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
1,181 results for “area:"learning theory"” in ICLR 2027. 193 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When Can Voting Help, Hurt, or Change Course? Exact Structure of Binary Test-Time Aggregation▲4.6k3.00
[PDF]NOT A FITNESS BOTTLENECK: WHY PROTEIN LANGUAGE MODELS FALL SHORT ON DISORDERED PROTEIN ENSEMBLES▲3.0k2.33
[PDF]λ-Cert: A Linear Calibration Budget Rules Out a Pipeline's Certificate Before Any Data Is Collected▼1.2k1.67
[PDF]On the Necessity of Non-Additive Modeling for Interaction Prediction: Theory and Application to Drug Synergy▼4.3k2.00
[PDF]Spectral Thresholds for Order and Gibbs Sampling Relaxation in a Spin System with a Given Coupling Matrix▼1.2k1.67
[PDF]EW-GET: Access-Conditioned Identifiability of Failure Mechanisms in Sensor-to-Decision Models▼4.3k2.00
[PDF]When Do Stale Updates Help? Forecasting, Participation Weighting, and Step Scale in Federated Learning▼4.3k2.00
[PDF]Reinforcement Learning for Hierarchical Reasoning Rewards: Minimax-Optimal Rates with Transformers▼4.3k2.00
[PDF]GenLimitLib: A Formal Library for Language Generation in the Limit and AI-Assisted Mathematical Research▲5103.00
[PDF]Inverse design of implicit bias by symmetry, stochasticity and holomorphic parametrizations▼1.2k1.67
Withdrawn or desk rejected (193)
[PDF]Curvature Controlled Mixing on the Interpolation Manifold: Sharp Cutoffs in Late-Phase Training DynamicsDesk rejected
[PDF]Exact Recovery Thresholds for Weighted Data Selection in Vector-Valued Linear RegressionDesk rejected