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