Unified Reward Model for Multimodal Understanding and Generation Paper • 2503.05236 • Published Mar 7 • 119
Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders Paper • 2503.03601 • Published Mar 5 • 230
Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion Paper • 2409.11406 • Published Sep 17, 2024 • 28