In progress2026SPAR · Co-mentor

Multimodal Safety & Interpretability in Encoder-Free VLMs

Overview

Safety and interpretability of unified, encoder-free vision-language models. A SPAR project I co-mentor.

This work is in progress. Details and results will be shared here once it is published. Get in touch if you'd like to discuss it.

Results

Results will be posted here once the work is published.

Updates

2026Project started as part of SPAR.

Cite

Work in progress. If you refer to this project before a paper is available, please cite this page:

@misc{saxena2026encoderfreevlm,
  title        = {Multimodal Safety and Interpretability in Encoder-Free Vision-Language Models},
  author       = {Saxena, Rohit and others},
  year         = {2026},
  howpublished = {\url{https://saxenarohit.github.io/projects/encoder-free-vlm-safety/}},
  note         = {SPAR research project. Work in progress}
}