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
33,055 results for “keyword:"r"” in ICLR 2027. 8,245 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs▼1.2k1.67
[PDF]FAIL2TASK: Reproducing Coding-Agent Failure Patterns through Executable Task Synthesis▲3.0k2.50
[PDF]OVOGO: Offline Value-Guided On-Policy Generative Optimization for Flow-Based Vision-Language-Action Models▲13k2.33
[PDF]Learning When Cellular Responses Transfer: A Factorized Memory-Guided Agent for Perturbation Prediction▼4.3k2.00
[PDF]Acting in the Right Basis: Test-Time Compositional Generalisation for Offline Goal-Conditioned RL▼4.3k2.00
[PDF]The Error You See Is Not the Error You Made: Progression-aware Reasoning Origin for Reasoning Error Localization▲6.0k2.00
[PDF]MRG-Router: Pre-Rendering Routing via Capability Probes for Multi-Reference Image Generation▲6.0k2.00
[PDF]Re-Attending to the Missing Pieces: Test-Time Visual Evidence Refinement for High-Resolution Reasoning▲3282.67
[PDF]A General Model Diffing Framework for Understanding Post-Training: Attributing Behavioral Differences to Parameter Updates▼1.2k1.67
[PDF]TACO: Text-Anchored Classification with Structural Covariance Transfer for One-Shot Federated Learning▲3.1k2.33
[PDF]SpikeRED: Fully Spike-Driven RGB-Event Object Detection with Event-Guided Fusion and Box-Guided Query Refinement▼4.3k2.00
[PDF]ProFiNER: Progressive Entity Calibration and Conflict-Aware Inference for Zero-Shot Named Entity Recognition▼4.5k2.67
[PDF]MARS: Multi-Evidence Adaptive Search with State-Preserving Control for Repository-Level Program Repair▼4.3k2.00
[PDF]Adaptation Is Not Retention: Reframing Continual Low-Rank Adaptation through Response Coordinates▼5.9k2.33
[PDF]Parameterized Complexity of -Lipschitz Constants for Input Convex Neural Networks and -Norm Maximization over Zonotopes▲2453.00
[PDF]Beyond Action Entropy: Quotient-Space Exploration for Genome-Scale Metabolic Model Repair▼4.5k2.67
[PDF]Learning What Not to Learn: Target-Conditioned Update Eligibility for Self-Improving Agents▼5.9k2.33
[PDF]CTDG-THOR: Query-Side Second-Order Temporal History Routing for Continuous-Time Dynamic Graphs▼1361.33
[PDF]SphereJEPA: Learning Spherical Video Representations From Perspective Video via Self-Supervision▲3.1k2.40
Withdrawn or desk rejected (8,245)
[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]Same-Checkpoint Intervention on Pre- and Post-Context States in Entity-Local Temporal EncodersWithdrawn1.33
[PDF]Pulse2View: Same-Sensor Cross-View Pre-Training for Patient-Level Multi-Disease Classification from Wearable PPGWithdrawn1.67