Audio-visual data curation: AVE-2, 570K+ clips scored for temporal alignment, physical causality and source visibility with LLM/VLM weak supervision (LTU-AS, LLaVA-NeXT, Mistral 7B); cross-modal retrieval; Python, PyTorch, Azure.
Research Intern
Research Intern
Tue Apr 30 2024 20:00:00 GMT-0400 (Eastern Daylight Time)