HuggingFace 每日AI论文速递

2025.07.24 | MLLMs视觉感知仍不足;Yume模型可生成交互虚拟世界。


Listen Later

本期的 9 篇论文如下:

[00:23] 👁 Pixels, Patterns, but No Poetry: To See The World like Humans(像素、模式,却无诗意:像人类一样感知世界)

[00:56] 🌌 Yume: An Interactive World Generation Model(Yume:交互式世界生成模型)

[01:29] ✨ DesignLab: Designing Slides Through Iterative Detection and Correction(DesignLab:通过迭代检测与修正进行幻灯片设计)

[02:14] 🧠 Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning(一个领域能否助益其他领域?一项以数据为中心的多领域强化学习推理研究)

[02:59] ✅ Re:Form -- Reducing Human Priors in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny(Re:Form:在LLM中利用强化学习减少可扩展形式化软件验证中的人类先验——基于Dafny的初步研究)

[03:35] 🔍 RAVine: Reality-Aligned Evaluation for Agentic Search(RAVine:面向代理式搜索的现实对齐评估)

[04:13] ⚡ Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention(Ultra3D:采用部分注意力的高效高保真3D生成)

[04:59] ✨ Elevating 3D Models: High-Quality Texture and Geometry Refinement from a Low-Quality Model(提升3D模型:从低质量模型实现高质量纹理与几何精修)

[05:31] 🔍 Finding Dori: Memorization in Text-to-Image Diffusion Models Is Less Local Than Assumed(寻找多莉:文本到图像扩散模型中的记忆化比假设的局部性更低)

【关注我们】

您还可以在以下平台找到我们,获得播客内容以外更多信息

小红书: AI速递

...more
View all episodesView all episodes
Download on the App Store

HuggingFace 每日AI论文速递By duan

  • 5
  • 5
  • 5
  • 5
  • 5

5

2 ratings


More shows like HuggingFace 每日AI论文速递

View all
硅谷101|中国版 by 泓君Jane

硅谷101|中国版

56 Listeners

商业就是这样 by 商业就是这样

商业就是这样

292 Listeners

声动早咖啡 by 声动活泼

声动早咖啡

293 Listeners

思文,败类 by 思文败类

思文,败类

156 Listeners

不开玩笑 Jokes Aside by 不开玩笑JokesAside

不开玩笑 Jokes Aside

136 Listeners

人民公园说AI by JustSayAI

人民公园说AI

7 Listeners

數創實驗室 - AI時代的學習指南 by Vincent在數創

數創實驗室 - AI時代的學習指南

1 Listeners

AI可可AI生活 by fly51fly

AI可可AI生活

0 Listeners