AIGC周刊 | 第24期

时间: 2023.4.17-2023.4.23

本周大事记

1. StableLM: Stability AI Language Models

StabilityAI开源了他们的大语言模型,目前3b和7b提供下载

readmore

2. 复旦大学开源大模型Moss

复旦 NLP 团队的 MOSS 大语言模型开源了,增加「搜索引擎、计算器、解方程、文生图」等插件功能,可以在线体验,支持本地部署

readmore

更多讨论:www.zhihu.com

最新技术:

  1. Ask-Anything, tool for chatting about video with chatGPT, miniGPT4 and StableLM

    github: github.com

  2. Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models

    论文:arxiv.org

    主页:research.nvidia.com

  3. Reference-based Image Composition with Sketch via Structure-aware Diffusion Model

    论文:arxiv.org

  4. Inpaint Anything: Segment Anything Meets Image Inpainting

    github: github.com

    demo: huggingface.co

  5. DINOv2: Learning Robust Visual Features without Supervision

    github: github.com

  6. Anything-3D, present a project combining Segment Anything with a series of 3D models

    github: github.com

  7. LLM as A Robotic Brain: Unifying Egocentric Memory and Control

    论文:arxiv.org

  8. whisper-jax

    github: github.com

  9. Theory on Adam Instability in Large-Scale Machine Learning

    论文: arxiv.org

  10. Generative Disco: Text-to-Video Generation for Music Visualization

    论文: arxiv.org

  11. NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers

    论文: arxiv.org

    主页: speechresearch.github.io

  12. SAM Fails to Segment Anything? — SAM-Adapter: Adapting SAM in Underperformed Scenes: Camouflage, Shadow, and More

    论文: arxiv.org

    主页: tianrun-chen.github.io

  13. Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model

    论文: arxiv.org

    主页: dulucas.github.io

  14. Low-code LLM: Visual Programming over LLMs

    论文: arxiv.org

  15. Tool Learning with Foundation Models

    论文: arxiv.org

    github: github.com

  16. Synthetic Data from Diffusion Models Improves ImageNet Classification

    论文: arxiv.org

  17. LongForm: Optimizing Instruction Tuning for Long Text Generation with Corpus Extraction

    论文: arxiv.org

  18. 梯度视角下的LoRA:简介、分析、猜测及推

    mp.weixin.qq.com

课程:

  1. “生成式大语言模型技术分享”系列直播

    mp.weixin.qq.com

  2. 如何生成文本: 通过 Transformers 用不同的解码方法生成文本

    mp.weixin.qq.com

商业:

  1. 陆奇最新演讲实录:我的大模型世界观

    mp.weixin.qq.com

  2. 王川: 从 chatGPT 看人工智能的投资机会和风险

    mp.weixin.qq.com

  3. 对话王慧文:AGI这么伟大的事情,谁做成了我都会鼓掌

    mp.weixin.qq.com

案例:

  1. Chinese-LangChain

    github.com

  2. 电商数字模特生成技术实践分享

    zhuanlan.zhihu.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

Diffusion models explained in 4-difficulty levels

Next Post

3 steps to mastering the right indicators for lasting SEO results

Read next

AIGC Weekly | #75

1.) MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention ( webpage |…
Subscribe to our newsletter
Get notified of the best deals on our WordPress themes.