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
33,057 results for “keyword:"r"” in ICLR 2027. 8,243 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]MemCredit: Reinforcement Learning for Memory-Based Search Agents via Retained-State Credit Assignment▲4.7k3.00
[PDF]FedESO: Exploration-to-Stabilization Optimization for Model-Heterogeneous Federated Learning▼5.9k2.33
[PDF]Beyond Update Geometry: Post-Commitment Auditing of Individual Decision Influence for Proposal Admission in Decentralized Federated Graph-Level Clustering▼5.3k1.33
[PDF]Evaluating Dynamical Fidelity through Predictive Structure in Physical Representations▼4.3k2.00
[PDF]Training Hybrid Quantum Policies with Classical Surrogates for Actor–Critic Reinforcement Learning▼4.3k2.00
[PDF]Discarding Sensor Depth: Reliability-Aware Geometry Learning for Salient Object Detection▼5.9k2.33
[PDF]MatchVLM: Synergizing Vision-Language Models and Local Feature Matching for Cross-View Point Correspondence▲4743.00
[PDF]Personalized but Unchecked: Safe Personalization Requires Conditional Control in Medical Advice▼1.2k1.67
[PDF]SPIRA: A Spatially-Variant Reinforcement-Learning Agent for Unsupervised Imaging Inverse Problems▼1361.33
[PDF]Remember Smarter: Visual History Compressor and Hyperbolic Experience Space for Robotic Memory▼1361.33
[PDF]Do You Even Need More Data? Rethinking LLM Deployment for Label-Scarce Tabular Classification with TabLens▼1431.50
[PDF]Grounding Is Inherited, Action Is Concentrated: What VLA Finetuning Adds to a Web-Pretrained VLM▼51.25
[PDF]Sketch–Solver: Decoupling Construction and Parameterization for Natural-Language CAD Program Synthesis▼1.2k1.67
[PDF]FINE-GRAINED DEVICE-DIRECTED SPEECH RECOGNITION: FROM OFFLINE MODELING TO STREAMING INFERENCE▼1361.33
Withdrawn or desk rejected (8,243)
[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