Hosted on MSN

Who needs Proxmox templates? I built my own base image instead

This year has been somewhat of a revelation for my home lab, as I finally moved my mess of containers and virtual machines from my Windows desktop and NAS to a dedicated mini PC with Proxmox as the ...
The New York Times

The New York Times Magazine

He is ranked No. 33 in the world. Can he rise to the top by using lessons from his father’s time on Wall Street? By Hugo Lindgren Forty-five current and former employees on the changes they say are ...
IEEE

TCTL-Net: Template-Free Color Transfer Learning for Self-Attention Driven Underwater Image Enhancement

Abstract: Vision is an important source of information for underwater observations, but underwater images commonly suffer severe visual degradation due to the complexity of the underwater imaging ...
IEEE

Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Bag-Level Classifier is a Good Instance-Level Teacher

Abstract: Multiple Instance Learning (MIL) has demonstrated promise in Whole Slide Image (WSI) classification. However, a major challenge persists due to the high computational cost associated with ...
GitHub

sdbds/sliders-for-windows

Official code implementation of "Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models", European Conference on Computer Vision (ECCV 2024). You can train sliders for FLUX-1 models.
GitHub

2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification

Adding training/testing instructions. Fix bugs in draw_heatmap.py. Upload model weights. Pack CUDA kernel into a python package. $ conda create --name 2dmamba python=3.10 $ conda activate 2dmamba $ ...