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1,181 results for “area:"learning theory"” in ICLR 2027. 193 withdrawn or desk rejected listed apart.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]Stability-Based Adversarial Generalization Bounds for Hypergraph Convolutional Networks▼4.3k2.00
[PDF]RLVR landscapes for iterated multiplications can be benign: Insights from spin-glass theory▼4.3k2.00
[PDF]Complex Phase Retrieval via Conditional Quantiles: Finite-Sample Recovery without Noise Moments▲143.33
[PDF]Algorithmic Capture, Computational Complexity, and Inductive Bias of Infinite Transformers▼4.3k2.00
[PDF]The Comparison Graph Determines What RLHF Can Learn: Spectral Identifiability, Error Bounds, and a Pre-Training Diagnostic for Preference Data▲3.0k2.33
[PDF]Quantitative Generalization Bounds for Multi-Layer Transformers: A Few Long Strings can Beat Many Short Ones▲143.33
[PDF]Beyond Overparameterization: Provable Learning of Input-Convex Multi-Layer Polynomial Networks with Active Queries▼5.8k2.33
[PDF]Muon–Adam Training for Overparameterized Neural Networks: Convergence and Generalization▼4.3k2.00
[PDF]Hidden Reasoning Must Leak, but Need Not Be Readable: Fundamental Opportunities and Limits for Chain-of-Thought Monitoring▼1.2k3.00
[PDF]Graph Convolutional Networks Achieve Information-Theoretic Limits under Stochastic Block Models with Non-Informative Node Features▲14k3.00
Withdrawn or desk rejected (193)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