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
800 results for “keyword:"distribution"” in ICLR 2027. 203 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ORION: EXACT CANONICAL-STATE SUPERVISION FOR SYSTEMATIC GENERALIZATION IN TRANSFORMERS▼1.2k1.67
[PDF]Iterate, Don't Stack: Grounded Recursive Transformers for Generalizable Novel View Synthesis▲5.4k3.00
[PDF]When Amortized Posteriors Become Priors: One-Shot Accuracy Does Not Certify Recursive Reuse▼1.2k1.67
[PDF]Guaranteed Environment-Action Regularization for Feature-Level Federated Domain Generalization▼5.8k2.33
[PDF]SIFT: Robust Meta-Faithfulness Verification of Chain-of-Thought Reasoning Under Distribution Shift▼1361.33
[PDF]Does Adversarial Training Improve Generalization in Multi-View VLAs? Revealing and Mitigating View Collapse▲3952.67
[PDF]CUG-JEPA: Continual Test-Time Adaptation of Latent World Models under Visual Condition Shifts▼4.3k2.00
[PDF]When Forces Disagree: An Out-of-the-Box Stability and Uncertainty Estimate for Direct-Force Machine Learning Interatomic Potentials▲6.1k2.00
[PDF]LAGO: Language-Guided Adaptive Object-Region Focus for Zero-Shot Visual-Text Alignment▲3.0k2.33
[PDF]On the Generalizability of Non-Causal Subgraphs: Addressing Cue Discordance for Graph OOD Generalization▲3.0k2.33
[PDF]GraphPTQ: Post-Training Quantization for Graph Models, Memory Savings and Generalization▼5.8k2.33
[PDF]Noise-free Provable Trustworthy Machine Learning via Distribution-Specific Indistinguishability▼5.8k2.33
Withdrawn or desk rejected (203)
[PDF]Beyond Online Accuracy: What Persists After Continual Test-Time Adaptation of Multimodal LLMs on Multiple-Choice VQA?Withdrawn1.67
[PDF]How to Reuse a RepresentationDesk rejected
[PDF]When Silence Misleads: Censored Observation-aware Verification for Collaborative PerceptionWithdrawn2.33