REVE: A Foundation Model for EEG -- Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects Paper • 2510.21585 • Published Oct 24, 2025 • 7
D5P4: Partition Determinantal Point Process for Diversity in Parallel Discrete Diffusion Decoding Paper • 2603.19146 • Published 5 days ago
Inner Loop Inference for Pretrained Transformers: Unlocking Latent Capabilities Without Training Paper • 2602.14759 • Published Feb 16
Residual Connections and the Causal Shift: Uncovering a Structural Misalignment in Transformers Paper • 2602.14760 • Published Feb 16