Shuai Bai

FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark

Revisiting Multimodal Positional Encoding in Vision–Language Models

ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models