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
7,679 results for “keyword:"ai"” in ICLR 2027. 1,830 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Learning from Failures: Verified Edit Distillation for Variable-Length Diffusion Language Models▲1.7k3.33
[PDF]P-BFM: Perceptive Behavioral Foundation Models for Humanoid Control via Unsupervised Reinforcement Learning▲143.33
[PDF]Recursive Hypercompression: Phase Transitions from Self-Improvement to Self-Deterioration▼5.8k2.33
[PDF]When Multimodality Stops Helping: Auditing Representation-Conditioned Residual Modality Utility▼1.2k1.67
[PDF]Disentangling Verbalized Evaluation Awareness and Refusal through Neuron-Level Intervention▼4.3k2.00
[PDF]From Model Coverage to Control Value: Auditing Few-Shot Safety Filters under Topology Shift▲11.00
[PDF]Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games▼4.3k2.00
[PDF]Data-Space Dirichlet Process Bayesian Neural Networks: Resolving Epistemic Uncertainty Collapse in the Data Void▲9.2k2.67
[PDF]Certifying Data Rankings Under Deployment Uncertainty: When Benchmark Agreement Transfers and When to Abstain▼1361.33
[PDF]Scale Sensitivity in Low-Bit Post-Training Quantization: Curvature of the Quantization Error Landscape▼4.3k2.00
[PDF]Beyond In-Domain Evaluation: Benchmarking Experimental Generalization in Disordered Crystal Generation▼1361.33
Withdrawn or desk rejected (1,830)
[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