2 papers
cs.LG2025
DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights
Liana Mikaelyan, Ayyoob Imani, Mathew Salvaris +2
We introduce DeltaLLM, a new post-training compression technique to reduce the memory footprint of LLMs. We propose an alternative way of structuring LLMs with weight sharing betwe…
cs.CV2022
Matching Multiple Perspectives for Efficient Representation Learning
Omiros Pantazis, Mathew Salvaris
Representation learning approaches typically rely on images of objects captured from a single perspective that are transformed using affine transformations. Additionally, self-supe…