热点
"LLaDA-V" 相关文章
This AI Paper Introduces LLaDA-V: A Purely Diffusion-Based Multimodal Large Language Model for Visual Instruction Tuning and Multimodal Reasoning
MarkTechPost@AI 2025-06-03T02:45:50.000000Z
舍弃自回归！国内团队打造纯扩散多模态大模型LLaDA-V，理解任务新SOTA
掘金 人工智能 2025-05-27T09:43:01.000000Z