3 papers
cs.LG2025
Deep Augmentation: Dropout as Augmentation for Self-Supervised Learning
Rickard Brüel-Gabrielsson, Tongzhou Wang, Manel Baradad +1
Despite dropout's ubiquity in machine learning, its effectiveness as a form of data augmentation remains under-explored. We address two key questions: (i) When is dropout effective…
cs.DC2025
Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead
Rickard Brüel-Gabrielsson, Jiacheng Zhu, Onkar Bhardwaj +4
Fine-tuning large language models (LLMs) with low-rank adaptations (LoRAs) has become common practice, often yielding numerous copies of the same LLM differing only in their LoRA u…
cs.LG2025
Closed-Form Diffusion Models
Christopher Scarvelis, Haitz Sáez de Ocáriz Borde, Justin Solomon
Score-based generative models (SGMs) sample from a target distribution by iteratively transforming noise using the score function of the perturbed target. For any finite training s…