Kushwaha, Saksham Singh

3 publications

NeurIPS 2025 $\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time Sarthak Kumar Maharana, Saksham Singh Kushwaha, Baoming Zhang, Adrian Rodriguez, Songtao Wei, Yapeng Tian, Yunhui Guo

CVPR 2025 VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation Saksham Singh Kushwaha, Yapeng Tian

TMLR 2024 Audio-Visual Dataset Distillation Saksham Singh Kushwaha, Siva Sai Nagender Vasireddy, Kai Wang, Yapeng Tian