2 papers
cs.CV2025
WorldGen: From Text to Traversable and Interactive 3D Worlds
Dilin Wang, Hyunyoung Jung, Tom Monnier +22
We introduce WorldGen, a system that enables the automatic creation of large-scale, interactive 3D worlds directly from text prompts. Our approach transforms natural language descr…
cs.CV2025
MMGenBench: Fully Automatically Evaluating LMMs from the Text-to-Image Generation Perspective
Hailang Huang, Yong Wang, Zixuan Huang +4
Large Multimodal Models (LMMs) demonstrate impressive capabilities. However, current benchmarks predominantly focus on image comprehension in specific domains, and these benchmarks…