Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows Paper • 2512.16969 • Published 7 days ago • 101
Next-Embedding Prediction Makes Strong Vision Learners Paper • 2512.16922 • Published 7 days ago • 77
Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling Paper • 2512.12675 • Published 11 days ago • 40
SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder Paper • 2512.11749 • Published 13 days ago • 36
TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows Paper • 2512.05150 • Published 22 days ago • 74