← Search

Alessandro Pietro Serra

2 accepted papers

2025

The Narrow Gate: Localized Image-Text Communication in Native Multimodal Models

NeurIPS 2025poster

Recent advances in multimodal training have significantly improved the integration of image understanding and generation within a unified model. This study investigates how vision-language models (VLMs) handle image-understanding tasks, focusing on how visual information is processed and transferred…

Cited by 0SourceScholar
2024

The Representation Landscape of Few-Shot Learning and Fine-Tuning in Large Language Models

NeurIPS 2024poster

In-context learning (ICL) and supervised fine-tuning (SFT) are two common strategies for improving the performance of modern large language models (LLMs) on specific tasks. Despite their different natures, these strategies often lead to comparable performance gains. However, little is known about w…