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
119 results for “keyword:"model selection"” in ICLR 2027. 16 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]What Do Collapse Diagnostics Certify? Testing Alignment Objectives for Orthographic Shortcuts▼4.5k2.67
[PDF]Forecast residuals for the diagnosis of hidden traffic events: the ranking of normal models depends on the alarm rule▼1361.33
[PDF]Better Contrast Decisions, Worse Ranking? How Validation Selects Readouts for Text Embeddings▼1361.33
[PDF]Chemical-Support-Resolved Evaluation of Model-Selection Stability under Molecular Extrapolation▲3.0k2.33
[PDF]Tracking the Best Imputer under Drift: Continual Competence Routing for Non-Stationary Time Series▲6.1k2.00
[PDF]Correct Scores, Unsupported Conclusions: Benchmarking Evaluation under Incomplete Semantic Reference▼4.3k2.00
[PDF]From Prompts to Question Graphs: Structure-Aware Evaluation and Selection of Text-to-Image Models▼4.3k2.00
[PDF]Tailoring the Clustering Objective to the Data: Utility-Guided Validity-Index Selection and Candidate Reranking▲6.1k2.00
[PDF]Does Better Reprojection Mean Better 3D Reconstruction? Candidate- and Evidence-Stratified Evaluation for FLFM▼1.2k1.67
[PDF]Triage Before Fine-Tuning: Feasibility-Gated Selection and Monitored Adaptation of Embodied Foundation Models for a Fixed Physical Platform▲3972.67
[PDF]Certification, Not Search: Deployment-Time Model Sharing under Hard Per-Cell Risk Contracts▲3.0k2.33
[PDF]MRG-Router: Pre-Rendering Routing via Capability Probes for Multi-Reference Image Generation▲6.1k2.00
[PDF]When Shared Inputs Prevent Heavy Tails from Slowing Model Selection: A Minimax Separation▼4.5k2.67
Withdrawn or desk rejected (16)
[PDF]A Downstream Metric Can Be Non-Diagnostic for Predictive-Fit World-Model SelectionDesk rejected
[PDF]When Geometry Flips Architecture Rankings: An Exact Theory of Alignment and ComplexityDesk rejected