Paolo Rota

Leading MLLMs still struggle to articulate and localize physical changes across revisited scenes, exposing a fundamental blind spot in multi-image spatial grounding that targeted synthetic data can overcome.

Skip the labeled data: TEGU uses LLM-derived textual information to achieve state-of-the-art zero-shot temporal action localization.

VLMs struggle with Earth observation tasks involving complex land use, but a new dataset with nearly 10 million text annotations could change that.