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
3,951 results for “keyword:"ad"” in ICLR 2027. 1,018 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models▼4.3k2.00
[PDF]KalmanCache+: Uncertainty-Aware Closed-Loop Diffusion Caching via Predict–Trust–Correct Residual Estimation▲8.9k2.75
[PDF]Who Scores the Tutor? Sampling Noise and Self-Preference in Simulated-Learner Evaluation▼4.3k2.00
[PDF]Sem2Pix: Privacy Leakage from Gradients via Semantic-to-Pixel Fine-Grained Guidance Diffusion Models▼5.9k2.33
[PDF]Graph-Constrained Heterogeneous Tree Allocation for Workload-Adaptive Speculative Decoding▼1.3k1.75
[PDF]Amplification Without Repair: Causal Limits of Activation Steering in Abstract Reasoning▼5.9k2.50
[PDF]VEC-CT: Visual Cue-Guided Error-Corrective Clinical Reasoning for Lung CT Report Generation▼4.3k2.00
[PDF]Hourglass: Towards Better Unified Multimodal Modeling Through Hierarchical Sharing and Conflict-Aware Gradient Surgery▼5.9k2.50
[PDF]A New Approach to Bilevel Optimization: A Value-Centric Perspective via a Distributional Follower▼5.9k2.33
[PDF]A Two-Scalar Law for Activation Functions: How Peak Slope and Peak Curvature Govern Adversarial Robustness▼1.2k1.67
[PDF]Probabilistic Mixed-Effects Graph Autoencoding for Individualized Multi-Paradigm Functional Connectome Modeling▲3912.67
[PDF]SynMorph: Learning to Build Task-Adaptive Spatiotemporal Models from Synaptic Primitives▼4.3k2.00
[PDF]Deeper Is Not Better for Quantized CLIP: Early Readout Recovers Accuracy While Cutting Compute▼5.9k2.33
Withdrawn or desk rejected (1,018)
[PDF]FairWatch: Interaction Topology as a First-Order Variable Shaping Safety and Fairness in Multi-Agent DeliberationDesk rejected2.00