Roy Schwartz

Text-to-image generation models suffer from alignment problems, where generated images fail to accurately capture the objects and relations in the text prompt. Prior work has focused on improving alignment by refining the diffusion process, ignoring the role of the text encoder, which guides the...

Large language models (LLMs) often encode word-form variation (e.g., walk vs. walk ed ) as linear directions in the embedding space. However, standard tokenization algorithms treat such variants as distinct words with different vocabulary entries—quickly filling the size-capped token vocabulary w...