AIGC周刊 | 第26期

时间: 2023.5.2-2023.5.8

本周大事记

1. OpenAI 发布最新3D生成模型论文,代码已开源

论文: arxiv.org

代码: github.com

2. Perfusion: 英伟达最新个性化文生图模型

Key-Locked Rank One Editing for Text-to-Image Personalization

论文:arxiv.org

主页:research.nvidia.com

3. 视觉读心术:将脑信号转换成视频

论文:Learnable latent embeddings for joint behavioural and neural analysis

官网:cebra.ai

论文提出一种名为CEBRA的新编码方法,可以在联合使用行为数据和神经数据的情况下,以监督假设或自监督发现驱动方式,生成一致和高性能的潜空间,以揭示神经动态。

最新技术:

  1. Composite Motion Learning with Task Control

    论文: arxiv.org

    代码: github.com

  2. Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusion

    论文: arxiv.org

    官网:poloclub.github.io

  3. Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs

    论文: arxiv.org

  4. Otter: A Multi-Modal Model with In-Context Instruction Tuning

    论文: arxiv.org

    代码: github.com

  5. NeuralEditor: Editing Neural Radiance Fields via Manipulating Point Clouds

    论文: arxiv.org

  6. Personalize Segment Anything Model with One Shot

    论文:arxiv.org

    代码:github.com

  7. Real-Time Neural Appearance Models

    官网:research.nvidia.com

  8. AG3D: Learning to Generate 3D Avatars from 2D Image Collections

    论文: arxiv.org

    主页: zj-dong.github.io

  9. Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings

    论文: arxiv.org

  10. Making the Most of What You Have: Adapting Pre-trained Visual Language Models in the Low-data Regime

    论文: arxiv.org

  11. Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes

    论文: arxiv.org

  12. DreamPaint: Few-Shot Inpainting of E-Commerce Items for Virtual Try-On without 3D Modeling

    论文: arxiv.org

  13. In-Context Learning Unlocked for Diffusion Models

    主页: zhendong-wang.github.io

  14. GeneFace++: Generalized and Stable Real-Time Audio-Driven 3D Talking Face Generation

    论文: arxiv.org

    主页: genefaceplusplus.github.io

  15. Chatbot Arena: Benchmarking LLMs in the Wild with Elo Ratings

    lmsys.org

  16. AI通灵!类ChatGPT模型解码大脑信息,准确率高达82%

    mp.weixin.qq.com

  17. 大语言模型(LLM)分布式训练框架总结

    mp.weixin.qq.com

  18. 大模型物种进化图转疯了:8位华人打造,一眼看懂“界门纲目”,原来BERT后代已绝种

    mp.weixin.qq.com

  19. NVIDIA 最新图形学研究成果推动生成式 AI 前沿领域的进一步发展

    mp.weixin.qq.com

  20. 复杂推理:大语言模型的北极星能力

    mp.weixin.qq.com

课程:

  1. 哈佛大学CS50课程:使用GPT4打造智能程序

    www.bilibili.com

商业:

  1. Character.AI:AI Agents 平台下的大模型“民主化”梦想

    mp.weixin.qq.com

  2. 科大讯飞发布星火大模型

    mp.weixin.qq.com

  3. 后GPT时代,多模态是最大的机会

    mp.weixin.qq.com

  4. John Schulman:强化学习与真实性,通往TruthGPT之路

    mp.weixin.qq.com

  5. 谷歌内部文件泄漏:谷歌、OpenAI都没有护城河,大模型门槛正被开源踏破

    mp.weixin.qq.com

  6. Microsoft doubles down on AI with new Bing features

    techcrunch.com

  7. 谷歌突失Hinton!深度学习之父警告AI风险,对毕生工作表示遗憾

    mp.weixin.qq.com

案例:

  1. 以5万美元成本训练 stable diffusion模型

    www.mosaicml.com

  2. 「AI孙燕姿」全网沸腾!AI翻唱大爆发,整个华语乐坛都「复兴」了

    mp.weixin.qq.com

  3. 开源的短视频生成和编辑工具

    github.com

  4. Raycast AI Beta版发布

    raycastapp.notion.site

  5. AIGC教程:如何用Stable Diffusion生成完美的像素美术?

    mp.weixin.qq.com

source
The article is sourced from the internet. Click the “Source” button to view the original content. If there is any copyright infringement, please contact our team for removal.

Share this article
Shareable URL
Prev Post

Twelve Labs is building models that can understand videos at a deep level

Next Post

Data providers on the Google October 2023 core and spam update

Read next
Subscribe to our newsletter
Get notified of the best deals on our WordPress themes.