1 citations · 1 across the 9 of their papers we have counts for
4 papers · 1 filter
FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction
Runqi Lin, Alasdair Paren, Suqin Yuan +4
The integration of new modalities enhances the capabilities of multimodal large language models (MLLMs) but also introduces additional vulnerabilities. In particular, simple visual…
Focus On This, Not That! Steering LLMs with Adaptive Feature Specification
Tom A. Lamb, Adam Davies, Alasdair Paren +2
Despite the success of Instruction Tuning (IT) in training large language models (LLMs), such models often leverage spurious or biased features learnt from their training data and…
Universal In-Context Approximation By Prompting Fully Recurrent Models
Aleksandar Petrov, Tom A. Lamb, Alasdair Paren +2
Zero-shot and in-context learning enable solving tasks without model fine-tuning, making them essential for developing generative model solutions. Therefore, it is crucial to under…
A Stochastic Bundle Method for Interpolating Networks
Alasdair Paren, Leonard Berrada, Rudra P. K. Poudel +1
We propose a novel method for training deep neural networks that are capable of interpolation, that is, driving the empirical loss to zero. At each iteration, our method constructs…