Sublime

An inspiration engine for ideas

AllPeopleCollectionsArticlesAudioBooksFilesHighlightsImagesLinksNotesTextTweetsVideosSocial

"new" SOTA object detector, and it's NOT YOLOv12 D-FINE is a model released 3 months ago under Apache-2.0 license; I have no idea how it flew under my radar @onuralpszr thanks for adding it to leaderboard leaderboard link:... See more

SkalskiP

x.com

Hash3D Training-free Acceleration for 3D Generation The evolution of 3D generative modeling has been notably propelled by the adoption of 2D diffusion models. Despite this progress, the cumbersome optimization process per se presents a critical hurdle to efficiency. In this... See more

x.com

转：关于 DeepSeek 的研究和思考 (Archerman Capital) 关于这几天很火的 DeepSeek, 我们 (Archerman Capital) 做了一些研究和思考, 和大家分享, enjoy! 灰色部分是技术细节, 不感兴趣的可略过。几个事实 1) DeepSeek 不是套壳不是蒸馏美国的大模型。虽然中国有些大模型是套壳和蒸馏的, 但 DeepSeek 不是。 2) 核心架构还是基于 Transformer, deepseek... See more

宝玉

x.com

A Chemical Progression

An exploration of the discovery and history of the atom, including the theories and experiments that led to its understanding in chemistry.

gregbrockman.com

3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features paper page: https://t.co/WmCgVMsQNF present 3DiffTection, a state-of-the-art method for 3D object detection from single images, leveraging features from a 3D-aware diffusion model. Annotating large-scale image data for... See more

x.com

RT-DETRv2 - object detection code on Huggingface: https://t.co/LzkvNr3RKB

el.cine x.com

Applied to YC with https://t.co/an3vYx4bMy Perplexity but for finding Professionals on the internet. https://t.co/CPtP1TTHiH

Dev Shah x.com

How to understand Github code repos with LLMs in 2 mins. Even after 10yrs of engineering, dissecting a large codebase is daunting. 1 Dump the code into one big file 2 Feed it to Gemini-1.5Pro (2M context) 3 Ask it anything. Here's, I dissect... See more

Deedy

x.com

Image as Set of Points abs: https://t.co/JZiivfycj6 github: https://t.co/taa5mQq8OJ https://t.co/zHFAowPtNL

x.com