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
945 results for “keyword:"analysis"” in ICLR 2027. 246 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Almost Exogenous: Regret Guarantees for Reinforcement Learning under Bounded Action Influence▲3952.67
[PDF]Backdoors Live in Shallow MLPs: State-Level Discriminative Attribution for Localized Pruning in LLM Backdoor Defense▼4.5k2.67
[PDF]One-Prox Random Reshuffling for Nonsmooth Nonconvex Optimization: Complexity and KL Last-Iterate Rates▼4.3k2.00
[PDF]How Far Does a Shared Linear Map Go? Probing Feature-Space Manipulability for Image Editing▲6.1k2.00
[PDF]Token Mass, Not Geometry: A Confound in Embedding-Based Data Selection for Language Model Pretraining▼1.3k1.75
[PDF]From Spectral Responses to Task Effects: Auditing Frequency Dependence in Spiking Neural Networks▼1361.33
[PDF]Before Attention Sinks Form: Hidden-State Geometry Reveals and Modulates Their Formation▼1.2k1.67
[PDF]Overjet-1: A Multi-modal Generalist Vision-Language Model for Grounded Dental Image Understanding▲9.2k2.67
[PDF]Nuisance-Induced Confounding in LLM Output Sensitivity Analysis: A Semantic Normalization Framework▼4.3k2.00
[PDF]Separating operator geometry from learned routing in a gated, slot-routed associative memory▼1361.33
[PDF]Linguistic Cartography: Metric Spatial and Hierarchical Platial Representations in Language Models▲5103.00
[PDF]Parameter Conventions Confound Compute-Optimal Scaling Exponents of Dense Language Models▲5103.00
[PDF]Causal Partial Separability: Learning Nonlinear DAGs from Multivariate Functional Data▼1.2k1.67
[PDF]SciDynBench-R: Benchmarking Error-Validity Disagreement in Scientific Dynamical Forecasting▼4.3k2.00
Withdrawn or desk rejected (246)
[PDF]ReLoC: Recursive Local Causal Modeling for Explaining and Predicting LLM-Based Multi-Agent BehaviorWithdrawn1.33
[PDF]CCQ: Compensation-Conditioned Quadratic Selection for Absorbing Skipped Experts in MoE LLMsWithdrawn2.00
[PDF]Probing Interaction Awareness in Trajectory Prediction with Counterfactual PerturbationsDesk rejected
[PDF]When Does Chain-of-Thought Hurt Spatial Answers? Length, Retrieval, and Content Controls in Vision-Language ModelsWithdrawn1.67