Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling Paper • 2512.12675 • Published 18 days ago • 40
SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder Paper • 2512.11749 • Published 20 days ago • 36
Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights Paper • 2512.01816 • Published about 1 month ago • 88
Quantile Advantage Estimation for Entropy-Safe Reasoning Paper • 2509.22611 • Published Sep 26, 2025 • 118