← Search

Lilian Ngweta

2 accepted papers

2024

Aligners: Decoupling LLMs and Alignment

EMNLP 2024finding

Large Language Models (LLMs) need to be aligned with human expectations to ensure their safety and utility in most applications. Alignment is challenging, costly, and needs to be repeated for every LLM and alignment criterion. We propose to decouple LLMs and alignment by training *aligner* models th…

2023

Simple Disentanglement of Style and Content in Visual Representations

ICML 2023poster

Learning visual representations with interpretable features, i.e., disentangled representations, remains a challenging problem. Existing methods demonstrate some success but are hard to apply to large-scale vision datasets like ImageNet. In this work, we propose a simple post-processing framework to…