NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
753 results for “area:"probabilistic methods (Bayesian methods, variational inference, sampling, UQ, etc.)"” in ICLR 2027. 123 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]What Does a Predictive Gain Certify? Auditing Information Claims under Approximate Inference▼5.8k2.33
[PDF]Data-Space Dirichlet Process Bayesian Neural Networks: Resolving Epistemic Uncertainty Collapse in the Data Void▲9.2k2.67
[PDF]When Proxy Calibration Controls the Wrong Risk: Accepted-Set Target Mismatch in Selective LLMs▼4.3k2.00
[PDF]An Execution Contract for Law-Preserving Row Eviction in Verifier-Guided Sequential Monte Carlo▼4.3k2.00
[PDF]Distance Does Not Predict Competence: A Two-Axis Decomposition of Out-of-Distribution Failure▼4.3k2.00
[PDF]Speeding Up Nonsmooth Bayesian MCMC Sampling via Inexact Proximal Unadjusted Langevin Algorithm▼1.2k1.67
[PDF]Prior-Aware Transductive Conformal Prediction for Vision–Language Models under Label Shift▼5.8k2.33
[PDF]On Uniformly Scaling Flows: A Density-Aligned Approach to Deep One-Class Classification▼4.3k2.00
[PDF]PACE: Parameter-Efficient Calibration for Robust Posterior Inference under Simulator Misspecification▼12k1.67
Withdrawn or desk rejected (123)
[PDF]When Can Graph Conformal Sets Transfer? Selective Diagnostics Under Unlabeled Topology ShiftWithdrawn1.00
[PDF]Scalable Bayesian Deep Kernel Networks via Ensemble-Induced Finite Function SpacesWithdrawn1.67
[PDF]Mode Collapse Is Cheap to Detect: A Ground-Truth-Free Pre-Flight Check for Neural SamplersWithdrawn1.33
[PDF]Think Until No Future Thought Can Help: Certified Remaining-Gain Stopping for Adaptive-Compute PoliciesWithdrawn2.00