2 papers
cs.CV2026
CoFi-UCGen: Coarse-to-Fine Unsupervised Conditional Generation without Label Priors
Shengxi Li, Zhaokun Hu, Ce Zheng +3
Unsupervised conditional image generation (UCGen) aims to control generation without relying on manually annotated labels, yet remains challenging due to unstructured semantic repr…
cs.MM2025
MAVERIX: Multimodal Audio-Visual Evaluation and Recognition IndeX
Liuyue Xie, Avik Kuthiala, George Z. Wei +12
We introduce MAVERIX (Multimodal audiovisual Evaluation and Recognition IndeX), a unified benchmark to probe the video understanding in multimodal LLMs, encompassing video, audio,…