pretrained weights

5 papers

• ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion Generation
• REVE: A Foundation Model for EEG - Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects
• Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding
• TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception
• Understanding Differential Transformer Unchains Pretrained Self-Attentions