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
11,747 results for “keyword:"models"” in ICLR 2027. 2,924 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When Answers Stray from Questions: Hallucination Detection via Question-Answer Orthogonal Decomposition▲5.3k3.00
[PDF]SpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision–Language Models▲1462.75
[PDF]Sparse-View Interpretable 3D Animal Behavior Representations for Neural Encoding and Decoding▼1.2k1.67
[PDF]Understanding Forgetting Dynamics in Full Fine-Tuning of LLMs: A Neural Tangent Kernel Perspective▲3352.67
[PDF]From Scan to Focus: Learning a Value-Guided Adaptive Browsing Policy for Efficient Long-Video Reasoning▲3.1k2.33
[PDF]PoseStage: Unifying External Pose and Internal Structure Control in Multi-Object Scenes▲5.3k3.00
[PDF]R²-WAM: Functional Reuse and Refinement of Historical Adaptations for World-Action Models▲3.1k2.33
[PDF]FlowForget: Data Unlearning in Flow Matching Models via On-Policy Distillation and Preference Optimization
[PDF]EgoSteer: An Open-Source Full-Stack System Towards Steerable Dexterous Manipulation from Egocentric Videos▼1.2k3.00
Withdrawn or desk rejected (2,924)
[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