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3,951 results for “keyword:"ad"” in ICLR 2027. 1,018 withdrawn or desk rejected listed apart.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]C2F-DiffAttack: Coarse-to-fine diffusion for local black-box attack on time series classifiers▼4.3k2.00
[PDF]Item Content Helps the Long Tail but Hurts Popular Items in Sequential Recommendation under a Lexical Encoder: Frequency-Gated Content Injection▼1.2k1.67
[PDF]STEPS: Spectral–Temporal Error Propagation for Test-Time Adaptation in Time-Series Forecasting▲3.0k2.33
[PDF]PonderAgent: A Risk-Adaptive Dual-System Framework for Safe and Selective Mobile GUI Agents▲11.00
[PDF]Smooth Spectral Operators for Indefinite Hessians: Relative Resolution, Stability, and Matrix-Free Approximation▼1611.50
[PDF]Unveiling Lookahead’s Potential in Sharpness-Aware Minimization: Convergence and Generalization Revisited▲3892.67
[PDF]Is Adaptation Worth the Cost? Economics-Guided Test-Time Adaptation under Budget Constraints▼4.5k2.67
[PDF]Whose Brain Is It? Reader Identity Accounts for Almost All of EEG-to-Text Retrieval, and a Per-Reader Adapter Recovers It▲3.0k2.33
[PDF]The Alignment Boundary in Cross-Subject Imagined-Speech EEG: Provable Limits of Pre-Alignment and In-Training Alignment▼1361.33
[PDF]Tracing Chains of Evidence: Cross-View Test-Time Adaptation for Point Cloud Part Segmentation▲1.7k3.33
[PDF]Cooperative Words, Adversarial Actions: Action-Level Ambiguity in Embodied Multi-Agent Systems▼13k2.00
Withdrawn or desk rejected (1,018)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