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
237 results for “keyword:"distribution shift"” in ICLR 2027. 82 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]DepShift: Measuring What Cross-Channel Modeling Buys, and What It Costs Under Dependency Shift▼1361.33
[PDF]Predictive Multiplicity Is Mostly Margin: Decomposing Robustness and Distribution Shift▼5.8k2.33
[PDF]Don't Fix What Isn't Broken: Calibrated Repair of Frozen Foundation Models under Product Shift▼4.5k2.67
[PDF]Sinkhorn-DPO: Distributionally Robust Preference Alignment via Entropic Optimal Transport▼1361.33
[PDF]What Does a Channel Name Identify? Task Transfer Versus Channel Identity Across Neural Recording Sessions▼1361.33
[PDF]SafeAdapt: Selective Deployment of Local Corrections to Reduce Harmful Updates in Spatial Soil Carbon Prediction▲6.1k2.00
[PDF]GraphSteer: Soft Edge Reweighting via Informative Leiden Subgraphs for Graph Out-of-Distribution Generalization▼1611.50
[PDF]From Benchmark to Deployment: Efficient Evaluation of LLMs for Health under Task and Evaluator Shift▼5.8k2.33
[PDF]Constructed Negatives Shape the Evaluation of Sequence-Based Protein–Protein Interaction Models▲6.6k3.33
[PDF]When Does Learned Normalization Actually Adapt? A Diagnostic Analysis of Adaptive Centring in Time Series Forecasting▼1.2k1.67
[PDF]Refit or Expand? Finite-Sample Certification of Interaction Surrogates under Compound Shifts▼4.3k2.00
[PDF]Certified Selective Gates for Video-Language Models Exceed Their Error Target Before Genre Drift Begins▼1.2k1.67
[PDF]Beyond Error Rates: Separating Difficulty from Decision-Rule Shift in Neural Quantum Error Correction▼5.8k2.33
[PDF]When Marginal Stability Is Not Enough: Auditing Benchmark Conclusions under Composition Shift▼4.3k2.00
[PDF]Does Certified Robustness Generalize? A Neural Network Verification Study of Distribution Shift▼1611.50
[PDF]When Is a Veto Worth Its Cost? Proposer Precision, Gate Selectivity, and Requalification under Distribution Shift▼1361.33
[PDF]Count the Groups, Not the Configurations: Exact Inference and Learning at Fixed Totals▲4.6k3.00
[PDF]Auditing Forecast Outputs Under Cohort Shift: Residual Learning Retains Conversion-Ranking Information Where Predicted Change Does Not▼4.3k2.00
[PDF]MODE-TTA: Multi-Mode Density Modeling for Test-Time Adaptation of 3D Vision-Language Foundation Models▼5.8k2.33
[PDF]Beyond Context Concatenation: Scalable, Manifold-Aligned Retrieval for Time-Series Foundation Models▼1.2k1.67
[PDF]Factorized Chain Utility: A Calibrated Divergence Diagnostic for Synthetic Tabular Data▲5.4k3.00
[PDF]AdaEval: Adaptive Importance Weighting for Reliable Model Evaluation under Unknown Covariate Shift▼4.3k2.00
Withdrawn or desk rejected (82)
[PDF]Beyond Online Accuracy: What Persists After Continual Test-Time Adaptation of Multimodal LLMs on Multiple-Choice VQA?Withdrawn1.67
[PDF]When Silence Misleads: Censored Observation-aware Verification for Collaborative PerceptionWithdrawn2.33
[PDF]When the Average Doesn't Exist: Why Learned Insurance Payouts Fail Under Distribution ShiftDesk rejected