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
79 results for “keyword:"information theory"” in ICLR 2027. 13 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]The Saussurean Representation Hypothesis: A Causal Account of Representational Structures in LLMs▼4.3k2.00
[PDF]Why Diffusion Sampling Can Ignore Ambient Dimension: Rate-Distortion Bounds in KL and TV▼1.2k3.00
[PDF]NOT A FITNESS BOTTLENECK: WHY PROTEIN LANGUAGE MODELS FALL SHORT ON DISORDERED PROTEIN ENSEMBLES▲3.0k2.33
[PDF]Generation Order and Parallel Decoding in Masked Diffusion Models: An Information-Theoretic Perspective▼4.5k2.67
[PDF]Equal Path Cost, Unequal Output Effects: Understanding Perturbation Propagation in Diffusion Models▲3972.67
[PDF]On-Policy Self Distillation As Automatisation: When and Why Thinking Collapses in Reasoning Models▼4.3k2.00
[PDF]Information-Theoretic Corrective Example Selection (IT-CES): Calibrated In-Context Example Selection for Automated Code Correction▼4.3k2.00
[PDF]Interpretable Client Contribution Evaluation in Federated Learning via Partial Information Decomposition▲3.8k2.50
[PDF]Inferred Generative-Process Diversity Predicts Correlated Failure Across Language Models▼5.8k2.33
[PDF]Toward Optimal Adversarial Attacks in Reinforcement Learning via Rate–Distortion Theory▼1.2k1.67
[PDF]Curvature as Decoder State: Exact Cache–Update Frontiers for Strongly Convex Unlearning▲13k2.33
[PDF]From Pixels to Privacy-Sensitive Features: An Information-Theoretic Framework for Reconstruction Bounds▲2623.67
Withdrawn or desk rejected (13)
[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]When Does an Observable Lose Failure Evidence? Exact Ranking Losses for Runtime Detection in Vision–Language–Action PoliciesWithdrawn1.00
[PDF]EAGLE: Entropy-Aware Geometric Learning Enhancer for Partially Polygon-Supervised Object LocalizationWithdrawn1.33
[PDF]Canonical Paraphrasing: A Provable Defense against Steganography in Language ModelsWithdrawn1.33