4 accepted papers
We introduce NerVE, a unified eigenspectral framework for understanding how feed-forward networks (FFNs) in large language models (LLMs) organize and regulate information flow in high-dimensional latent space. Despite FFNs dominating the parameter budget, their high-dimensional dynamics remain poorl…
As Large Language Models (LLMs) scale, the question is not just how large they become, but how much of their capacity is effectively utilized . Existing scaling laws relate model size to loss, yet overlook how components exploit their latent space. In this work, we focus on Feed-Forward Networks (FF
The simultaneous rise of machine learning as a service and concerns over user privacy have increasingly motivated the need for private inference (PI). While recent work demonstrates PI is possible using cryptographic primitives, the computational overheads render it impractical. State-of-art deep ne…
The recent rise of privacy concerns has led researchers to devise methods for private neural inference—where inferences are made directly on encrypted data, never seeing inputs. The primary challenge facing private inference is that computing on encrypted data levies an impractically-high latency pe…