Larian Studios Says It Won't Use Generative AI to Create Divinity Concept Art

Larian CEO Swen Vincke had sparked controversy last month after confirming that the studio was experimenting with AI tools in ...
IEEE

Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion

Abstract: We present Florence-VL, a new family of multimodal large language models (MLLMs) with enriched visual representations produced by Florence-2 [45], a generative vision foundation model.