All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation Paper • 2609.27901 • Published 1 day ago • 4
CRISP: Persistent Concept Unlearning via Sparse Autoencoders Paper • 2508.13650 • Published Aug 19, 2025 • 16
RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation Paper • 2504.17502 • Published Apr 24, 2025 • 55
Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models Paper • 2501.06751 • Published Jan 12, 2025 • 31
Bringing Objects to Life: 4D generation from 3D objects Paper • 2412.20422 • Published Dec 29, 2024 • 41