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
413 results for “keyword:"pretrain"” in ICLR 2027. 78 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Shifted-window Diffusion with Temporal-distance Attention for Self-Supervised Time-Series Forecasting▼4.3k2.00
[PDF]TRACE: Temporal Routing with Autoregressive Cross-channel Experts for EEG Representation Learning▼5.8k2.33
[PDF]ChromaMuon: Spectral Optimizer Diagnostics and Design with Retained Newton–Schulz Coordinates▼1.2k1.67
[PDF]SANLAPA: Adversarial Masked Language Modeling via Differentiable Teacher-Student Minimax Pre-training▼5.8k2.33
[PDF]Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings▼4.3k2.00
[PDF]UMM-JEPA: Generative Pretraining via Masked Next-Scale Representation Prediction for Unified Multimodal Models▲432.75
[PDF]Consero: Knowledge-Informed Prediction Framework with Language and Tabular Foundation Models▲3.0k2.33
[PDF]Synthetic to SPX: Model-Based Pre-Training for Diffusion Models of Financial Time Series▼1361.33
[PDF]Not All Dimensions Are Equal: Outlier-Aware Attention Linearization with Grouped Quadratic Kernels▲6.1k2.00
[PDF]Structure, Dimensionality, and Distribution Shape: What Makes Pretraining Data Transferable, and Why the Input Pipeline Decides Which▼5.8k2.33
[PDF]Pretraining Shapes Spectral Structure: Architecture- and Strategy-Conditional Prediction of OOD Robustness in Foundation Models▼1361.33
[PDF]From Minutes to Days: Scaling Intracranial Speech Decoding with Supervised Pretraining▼4.3k2.00
[PDF]Corrupted Inputs Make Dense Supervision Informative for Zero-Shot Variant Scoring: A Controlled Factorial Study of Compact Protein Encoders▼5.4k1.50
Withdrawn or desk rejected (78)
[PDF]The Variance Brain Foundation Models Forgot: A Third-Order Basis for Predicting Individual DifferencesWithdrawn1.67
[PDF]Learning to Be Fooled: pretraining grows knowledge but keeps the scar of framing susceptibilityDesk rejected
[PDF]Approximating Softmax in Pretrained LLMs: Model Sensitivity and Kernel AccelerationWithdrawn1.67