Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.
Yue Zhang, Ke Sun, Zhen Lin et al. · 3 Mar 2026
High-quality scientific illustrations are essential for communicating complex scientific and technical concepts, yet existing automated systems remain limited in editability, stylistic controllability, and efficiency.
Yue Zhang, Zhen Lin, Qiujie Xie et al. · 3 Feb 2026
FigureBench presents the first large-scale benchmark for generating scientific illustrations from long-form scientific texts, while AutoFigure introduces an agentic framework that produces publication-ready illustrations through extensive thinking, recombination, and validation processes.
Yuan Zhang, Yijun Yang, Hang Xu et al. · 5 May 2026
JoyAI-Image integrates a spatially enhanced MLLM with MMDiT to achieve unified visual understanding, text-to-image generation, and instruction-guided image editing with enhanced spatial intelligence.