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
21,644 results for “keyword:"ar"” in ICLR 2027. 5,063 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents▲9.2k2.67
[PDF]PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents▼5.9k2.33
[PDF]What does lie-detection accuracy measure? An Identification Audit of behavioural LLM deception benchmarks▼71.25
[PDF]AgentVIF: Event-Aware Multi-Agent Adaptation to Dynamic Degradations in Visible–Infrared Video Fusion▲6.6k3.33
[PDF]Right Verdict, Wrong Reason: Counterfactual Attribution Reveals Shortcut Learning in LLM Evaluators▼1.2k1.67
[PDF]VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts▼4.3k2.75
[PDF]Hindsight Compacts but Does Not Repair: Rethinking On-Policy Self-Distillation in Reasoning Models▼1.3k1.75
[PDF]A Bayesian Perspective on Task Retrieval and Task Learning in In-Context Learning on Markovian Data▲3.0k2.33
[PDF]Characterizing the Topological Distribution of Compromised Clients in Decentralized Federated Learning via Model Deviation▼1361.33
[PDF]ChainBait: Task-Conditioned Indirect Prompt Injection Exposes Reasoning-Configuration Gaps▼5.3k1.33
[PDF]ConsistNav: Improving Action Consistency in Zero-Shot Object Navigation with Semantic Executive Control▲3.0k2.33
[PDF]OmniEarthSeg: Unified Instruction-Driven Segmentation for Heterogeneous Remote Sensing Imagery▲5093.00
[PDF]Privacy-Aware Dirichlet Process Mixture Models: Diffusion-Based Trajectory Protection and Differentially Private Weights▲6.1k2.00
[PDF]NICE-CV: Neural Inference- and Cost-Efficient architecture search for Computer Vision models with online proxy calibration▼1.3k1.75
[PDF]Homogenization of -Adversarial Training in High-Dimensions: Exact Dynamics under Stochastic Gradient Descent▼5.9k2.33
[PDF]Your “Pro” LLM Subscription May Actually Be “Free”: Exposing Fingerprint Spoofing Risks in LLM Inference Services▼1.2k1.67
[PDF]PARA: Patch-based Adaptive multi-Resolution, time-Advancing and scale-equivariant neural PDE solver▲5093.00
[PDF]A Claim-Centered Publication Framework for Efficient Auditing of AI-Assisted Theoretical Research▼4.3k2.00
Withdrawn or desk rejected (5,063)
[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