works on
large language models 1post-training dynamics 1preference optimization 1supervised fine-tuning 1value alignment 1

From the 1 of 14 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs

Benno Krojer, Shravan Nayak, Oscar Mañas +4

Transforming a large language model (LLM) into a vision-language model (VLM) can be achieved by mapping the visual tokens from a vision encoder into the embedding space of an LLM.…