HuggingFace 每日AI论文速递

2025.07.30 | 混元世界从文字像素生成沉浸3D世界;X-Omni用强化学习提升图像生成质量。


Listen Later

本期的 8 篇论文如下:

[00:23] 🌍 HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels(混元世界 1.0:从文字或像素生成沉浸式、可探索、可交互的3D世界)

[00:56] ✨ X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again(X-Omni:强化学习让离散自回归图像生成模型再展辉煌)

[01:59] 🚀 CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning(CUDA-L1:通过对比强化学习改进CUDA优化)

[02:43] ✨ MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge(MaPPO:结合先验知识的最大后验偏好优化)

[03:32] 🐾 AnimalClue: Recognizing Animals by their Traces(AnimalClue:通过痕迹识别动物)

[04:04] 🏃 MOVE: Motion-Guided Few-Shot Video Object Segmentation(MOVE:运动引导的少样本视频目标分割)

[04:31] 🤥 MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual Questions(MoHoBench:通过无法回答的视觉问题评估多模态大语言模型的诚实性)

[04:59] 🐘 Evaluating Deep Learning Models for African Wildlife Image Classification: From DenseNet to Vision Transformers(评估用于非洲野生动物图像分类的深度学习模型:从DenseNet到视觉Transformer)

【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