Two Stony Brook University research initiatives were awarded seed funding through the SUNY Technology Accelerator Fund (TAF), which supports groundbreaking research opportunities and helps faculty inventors and scientists turn their research into market-ready technologies.

SUNY TAF targets critical research such as feasibility studies, prototyping and testing, which demonstrate that an idea or innovation has commercial potential. The goal is to accelerate time to market for these innovations and increase their market readiness for potential investors, strategic partners and customers.

Researchers have long recognised that for artificial intelligence to truly collaborate with people, it must accurately anticipate human intentions. Peter Zeng, Weiling Li, and Amie Paige, from Stony Brook University, alongside Zhengxiang Wang, Panagiotis Kaliosis, Dimitris Samaras et al, investigated how Large Visual Language Models (LVLMs) establish ‘common ground’ during communication , a fundamental aspect of human interaction. Their new study, detailed in a referential communication experiment, reveals a significant limitation in LVLMs’ ability to interactively resolve ambiguous references, using a unique dataset of 356 human and machine dialogues.