Simon Jenni

Unimodal models might already understand each other better than we thought: a shared relational structure, formalized via category theory, unlocks zero-shot cross-modal alignment.

You can drastically improve text-to-image retrieval from short, ambiguous queries by using a language model to generate richer, quality-aware descriptions.

Forget handcrafted metrics: RetouchIQ uses an RL-tuned MLLM to generate its own reward signals for instruction-based image editing, leading to more semantically consistent and perceptually pleasing results.