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1,181 results for “area:"learning theory"” in ICLR 2027. 193 withdrawn or desk rejected listed apart.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]Attention Sinks in Transformer-based Language Models: Emergence Mechanisms and Benign Effects▲5.4k3.00
[PDF]Beyond Monotonicity: Thompson Sampling for Convex Ridge Bandits with Polynomial Bayesian Regret▲3.0k2.33
[PDF]An Asymptotic One-Sample Surrogate for Non-Gaussian ERM with General Convex Regularization▲14k2.50
[PDF]Interpolated Policy Distillation: A Controllable Continuum Between Off-Policy and On-Policy Distillation▲9.2k2.67
[PDF]What Does Neural Collapse Indicate for Generalization?: A Singular Learning Theory Perspective▲3.9k1.67
[PDF]Risk-Seeking Strategic Robustness in Games: A Substitutes-Complements Rule, and Where It Breaks▼4.5k2.67
[PDF]Fine-Tuning on Self-Generated and Reward-Weighted Data: Learning Dynamcis, Convergence Rates, and Benefits of Off-Policyness▲143.33
[PDF]Softmax Attention as a Covariance Readout: A Unified View of In-Context Learning and Repetition▲8.9k2.75
[PDF]Conservation Laws in Parameterized Quantum Circuits: Complete Characterizations and Rank Separation▼4.5k2.67
[PDF]Efficiency of Diffusion Models for Infinite-dimensional Data Generation: Dimension Independent Approximation and Estimation Errors▲3952.67
Withdrawn or desk rejected (193)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