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1,181 results for “area:"learning theory"” in ICLR 2027. 193 withdrawn or desk rejected listed apart.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]Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete▲5.4k3.00
[PDF]Towards Understanding How Deep Transformers Perform Classification with Unlabeled Context▼4.3k2.00
[PDF]What Stochastic Information Matters for Learning? Observable-Relative Equivalence and Control▲3.0k2.33
[PDF]Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory▼5.8k2.33
[PDF]Transductive Learning Over Unbounded Losses: An Unbounded Transductive Local Complexity Approach▼5.8k2.33
[PDF]Same Risks, Different Error Bars: Disagreement-Aware Uncertainty for Cross-Validated Model Selection▼4.3k2.00
[PDF]When Higher Scores Yield Less Feedback: Score Saturation in Self-Rewarding Language Models▲9.2k2.67
[PDF]When Equilibria Bifurcate: Statistical Resolution Limits for Learning Equilibrium Correspondences▼71.25
[PDF]Beyond the Attention Lottery: Expressive Power and Topological Complexity via Algebraic Geometry▼1361.33
[PDF]On Gradient Descent with Stochastic Rounding on Fixed-Point Grids for Quadratic Objectives▲1.9k3.67
[PDF]Instance-Optimal Best Policy Identification in Decoupled Causal MDPs with a Known Graph▼1.2k1.67
[PDF]When Can Pairwise Routing Dynamics Be Tested in Mixture-of-Experts? Identifiability Conditions and Evidence from a Learned Router▼1361.33
Withdrawn or desk rejected (193)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