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1,181 results for “area:"learning theory"” in ICLR 2027. 193 withdrawn or desk rejected listed apart.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]Learning without Overwriting: A Theory of Self-Distillation and Supervised Fine-Tuning in Continual Reasoning▲6.8k3.67
[PDF]Unveiling Lookahead’s Potential in Sharpness-Aware Minimization: Convergence and Generalization Revisited▲3942.67
[PDF]Phases of Cross-Entropy Training: Emergence and Implicit Bias in the Unconstrained Features Model▼1.1k3.25
[PDF]Learning Wasserstein-Stable Permutation-Invariant Functions: -Independent Latent Dimension and Sample Complexity▼1.2k3.00
[PDF]When Does Redundant Reasoning Pay? A Measurable Condition for Error-Tolerant Reasoning in Language Models▼4.3k2.00
[PDF]Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models▲3942.67
[PDF]Learning under Mechanism-Induced Covariate Shift: Finite-Scale Coverage and Source Allocation▼1361.33
[PDF]Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression▲1.7k3.33
[PDF]Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer▼1.2k3.00
[PDF]A Unified Framework for Change of Measure Inequalities: Applications to Generalization, Memorization and Privacy▲5103.00
[PDF]The Surrogate Is Not the Reward: Post-Surrogate Primary-Outcome Acquisition in Contextual Bandits▲3942.67
[PDF]Classification with Abstention under Class-Conditional Error Constraints: Minimax Rate and Algorithm▲143.33
[PDF]All roads lead to Markov kernel networks: A representation theorem for discretization-stable learning▼1.2k3.00
[PDF]When Errors Can Be Beneficial: A Categorization of Imperfect Rewards for Policy Gradient▲4.6k3.00
[PDF]Spanning, Not Counting: Novelty in Language Generation in the Limit, from Finiteness to Compactness▼5.8k2.33
[PDF]Certification Frontiers for Gaussian LoRA: Independent Priors, Posterior Risk, and Prediction-Preserving Balancing▼4.3k2.00
Withdrawn or desk rejected (193)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