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1,181 results for “area:"learning theory"” in ICLR 2027. 193 withdrawn or desk rejected listed apart.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]Variance-Aware Lexicographic Generalized Linear Bandits: Unknown Variance and Tighter Bounds▲3.0k2.50
[PDF]Bandit Submodular Maximization under Matroid Constraints: Learning Compressed Exchange Policy▲143.33
[PDF]Read Depth and Broadcast Depth: What Sharing Keys and Values Across Layers Costs a Transformer▲3.0k2.33
[PDF]When More Candidates Hurt: A Proposal–Evidence Reliability Frontier for Causal Selection▼1.3k1.80
[PDF]The Arbitrary-Placement Problem in Entropy-Minimizing Selection, and a Residual-Entropy Formulation▼4.3k2.00
[PDF]Uniform Discrete Diffusion Models Are Minimax Optimal for Estimating Distributions with Small Effective Support Size▲1.7k3.33
[PDF]From Policy Evaluation to Off-Policy Control: Provable Emergence of In-Context Q-Learning▲3952.67
[PDF]When Prediction Chooses the Representation: Learning Dynamics and Planning in World Models▼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Withdrawn or desk rejected (193)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