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
21,630 results for “keyword:"ar"” in ICLR 2027. 5,077 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]From Relevance to Decision Value: Low-Overhead Trajectory-Grounded Memory Valuation and Selection for LLM Agents▲14k3.00
[PDF]EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training▲3.1k2.33
[PDF]Semiparametrically Efficient Off-Policy Evaluation and Learning in Constrained Markov Decision Processes▼4.3k2.00
[PDF]MemoReason: Evaluating the Effect of Parametric Memory on Contextual Reasoning in LLMs▲3.1k2.33
[PDF]CLoRE: Drift-Controlled Continual Learning of LLMs via Expert Expansion with Reservoir Routing▲9.3k2.67
[PDF]The Model Already Has a Dictionary: Cumulative SVD Features as a Training-Free Alternative to Sparse Autoencoders▲3342.67
[PDF]UniRefDet: Universal Referring Detection of Salient and Camouflaged Objects in Unconstrained Scenes▼4.3k2.00
[PDF]ES4SURV: AN EVIDENCE-SEEKING MULTIMODAL LARGE LANGUAGE MODEL FOR WHOLE-SLIDE SURVIVAL PREDICTION▼4.3k2.00
[PDF]Meta-Diffusion: Transferable Reverse-Dynamics Coordinates for Data-Asymmetric Generation▼4.3k2.00
[PDF]Prospective Interpretation Risk: Predicting and Preventing Miscommunication Between LLM Agents▲3.1k2.33
[PDF]SelectTTRL: Representation-Guided Data Selection for Efficient Test-Time Reinforcement Learning▼1.2k1.67
[PDF]Preserving Fine-Grained Structure under Coarse Supervision via EMA-Guided Similarity-Weighted Contrastive Learning▼1361.33
[PDF]Swiftly Generating Whittle Index in a Changing Environment: An Environment Parameter-Driven Actor-Critic Approach▲3342.67
[PDF]VR-JEPA: Learning Contrastive-State Latent Guidance for Generation-based Video Reasoning▲1.7k3.33
[PDF]DySCo: A Lightweight Data Curation Framework for Reinforcement Learning in SMILES-based Molecular Design▼1.2k1.67
[PDF]FitBench: Benchmarking Human–AI Collaboration across Option-Picking-Driven Decision Styles▼4.3k2.00
[PDF]When Negative Advantages Are Unreliable: Risk-Calibrated Negative Suppression for Generative Recommendation▲9.8k2.75
[PDF]Symbol and Rule Discovery in Continuous Control Through Progressive Inductive Abductive Learning▼5.9k2.50
Withdrawn or desk rejected (5,077)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[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