3 citations · 5 across the 9 of their papers we have counts for
4 papers · 1 filter
Revealing Structured Heterogeneity
Christopher Turansick
In this paper, we study models of restricted heterogeneity. While the random utility model allows for arbitrary heterogeneity among rational types, we consider the case when an ana…
Training-Free Speech-Centric Omni Understanding with Frozen VLMs
Ankan Deria, Hanoona Rasheed, Xilin He +2
Audio-visual understanding remains challenging because models must jointly interpret spoken content, visual events, and their temporal relationships. Existing omni models typically…
Conversational Human Audio-visual Talking Dialogue Generation
Junhao Song, Lluis Guasch, Xilin He +8
Large-scale dyadic interactive audio-visual dialogue (DIAD) datasets provide fundamental data resources for developing humanoid interactive virtual agents and digital humans. Howev…
CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning
Ankan Deria, Komal Kumar, Xilin He +4
Recent vision-language models (VLMs) typically rely on a single vision encoder trained with contrastive image-text objectives, such as CLIP-style pretraining. While contrastive enc…