Search papers, labs, and topics across Lattice.
Affiliation:, Dartmouth College
3
0
4
10
Zero-shot LLM agents struggle to predict wellbeing scores from longitudinal data, often performing no better than a basic mean baseline.
Reliability scores in multimodal systems may not influence decisions as expected, revealing a disconnect between potential and actual performance gains. WHY_IT MATTERS: This insight challenges assumptions about the utility of reliability metrics in multimodal systems, potentially reshaping how researchers design and evaluate these models.
Achieve zero-shot sensor understanding across diverse sensor setups by repurposing a pretrained language model with a novel sensor-language alignment framework.
