牛哥精选 · 所有

📋 全部 🤖 AI·大模型 ⚡ 效率工具 📝 深度技术 🚀 产品观察 💰 商业科技 🔓 开源项目 🎨 设计创意 📖 阅读推荐 🏷 资源合集 🌱 成长效率

🤖 AI·大模型 arXiv AI 2026-06-24

IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation

把隐式视觉思维链引入文生图，让模型按结构逻辑逐层生成，画面布局更稳更精确

arXiv:2606.24849v1 Announce Type: cross Abstract: Unified multi-modal large language models (MLLMs) have achieved strong text-to-image generation qual…

文本生成图像思维链结构感知视觉推理扩散模型

🤖 AI·大模型 arXiv 计算机视觉 2026-05-29

Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers

揭示多模态扩散Transformer中概念遗漏的根源，并提出基于线性探测的诊断与纠正方法。

arXiv:2605.14270v2 Announce Type: replace Abstract: Multimodal Diffusion Transformers (MM-DiTs) have achieved remarkable progress in text-to-image gen…

概念遗漏多模态扩散trans 文本生成图像线性探测模型诊断

🚀 产品观察 TechCrunch 2026-05-20

Google just declared itself a contender in AI design

谷歌在I/O大会上发布AI设计工具Pics，直接挑战Canva和Claude Design，零门槛生成社交图像和营销素材。

The tech giant says it's designed the app to be accessible to everyone, from teachers to small business owners.

google ai设计 pics canva claude des

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation

Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers

Google just declared itself a contender in AI design

📅 日期