What matters for Representation Alignment: Global Information or Spatial Structure? Paper • 2512.10794 • Published 20 days ago • 8
view article Article We’re open-sourcing our text-to-image model and the process behind it Nov 12, 2025 • 76
Diffusion Transformers with Representation Autoencoders Paper • 2510.11690 • Published Oct 13, 2025 • 165
Negative Token Merging: Image-based Adversarial Feature Guidance Paper • 2412.01339 • Published Dec 2, 2024 • 22
AIMv2 Collection A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint. • 19 items • Updated Aug 25, 2025 • 82
OpenDevin: An Open Platform for AI Software Developers as Generalist Agents Paper • 2407.16741 • Published Jul 23, 2024 • 74