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
11,749 results for “keyword:"models"” in ICLR 2027. 2,922 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]F-GRPO: Factorized Group Relative Policy Optimization for Unified Candidate Generation and Ranking▼5.9k2.33
[PDF]Enhanced Simulation Environment Based on Distribution Matching and Large Language Model-Guided Reinforcement Learning▼1.2k1.67
[PDF]"Benign-Shifted Compliance": A Mechanistic Insight into Safety Behaviors of Diffusion Language Models under Adversarial Prefixes▲5.4k3.00
[PDF]SHAPE: Structural Hierarchy of Affinities for Patch Enhancement in Training-Free Open-Vocabulary Semantic Segmentation▼1.2k1.67
[PDF]Search2Adapt: Training-Free Adapter Architecture Search for Segmentation Foundation Models▼4.3k2.00
[PDF]URGE: A Unified Representation-Guided Loss Reweighting Framework for Fine-grained Machine Unlearning▼5.9k2.33
[PDF]Structured World Models for Sample-Efficient Planning in Partially Known Dynamical Systems▼4.5k2.67
[PDF]Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models▲1.9k3.67
[PDF]Move Selection Upstream: Choosing What the Teacher Trains On in On-Policy Distillation▼1.2k1.67
[PDF]Beyond Confidence: Evidence-Guided Selective Answer Revision for Frozen Vision-Language Model▼1611.60
[PDF]Partner-Conditioned RNA Representations for Full-Sequence snoRNA–Target Interaction Prediction▲20k2.67
[PDF]ReTreVal: Reasoning Tree with Validation and Cross-Problem Memory for Large Language Models▼1.3k1.75
[PDF]ARCH-CPTQ: Replay-Free Continual Post-Training Quantization with Curvature History and Anchoring▲3.7k2.50
[PDF]ActForesight: Predictive Safety for Embodied Agents with Action-Conditioned Visual Futures and Motion Monitoring▼1.2k1.67
Withdrawn or desk rejected (2,922)
[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