Papers by Julian Asilis

1 papers
Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Steering methods have emerged as effective tools for guiding large language models’ behavior, yet multimodal large language model lacks comparable techniques due to architectural diversity and limited availability of multimodal steering vectors.
Approach: They validate steering vectors derived solely from text-only LLM backbones and use a cross-modal transfer technique to reuse existing interpretability tools.
Outcome: The proposed steering vectors can guide and enhance multimodal models using SPAR, Mean Shift, and Linear Probing.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations