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
7,676 results for “keyword:"ai"” in ICLR 2027. 1,833 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Spatial Encoding Geometry Determines the Maps and Transitions Recovered by Deep EEG Microstate Models▼4.3k2.00
[PDF]LazyFlash: Forward-Dense, Backward-Sparse Attention for Accelerated Long-Context Fine-Tuning▲4.7k3.25
[PDF]BrainWideBench: Benchmarking large-scale pretraining and across-animal transfer in multi-region neural recordings▲1.7k3.33
[PDF]How Multi-Head Transformers Specialize for In-Context Learning: A Theoretical Analysis of Training Dynamics and Generalization▲2843.00
[PDF]When Conversation is the Attack: Mining Transferable Contexts for Harmful Compliance and Over-Refusal▲3.0k2.33
[PDF]Rescuing Points Trapped Inside Incorrect Decision Regions: A target for Evaluating and Improving Forward-Forward Learning▲5103.00
[PDF]PRISM-BENCH: Diagnosing Grounded and Faithful Multimodal Reasoning Beyond Final-Answer Accuracy
[PDF]Robustness After Specialization: Installing Adversarial Robustness in Speech Foundation Model Descendants▲3912.67
[PDF]From Target Shift to Covariate Shift: How RL Post-Training Enables Transfer to New Tasks▼4.5k2.67
[PDF]HybridResearcher: Bridging the Structured-Unstructured Boundary for Deep Research Agents▲4.6k3.00
[PDF]Molecules Meet Language: Confound-Aware Representation Learning and Chemical Property Steering in Transformer-VAE Latent Spaces▼1361.33
[PDF]Analysis of MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible error▲3912.67
[PDF]First-Order Characterization of Probabilistic Robustness for Classifiers via the Coarea Formula▲5103.00
[PDF]Crescendo-Live: Multi-Turn Jailbreaks of Full-Duplex Speech Models in Live Calls and Their Defense with Daimonion▲3.0k2.50
[PDF]When One More Constraint Is Added: Decomposing Multi-Constraint Failure in Instruction-Following Evaluation▲3.0k2.33
Withdrawn or desk rejected (1,833)
[PDF]Everything in Moderation: Interior Per-Domain Coverage Optima and Gap-Preserving Fixed-Budget Alignment in Multi-Domain Mid-TrainingDesk rejected
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected