bayesian Neural Network Surrogates for Bayesian Optimization","created":"2023-05-31","cited_by_count":50,"area":null},{"id":"2211.12717","title":"Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks","created":"2022-11-23","cited_by_count":49,"area":null},{"id":"2303.02011","title":"Diagnosing Model Performance Under Distribution Shift","created":"2023-03-03","cited_by_count":39,"area":null},{"id":"2402.12264","title":"Uncertainty quantification in fine-tuned LLMs using LoRA ensembles","created":"2024-02-19","cited_by_count":37,"area":null},{"id":"2407.01032","title":"Overcoming Common Flaws in the Evaluation of Selective Classification Systems","created":"2024-07-01","cited_by_count":37,"area":null},{"id":"2403.10380","title":"BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics","created":"2024-03-15","cited_by_count":36,"area":null},{"id":"2302.11874","title":"What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers","created":"2023-02-23","cited_by_count":35,"area":null},{"id":"2208.12084","title":"Calibrated Selective Classification","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2402.02460","title":"Review of multimodal machine learning approaches in healthcare","created":"2024-02-04","cited_by_count":31,"area":null},{"id":"2502.06872","title":"Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey","created":"2025-02-08","cited_by_count":30,"area":"rag"},{"id":"2505.10475","title":"Parallel Scaling Law for Language Models","created":"2025-05-15","cited_by_count":30,"area":"lr"},{"id":"2302.02865","title":"Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs","created":"2023-02-06","cited_by_count":29,"area":null},{"id":"2208.00549","title":"Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantities","created":"2022-08-01","cited_by_count":28,"area":null},{"id":"2304.08653","title":"On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study","created":"2023-04-17","cited_by_count":25,"area":null},{"id":"2306.08751","title":"Improving Selective Visual Question Answering by Learning from Your Peers","created":"2023-06-14","cited_by_count":25,"area":null},{"id":"2312.09231","title":"Reliability in Semantic Segmentation: Can We Use Synthetic Data?","created":"2023-12-14","cited_by_count":24,"area":null},{"id":"2305.14824","title":"Mitigating Temporal Misalignment by Discarding Outdated Facts","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2312.17162","title":"Function-Space Regularization in Neural Networks: A Probabilistic Perspective","created":"2023-12-28","cited_by_count":20,"area":null},{"id":"2307.03810","title":"URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates","created":"2023-07-07","cited_by_count":17,"area":null},{"id":"2302.00704","title":"Pathologies of Predictive Diversity in Deep Ensembles","created":"2023-02-01","cited_by_count":16,"area":null},{"id":"2306.06849","title":"Mitigating Transformer Overconfidence via Lipschitz Regularization","created":"2023-06-12","cited_by_count":15,"area":null},{"id":"2312.15297","title":"Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models","created":"2023-12-23","cited_by_count":15,"area":null},{"id":"2402.07745","title":"Predictive Churn with the Set of Good Models","created":"2024-02-12","cited_by_count":15,"area":null},{"id":"2409.02628","title":"(Implicit) Ensembles of Ensembles: Epistemic Uncertainty Collapse in Large Models","created":"2024-09-04","cited_by_count":15,"area":null},{"id":"2409.02976","title":"Hallucination Detection in LLMs: Fast and Memory-Efficient Fine-Tuned Models","created":"2024-09-04","cited_by_count":15,"area":null},{"id":"2306.10087","title":"ActiveGLAE: A Benchmark for Deep Active Learning with Transformers","created":"2023-06-16","cited_by_count":14,"area":null},{"id":"2401.14555","title":"Revisiting Active Learning in the Era of Vision Foundation Models","created":"2024-01-25","cited_by_count":14,"area":"mllm"},{"id":"2507.01831","title":"Out-of-Distribution Detection Methods Answer the Wrong Questions","created":"2025-07-02","cited_by_count":14,"area":null},{"id":"2302.06541","title":"Towards Agile Text Classifiers for Everyone","created":"2023-02-13","cited_by_count":13,"area":null},{"id":"2408.16757","title":"Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarks","created":"2024-08-29","cited_by_count":13,"area":null},{"id":"2302.06495","title":"Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts","created":"2023-02-13","cited_by_count":12,"area":null},{"id":"2209.06078","title":"On the Optimal Combination of Cross-Entropy and Soft Dice Losses for Lesion Segmentation with Out-of-Distribution Robustness","created":"2022-09-13","cited_by_count":11,"area":null},{"id":"2301.12860","title":"Massively Scaling Heteroscedastic Classifiers","created":"2023-01-30","cited_by_count":11,"area":null},{"id":"2304.03398","title":"Quantum Conformal Prediction for Reliable Uncertainty Quantification in Quantum Machine Learning","created":"2023-04-06","cited_by_count":11,"area":null},{"id":"2305.07021","title":"Simple Token-Level Confidence Improves Caption Correctness","created":"2023-05-11","cited_by_count":11,"area":null},{"id":"2305.16999","title":"Three Towers: Flexible Contrastive Learning with Pretrained Image Models","created":"2023-05-26","cited_by_count":11,"area":"mllm"},{"id":"2305.18213","title":"Gaussian Process Probes (GPP) for Uncertainty-Aware Probing","created":"2023-05-29","cited_by_count":11,"area":null},{"id":"2407.11942","title":"Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design","created":"2024-07-16","cited_by_count":11,"area":"diffusion"},{"id":"2504.07092","title":"Are We Done with Object-Centric Learning?","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2303.00732","title":"R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents","created":"2023-03-01","cited_by_count":10,"area":null},{"id":"2402.16569","title":"Pretrained Visual Uncertainties","created":"2024-02-26","cited_by_count":10,"area":null},{"id":"2310.04627","title":"Profit: Benchmarking Personalization and Robustness Trade-off in Federated Prompt Tuning","created":"2023-10-06","cited_by_count":9,"area":null},{"id":"2502.00089","title":"Ensembles of Low-Rank Expert Adapters","created":"2025-01-31","cited_by_count":9,"area":null},{"id":"2401.11974","title":"Cross-Validation Conformal Risk Control","created":"2024-01-22","cited_by_count":8,"area":null},{"id":"2304.08479","title":"Towards Robust Prompts on Vision-Language Models","created":"2023-04-17","cited_by_count":7,"area":"mllm"},{"id":"2307.00398","title":"ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models","created":"2023-07-01","cited_by_count":7,"area":"mllm"},{"id":"2401.04305","title":"Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions","created":"2024-01-09","cited_by_count":7,"area":null},{"id":"2404.11350","title":"Calibrating Bayesian Learning via Regularization, Confidence Minimization, and Selective Inference","created":"2024-04-17","cited_by_count":7,"area":null},{"id":"2209.09178","title":"ViT-DD: Multi-Task Vision Transformer for Semi-Supervised Driver Distraction Detection","created":"2022-09-19","cited_by_count":6,"area":null},{"id":"2212.06370","title":"Dual Accuracy-Quality-Driven Neural Network for Prediction Interval Generation","created":"2022-12-13","cited_by_count":5,"area":null},{"id":"2307.07753","title":"Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks","created":"2023-07-15","cited_by_count":4,"area":null},{"id":"2309.02048","title":"Probabilistic Self-supervised Learning via Scoring Rules Minimization","created":"2023-09-05","cited_by_count":4,"area":null},{"id":"2504.18346","title":"Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review","created":"2025-04-25","cited_by_count":4,"area":null},{"id":"2511.10282","title":"Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantification","created":"2025-11-13","cited_by_count":4,"area":null},{"id":"2306.00206","title":"Training-Free Uncertainty Estimation for Embedding Models","created":"2023-05-31","cited_by_count":3,"area":null},{"id":"2308.07121","title":"Active Bird2Vec: Towards End-to-End Bird Sound Monitoring with Transformers","created":"2023-08-14","cited_by_count":3,"area":null},{"id":"2312.00486","title":"REDUCR: Robust Data Downsampling Using Class Priority Reweighting","created":"2023-12-01","cited_by_count":3,"area":null},{"id":"2402.05939","title":"Uncertainty Awareness of Large Language Models Under Code Distribution Shifts: A Benchmark Study","created":"2024-01-12","cited_by_count":3,"area":null},{"id":"2505.18636","title":"Asymmetric Duos: Sidekicks Improve Uncertainty","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2606.08277","title":"Remember with Confidence: Uncertainty Quantification for Spatio-temporal Memory with Probabilistic Guarantees","created":"2026-06-06","cited_by_count":3,"area":null},{"id":"2210.02989","title":"SynBench: Task-Agnostic Benchmarking of Pretrained Representations using Synthetic Data","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2212.05987","title":"Selective classification using a robust meta-learning approach","created":"2022-12-12","cited_by_count":2,"area":null},{"id":"2302.05807","title":"Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play","created":"2023-02-11","cited_by_count":2,"area":null},{"id":"2306.10043","title":"Unraveling the Interconnected Axes of Heterogeneity in Machine Learning for Democratic and Inclusive Advancements","created":"2023-06-11","cited_by_count":2,"area":null},{"id":"2308.14705","title":"Diversified Ensemble of Independent Sub-Networks for Robust Self-Supervised Representation Learning","created":"2023-08-28","cited_by_count":2,"area":null},{"id":"2309.05213","title":"Towards Federated Learning Under Resource Constraints via Layer-wise Training and Depth Dropout","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2309.07499","title":"Efficiently Robustify Pre-trained Models","created":"2023-09-14","cited_by_count":2,"area":null},{"id":"2309.10910","title":"Amplifying Pathological Detection in EEG Signaling Pathways through Cross-Dataset Transfer Learning","created":"2023-09-19","cited_by_count":2,"area":null},{"id":"2402.12664","title":"Discriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methods","created":"2024-02-20","cited_by_count":2,"area":null},{"id":"2406.07133","title":"Translating speech with just images","created":"2024-06-11","cited_by_count":2,"area":null},{"id":"2406.12082","title":"Uncertainty modeling for fine-tuned implicit functions","created":"2024-06-17","cited_by_count":2,"area":null},{"id":"2502.03366","title":"Rethinking Approximate Gaussian Inference in Classification","created":"2025-02-05","cited_by_count":2,"area":null},{"id":"2212.12411","title":"Benchmark for Uncertainty & Robustness in Self-Supervised Learning","created":"2022-12-23","cited_by_count":1,"area":null},{"id":"2308.01525","title":"VisAlign: Dataset for Measuring the Degree of Alignment between AI and Humans in Visual Perception","created":"2023-08-03","cited_by_count":1,"area":null},{"id":"2403.20047","title":"Embracing Unknown Step by Step: Towards Reliable Sparse Training in Real World","created":"2024-03-29","cited_by_count":1,"area":null},{"id":"2408.14281","title":"Uncertainties of Latent Representations in Computer Vision","created":"2024-08-26","cited_by_count":1,"area":null},{"id":"2509.05826","title":"Performance of Conformal Prediction in Capturing Aleatoric Uncertainty","created":"2025-09-06","cited_by_count":1,"area":null},{"id":"2512.02831","title":"Revisiting Theory of Contrastive Learning for Domain Generalization","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2605.08819","title":"From pre-training to downstream performance: Does domain-specific pre-training make sense?","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2606.14728","title":"FUSE: Quantifying Uncertainty in Vision-Language Models by Bayesian Fusing Epistemic and Aleatoric Uncertainty","created":"2026-06-01","cited_by_count":1,"area":"mllm"},{"id":"2301.08839","title":"A Trustworthiness Score to Evaluate DNN Predictions","created":"2023-01-21","cited_by_count":0,"area":null},{"id":"2308.00231","title":"Capsa: A Unified Framework for Quantifying Risk in Deep Neural Networks","created":"2023-08-01","cited_by_count":0,"area":null},{"id":"2311.18645","title":"Stochastic Vision Transformers with Wasserstein Distance-Aware Attention","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2501.00053","title":"Implementing Trust in Non-Small Cell Lung Cancer Diagnosis with a Conformalized Uncertainty-Aware AI Framework in Whole-Slide Images","created":"2024-12-28","cited_by_count":0,"area":null},{"id":"2505.20235","title":"Variational Deep Learning via Implicit Regularization","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2507.13727","title":"Adversarial Training Improves Generalization Under Distribution Shifts in Bird Sound Classification","created":"2025-07-18","cited_by_count":0,"area":null},{"id":"2510.03162","title":"Calibrated Uncertainty Sampling for Active Learning","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2511.04160","title":"On Joint Regularization and Calibration in Deep Ensembles","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2601.09261","title":"Learning to Trust Experience: A Monitor-Trust-Regulator Framework for Learning under Unobservable Feedback Reliability","created":"2026-01-14","cited_by_count":0,"area":null}],"next_cursor":"100"}