4 citations · 6 across the 7 of their papers we have counts for
5 papers · 1 filter
INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
Angelika Romanou, Negar Foroutan, Anna Sotnikova +56
The performance differential of large language models (LLM) between languages hinders their effective deployment in many regions, inhibiting the potential economic and societal val…
SaSR-Net: Source-Aware Semantic Representation Network for Enhancing Audio-Visual Question Answering
Tianyu Yang, Yiyang Nan, Lisen Dai +3
Audio-Visual Question Answering (AVQA) is a challenging task that involves answering questions based on both auditory and visual information in videos. A significant challenge is i…
Continual Audio-Visual Sound Separation
Weiguo Pian, Yiyang Nan, Shijian Deng +3
In this paper, we introduce a novel continual audio-visual sound separation task, aiming to continuously separate sound sources for new classes while preserving performance on prev…
Hear Me, See Me, Understand Me: Audio-Visual Autism Behavior Recognition
Shijian Deng, Erin E. Kosloski, Siddhi Patel +9
In this article, we introduce a novel problem of audio-visual autism behavior recognition, which includes social behavior recognition, an essential aspect previously omitted in AI-…
Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation
Nihal V. Nayak, Yiyang Nan, Avi Trost +1
We introduce Bonito, an open-source model for conditional task generation that converts unannotated text into task-specific training datasets for instruction tuning. We aim to enab…