RBench-V: A Primary Assessment for Visual Reasoning Models with Multi-modal Outputs Paper • 2505.16770 • Published May 22, 2025 • 12
Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs Paper • 2510.13795 • Published Oct 15, 2025 • 59
PresentBench: A Fine-Grained Rubric-Based Benchmark for Slide Generation Paper • 2603.07244 • Published 17 days ago • 2