热点
"多模态任务" 相关文章
o3和o4-mini来了！OpenAI突破最强“看图思考”，开源AI编程神器，史上最大收购曝光
2025-04-19T06:13:57.000000Z
R1-Omni开源！全模态模型+RLVR，让各模态作用清晰可见
通义 2025-04-09T10:05:39.000000Z
Google Gemini now works across multiple apps in a single prompt
The Verge - Artificial Intelligences 2025-01-22T18:02:26.000000Z
Researchers from MIT, Google DeepMind, and Oxford Unveil Why Vision-Language Models Do Not Understand Negation and Proposes a Groundbreaking Solution
MarkTechPost@AI 2025-01-20T01:35:03.000000Z
Florence-VL来了！使用生成式视觉编码器，重新定义多模态大语言模型视觉信息
机器之心 2024-12-18T09:24:10.000000Z
LLaMA-Mesh: A Novel AI Approach that Unifies 3D Mesh Generation with Large Language Models by Representing Meshes as Plain Text
MarkTechPost@AI 2024-11-17T07:19:53.000000Z
BLIP3-KALE: An Open-Source Dataset of 218 Million Image-Text Pairs Transforming Image Captioning with Knowledge-Augmented Dense Descriptions
MarkTechPost@AI 2024-11-14T07:50:16.000000Z
Med-MoE: A Lightweight Framework for Efficient Multimodal Medical Decision-Making in Resource-Limited Settings
MarkTechPost@AI 2024-09-11T10:20:32.000000Z