%0 Journal Article %1 journals/corr/abs-2310-05863 %A Sun, Guangzhi %A Yu, Wenyi %A Tang, Changli %A Chen, Xianzhao %A Tan, Tian %A Li, Wei %A Lu, Lu %A Ma, Zejun %A Zhang, Chao %D 2023 %J CoRR %K dblp %T Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models. %U http://dblp.uni-trier.de/db/journals/corr/corr2310.html#abs-2310-05863 %V abs/2310.05863

@article{journals/corr/abs-2310-05863, added-at = {2024-07-22T00:00:00.000+0200}, author = {Sun, Guangzhi and Yu, Wenyi and Tang, Changli and Chen, Xianzhao and Tan, Tian and Li, Wei and Lu, Lu and Ma, Zejun and Zhang, Chao}, biburl = {https://www.bibsonomy.org/bibtex/2314f2c8e6eb23599b7b95bb2311ae867/dblp}, ee = {https://doi.org/10.48550/arXiv.2310.05863}, interhash = {7d3c4bcf12d006c5807ba1fcea186d86}, intrahash = {314f2c8e6eb23599b7b95bb2311ae867}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-07-29T07:05:47.000+0200}, title = {Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2310.html#abs-2310-05863}, volume = {abs/2310.05863}, year = 2023 }