{"total":65,"rows":[{"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":"2405.19681","title":"Bayesian Online Natural Gradient (BONG)","created":"2024-05-30","cited_by_count":14,"area":null},{"id":"2507.18807","title":"Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator","created":"2025-07-24","cited_by_count":14,"area":null},{"id":"2412.06014","title":"Post-hoc Probabilistic Vision-Language Models","created":"2024-12-08","cited_by_count":13,"area":"mllm"},{"id":"2503.05318","title":"Uncertainty-Aware Decoding with Minimum Bayes Risk","created":"2025-03-07","cited_by_count":11,"area":null},{"id":"2602.06500","title":"Can Microcanonical Langevin Dynamics Leverage Mini-Batch Gradient Noise?","created":"2026-02-06","cited_by_count":7,"area":null},{"id":"2507.08150","title":"CLEAR: Calibrated Learning for Epistemic and Aleatoric Risk","created":"2025-07-10","cited_by_count":6,"area":null},{"id":"2406.03276","title":"Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning","created":"2024-06-05","cited_by_count":5,"area":"deeprl"},{"id":"2411.04421","title":"Variational Low-Rank Adaptation Using IVON","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2411.18425","title":"Streamlining Prediction in Bayesian Deep Learning","created":"2024-11-27","cited_by_count":5,"area":null},{"id":"2505.09591","title":"Variational Visual Question Answering for Uncertainty-Aware Selective Prediction","created":"2025-05-14","cited_by_count":5,"area":"lr"},{"id":"2506.14280","title":"Improving LoRA with Variational Learning","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2411.00214","title":"Inclusive KL Gradient Flows: Otto-Wasserstein, Fisher-Rao-Gaussian, and Local-Estimator Dynamics","created":"2024-10-31","cited_by_count":4,"area":null},{"id":"2501.17325","title":"Connecting Federated ADMM to Bayes","created":"2025-01-28","cited_by_count":4,"area":null},{"id":"2410.16901","title":"Bayes without Underfitting: Fully Correlated Deep Learning Posteriors via Alternating Projections","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2505.11412","title":"Uncertainty quantification with approximate variational learning for wearable photoplethysmography prediction tasks","created":"2025-05-16","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":"2506.13150","title":"Federated ADMM from Bayesian Duality","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2507.07853","title":"Optimization Guarantees for Square-Root Natural-Gradient Variational Inference","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2510.23684","title":"VIKING: Deep variational inference with stochastic projections","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2605.00742","title":"Position: agentic AI orchestration should be Bayes-consistent","created":"2026-05-01","cited_by_count":3,"area":"agents"},{"id":"2606.23357","title":"SOAP-Bubbles: Structured Weight Uncertainty for Neural Networks","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2405.18351","title":"Evaluating Bayesian deep learning for radio galaxy classification","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2409.10673","title":"A Bayesian Interpretation of Adaptive Low-Rank Adaptation","created":"2024-09-16","cited_by_count":2,"area":null},{"id":"2411.18385","title":"Federated Learning with Uncertainty and Personalization via Efficient Second-order Optimization","created":"2024-11-27","cited_by_count":2,"area":null},{"id":"2504.03623","title":"Quantifying the uncertainty of model-based synthetic image quality metrics","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2506.12903","title":"Variational Learning Finds Flatter Solutions at the Edge of Stability","created":"2025-06-15","cited_by_count":2,"area":null},{"id":"2506.17768","title":"Log-Normal Multiplicative Dynamics for Stable Low-Precision Training of Large Networks","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2509.15641","title":"Information Geometry of Variational Bayes","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2406.15664","title":"Flat Posterior Does Matter For Bayesian Model Averaging","created":"2024-06-21","cited_by_count":1,"area":null},{"id":"2411.14860","title":"Ex Uno Pluria: Insights on Ensembling in Low Precision Number Systems","created":"2024-11-22","cited_by_count":1,"area":null},{"id":"2412.08147","title":"Variational Model Merging for Pareto Front Estimation in Multitask Finetuning","created":"2024-12-11","cited_by_count":1,"area":null},{"id":"2412.11646","title":"Information-Geometric Barycenters for Bayesian Federated Learning","created":"2024-12-16","cited_by_count":1,"area":null},{"id":"2502.10295","title":"Fenchel-Young Variational Learning","created":"2025-02-14","cited_by_count":1,"area":null},{"id":"2503.09244","title":"How To Make Your Cell Tracker Say \"I dunno!\"","created":"2025-03-12","cited_by_count":1,"area":null},{"id":"2506.09648","title":"Scaling Laws for Uncertainty in Deep Learning","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2511.21223","title":"Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2601.18420","title":"Gradient Regularized Natural Gradients","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2603.03673","title":"A Stein Identity for q-Gaussians with Bounded Support","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2604.19530","title":"Calibrating Scientific Foundation Models with Inference-Time Stochastic Attention","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.21765","title":"Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2608.09805","title":"Parameter Exploration for RLVR via Variational Learning","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2609.29466","title":"Direct Message Approximation (DMA): A Consistency-Based Framework for Tractable Approximate Inference on Factor Graphs","created":"2026-09-24","cited_by_count":1,"area":null},{"id":"2403.10671","title":"Variation Due to Regularization Tractably Recovers Bayesian Deep Learning","created":"2024-03-15","cited_by_count":0,"area":null},{"id":"2502.06268","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2502.07273","title":"Variational Learning Induces Adaptive Label Smoothing","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2502.21143","title":"Variational Bayesian Pseudo-Coreset","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2503.13296","title":"On Local Posterior Structure in Deep Ensembles","created":"2025-03-17","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":"2509.10132","title":"Cost-Free Personalization via Information-Geometric Projection in Bayesian Federated Learning","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2512.01930","title":"SVRG and Beyond via Posterior Correction","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2601.01484","title":"SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and Guidelines","created":"2026-01-04","cited_by_count":0,"area":"distill"},{"id":"2604.08624","title":"Practical Bayesian Inference for Speech SNNs: Uncertainty and Loss-Landscape Smoothing","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.12434","title":"A Bayesian Perspective on the Role of Epistemic Uncertainty for Delayed Generalization in In-Context Learning","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.29908","title":"Joint Model and Data Sparsification via the Marginal Likelihood","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.16214","title":"Calibrated Sampling-Free Uncertainty Estimation in Bayesian Deep Learning","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.23591","title":"Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.24007","title":"Fast and Slow Variational Continual Learning","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.25745","title":"Gaussian Mean Field Variational Inference can Overestimate Predictive Variance","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.23649","title":"DP-IVON-Gradsq: Differentially Private Squared-Gradient Improved Variational Online Newton","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.15922","title":"Information Geometry of Message Passing","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.04066","title":"Subspace Inference Enables Efficient Active Reward Learning from Preferences","created":"2026-09-03","cited_by_count":0,"area":"alignment"},{"id":"2610.13764","title":"How Well Do Prior-Data Fitted Networks Amortize Bayesian Inference?","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16578","title":"Variational Filtering for Bayesian Last Layers with an Independent Binary Probit Surrogate","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17735","title":"Train for Many, Update with One: Improving Multi-Sample Reasoning via Fenchel-Bregman Posterior Learning","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}