Junlin Han

Early unification in multimodal training can prevent models from becoming overly reliant on language, unlocking new efficiencies in generative performance.

Forget brute-force context windows: a small vision-language model can compress hour-long videos below theoretical limits by intelligently prioritizing relevant content.

Vision models are far more data-hungry than language models, but Mixture-of-Experts can harmonize this asymmetry for truly unified multimodal models.