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
347 results for “keyword:"variance"” in ICLR 2027. 90 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]LNPO-ATC: LENGTH-NORMALIZED POLICY OPTIMIZATION WITH ADAPTIVE TOKEN CREDIT FOR LONG-CONTEXT REASONING▼4.5k2.67
[PDF]When Weak Features Hide: Separating Statistical Detection from Sparse Autoencoder Recovery▲6.1k2.00
[PDF]Beyond Coverage: Which Observations Share an Instance Decides What a Joint Model Can Learn▼1.2k1.67
[PDF]Compositional Representation Learning for RNA Modifications via Chemical Transformation Equivariance▼5.8k2.33
[PDF]Is your uncertainty map wrong, or is its target? Exact diagnostics for the Tweedie diagonal, and a gradient-free alternative▼1.2k1.67
[PDF]Behavioral Response Spectroscopy: Pre-RL Responses Reveal Shared Structure in RL-Induced Behavioral Change▼1.2k1.67
[PDF]Statistic Preservation Does Not Identify Attack-Suppression Preservation in Composed Federated-Learning Defences▼4.3k2.00
[PDF]SIVA-RL: Sensitivity–Invariance Visual Alignment for Multimodal Reinforcement Learning▼5.8k2.33
[PDF]Variance-Aware Lexicographic Generalized Linear Bandits: Unknown Variance and Tighter Bounds▲3.0k2.50
[PDF]AeroSCR: Recovering Stable Scene-Coordinate Decodability Under Scale and Rotation Shifts▲3.0k2.33
[PDF]When Physical Views Should Not Be Positive Pairs: Cross-Frequency Collapse in Self-Supervised Learning for Eddy Current Testing▼4.3k2.00
[PDF]Understanding the Subspace Stabilization of the Hessian and Gradient Covariance Matrix▼5.8k2.33
[PDF]Works Where Calibrated, Fails Where Misused: Auditing Small-Scale Pretraining's Seed-Noise Instruments▼4.3k2.00
[PDF]Breaking the Translation Equivariance Barrier: Coordinate Channels and Bounded Error Propagation in Multi-Physics Neural Operator Cascades▼71.25
[PDF]BioInvariant: Evaluating Appropriate Biological Invariance and Sensitivity in Genomic Foundation Models▲14k2.50
[PDF]Trust Labels Should Calibrate, Not Decide: Diagnosing and Reducing Source-Label Shortcuts in RL-Trained Fact-Checkers▲3.0k2.33
[PDF]Discourse Reconstructibility in Generative Language Models: Permutation-Invariant Bipartite Infilling, Representation Boundaries, and Non-Native Linguistic Invariance▼1361.33
[PDF]Equivariance Begins at the Source: Characterizing Compatible Sources for Generative Robot Policies▲5103.00
[PDF]LCG-SFNO: Low-Rank Clebsch–Gordan Corrections for Global Atmospheric Forecasting on the Sphere▼5.8k2.33
Withdrawn or desk rejected (90)
[PDF]Population Contracts for Scalable Language-Guided Multi-Robot Planning and ControlDesk rejected
[PDF]How to Reuse a RepresentationDesk rejected
[PDF]Periodic Gradient-Variance Suppression on SVD-Adapted Residuals for Cross-Generator Deepfake DetectionWithdrawn1.75