Saksham Singh Kushwaha

sakshamsingh1's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 3 papers 24 days ago

VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation

Paper • 2412.10768 • Published Dec 14, 2024

$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time

Paper • 2506.00358 • Published May 31, 2025

Object-WIPER : Training-Free Object and Associated Effect Removal in Videos

Paper • 2601.06391 • Published Jan 10 • 2