Sublime

Point-Cloud Completion with Pretrained Text-to-image Diffusion Models paper page: https://t.co/AVwq8BQssZ Point-cloud data collected in real-world applications are often incomplete. Data is typically missing due to objects being observed from partial viewpoints, which only capture a specific... See more

1/6 New paper! “The Geometry of Concepts: Sparse Autoencoder Feature Structure.” We find that the concept universe of SAE features has interesting structure at three levels: 1) “atomic” small-scale, 2) “brain” intermediate-scale, and 3) “galaxy” large-scale! https://t.co/tvJ6Gspf1y

Do we fully leverage image encoders in vision language models? 👀 A new paper built a dense connector that does it better! Let's dig in (demo and more under this tweet!) 🧶 https://t.co/1P3oALX0FV

AdalFlow: 一个用于构建和自动优化 LLM 应用的开源库 # 一个用于构建和自动优化 LLM 应用的统一框架，它通过两个基础类（Component 和 DataClass）实现了最小抽象和最大定制性，让开发者能像塑造水一样自由地将 LLM 塑造成任何形态的应用 // 框架设计理念： - 以 PyTorch 为灵感来源，继承了其优秀的设计理念 - 强调"LLMs are like water"的理念 - LLM 像水一样，可以被塑造成任何形态 -... See more

Structured information extraction from PDFs https://t.co/HP5fHfO77Z

DiffusionDet: Diffusion Model for Object Detection abs: https://t.co/GBu4bZPwKp github: https://t.co/bWHxGxayjB https://t.co/7a8lfNaqp9