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
21,629 results for “keyword:"ar"” in ICLR 2027. 5,078 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Spectral-Driven Adaptive-Rank Optimizer for Large Language Model Reinforcement Learning with Verifiable Rewards▲3.1k2.33
[PDF]DRFR:Deviation Representation and Failure Risk Learning for Weakly Supervised Continual Monitoring of Robot Task Semantics▼1.2k1.67
[PDF]When Fine-Grained Credit Assignment Helps and Hurts: Multimodal Agentic Reinforcement Learning through Video Editing▲3.1k2.33
[PDF]Associative-Retrieval Regime Entry Varies with Head Partition Under a Fixed Training Protocol in Transformers▲31.00
[PDF]LG-Transformer: LLM-Guided Discovery of Boosted Novel Transformer Models for Time-Series Modeling▲31.00
[PDF]Provably Efficient Algorithm Configuration with Local Structure and Reuse of Observations▲3322.67
[PDF]INCUMBENT: THE MODEL PROPOSES, THE STORE DISPOSES — STRUCTURAL TRUTH MAINTENANCE FOR AGENT MEMORY▼4.3k2.00
[PDF]Don't Learn When to Trigger, Learn When Waiting Is Not Worthwhile: A New Framework for Dynamic Task–Resource Assignment▼21k1.67
[PDF]Preserve, Then Bound: Conditionally Informative Acoustic Context for Few-Shot ATC Call-Sign Spotting▼4.3k2.00
[PDF]Do Reinforcement Learning Controllers Use Live State? A Diagnostic for Metro Operations▼1361.33
[PDF]Structure, Dimensionality, and Distribution Shape: What Makes Pretraining Data Transferable, and Why the Input Pipeline Decides Which▼5.9k2.33
[PDF]FlexTempRule: Interpretable Time Series Classification via Learning Flexible Temporal Logic Rules▼1.2k1.67
[PDF]Gaussian Stippling: Efficient Sorting-Free 3D Gaussian Rendering through Hybrid Sampling and Spatiotemporal Reconstruction▲293.33
[PDF]CellHIST: A Cell-Centric Dataset and Benchmark for Weakly-Supervised Virtual Spatial Transcriptomics from Histopathology▼4.5k2.67
[PDF]FAROS: Characterizing Coding-Agent Search for Executable Time-Series Anomaly Detectors▼1.3k1.75
Withdrawn or desk rejected (5,078)
[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