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
11,752 results for “keyword:"models"” in ICLR 2027. 2,919 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]CONTROLIR: LEARNING TO CONTROL STATE SPACE MODELS VIA SPATIAL EVIDENCE FOR IMAGE RESTORATION▼4.3k2.00
[PDF]TaylorSSM: Dependence-Preserving Robustness Certification for Selective State-Space Models▲3.0k2.33
[PDF]Beyond Fixed Sampling: Uncertainty-Aware Retrieval and Spatially-Grounded Reasoning for Fine-Grained Visual Recognition▼1.2k1.67
[PDF]LARCH: Latent Attribute Reasoning through Compositional Hierarchies for Generative Recommendation▼4.3k2.00
[PDF]EM-Lens: Towards Observation-Level Electromagnetic Signal Understanding via Agentic Zoom-and-Measure▲3.7k2.50
[PDF]MetaHuman-Anything: Vision-Language Face Similarity Grounding for Engine-Friendly Digital Human Sculpting▼1361.33
[PDF]Lead into Gold: The Surprising Effect of Symbolically Generated Deduction Data on LLMs▲3.0k2.33
[PDF]Improving Parallel Decoding of Block Diffusion Language Models with Autoregressive Generation Order▲5.4k3.00
Withdrawn or desk rejected (2,919)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33
[PDF]Propagation Is Not Decoration: When Physical Diffraction Carries Generative ComputationWithdrawn1.00
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected