most citedAdvancing Single and Multi-task Text Classification through Large Language Model Fine-tuning

4 citations · 4 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2025

Scaling Up Audio-Synchronized Visual Animation: An Efficient Training Paradigm

Lin Zhang, Zefan Cai, Yufan Zhou +10

Recent advances in audio-synchronized visual animation enable control of video content using audios from specific classes. However, existing methods rely heavily on expensive manua…