MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning Paper • 2510.14958 • Published Oct 16 • 22
SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models Paper • 2510.12784 • Published Oct 14 • 19
XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation Paper • 2506.21416 • Published Jun 26 • 28