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
764 results for “keyword:"theory"” in ICLR 2027. 116 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Instance-Dependent Auto-Exploration for Tabular Online Discounted Reinforcement Learning▲3.0k2.33
[PDF]Conditional Diffusion without ERM Oracles: From Finite Neural Training to Sampling Guarantees▼5.8k2.33
[PDF]Root Multiplicity Sets the Finite-Width Edge of Chaos in MLPs and Message-Passing Networks▼5.8k2.33
[PDF]AI Harness: Certification under Proposal-Conditioned Information for Foundation-Model Agents▼1361.33
[PDF]Toward Optimal Adversarial Attacks in Reinforcement Learning via Rate–Distortion Theory▼1.2k1.67
[PDF]History Matters: Strengthen Collaboration Through Delegation for Multi-agent Reinforcement Learning Systems▼5.8k2.33
[PDF]Fast Learning Beyond Finite Variance: Fractional Bernstein Geometry under Heavy-Tailed Losses▼5.8k2.33
[PDF]Curvature as Decoder State: Exact Cache–Update Frontiers for Strongly Convex Unlearning▲13k2.33
[PDF]MASOpt: Online Prompt Optimization for Multi-Agent Systems with Closed-Loop Control Theory▼5.8k2.33
[PDF]When Is Calibrated Confidence Sufficient for Optimal Stopping in Sequential Prediction?▲3.9k1.67
[PDF]Reconstruction Does Not Determine Generative Learnability: A Theory of Resource-Matched Visual Tokenization▼4.3k2.00
[PDF]From Pixels to Privacy-Sensitive Features: An Information-Theoretic Framework for Reconstruction Bounds▲2623.67
[PDF]Overcoming the Representational Limitations of Amplitude Encoding for Quantum Neural Networks▼5.3k1.33
[PDF]DETECTOR-COUPLED SURROGATE REGRET FOR TEST-TIME ADAPTATION IN PIECEWISE-STATIONARY CMDPS▼4.3k2.00
[PDF]Sharp Heterogeneity Barriers for Adam: Basis-Aware Convergence and High-Dimensional Divergence▲3952.67
[PDF]What Can Be Corrected in LLM Judge Ratings? Identifiability, Measurement, and Targeted Adjustment▼4.3k2.00
Withdrawn or desk rejected (116)
[PDF]Information-theoretic empowerment enhances healing following damage in self-organizing neural cellular automata.Desk rejected
[PDF]Physical and Evolutionary Constraints on Machine Learning Priors: Reconciling No Free Lunch with Real-World GeneralizationWithdrawn
[PDF]Caustic Spectroscopy: Identifiability and Acquisition Limits of Topological Event TimingWithdrawn2.00
[PDF]Stability and Generalization of Noisy signSGD: From Sign Discontinuity to Gaussian SmoothingWithdrawn
[PDF]DelibRRG: Trustworthy Cross-Examination and Clinical-First Deliberation for Radiology Report GenerationWithdrawn2.00
[PDF]Generalized Residual Closure: General Learning Dynamics for Stability–Plasticity CompatibilityWithdrawn2.00
[PDF]When Does an Observable Lose Failure Evidence? Exact Ranking Losses for Runtime Detection in Vision–Language–Action PoliciesWithdrawn1.00