Attention IoU: Examining Biases in CelebA using Attention Maps Paper • 2503.19846 • Published Mar 25 • 7
xT: Nested Tokenization for Larger Context in Large Images Paper • 2403.01915 • Published Mar 4, 2024 • 1
Unifying Specialized Visual Encoders for Video Language Models Paper • 2501.01426 • Published Jan 2 • 21