#other
Here’s a simple summary of the most important information and its benefit to you get enough good sleep, avoid smoking, move your body every day, and eat less sugar—doing just these four can make a big difference. The text also shares tips from neuroscience, like getting sunlight in the morning to help wake up and feel better, and avoiding bright lights at night to sleep well. Eating mostly plants and fermented foods helps your gut and immune system, while timing your meals (like eating in an 8-hour window) can boost your health and even help you live longer. The text also explains how your brain’s chemicals, like dopamine, affect your mood and motivation, and how you can use simple tricks—like taking breaks, trying new things, or doing light exercise—to stay focused and happy. The benefit is that you can feel better, think clearer, and stay healthier by making small, smart changes to your daily routine.
https://github.com/zijie0/HumanSystemOptimization
#DL
📱
Zeus New Pytorch Ecosystem Tool
Zeus is an open source toolkit for measuring and optimizing power consumption of deep learning workloads.
🖥Github
-----
Main channel: @repo_science
Coupons: @freecoupons_reposcience
-----
#dl
Park, Chanwook, Sourav Saha, Jiachen Guo, Hantao Zhang, Xiaoyu Xie, Miguel A. Bessa, Dong Qian, et al. 2025. “Unifying Machine Learning and Interpolation Theory via Interpolating Neural Networks.” Nature Communications 16 (1): 1–12.
https://www.nature.com/articles/s41467-025-63790-8
#dl
A few cool ideas in this model.
Introducing Gemma 3n: The developer guide - Google Developers Blog
https://developers.googleblog.com/en/introducing-gemma-3n-developer-guide/
#dl
There is this new lib called scale. One could compile CUDA code to use it on AMD GPU.
https://docs.scale-lang.com/manual/how-to-use/
I don't know who is more pissed off, NVidia or AMD.
#dl
This repo is really nice.
yuanchenyang/smalldiffusion: Simple and readable code for training and sampling from diffusion models
https://github.com/yuanchenyang/smalldiffusion
#dl
Google & USC benchmarked a prompt based forecasting method, and the results are amazing.
Cao D, Jia F, Arik SO, Pfister T, Zheng Y, Ye W, et al. TEMPO: Prompt-based Generative Pre-trained Transformer for time series forecasting. arXiv [cs.LG]. 2023. Available: http://arxiv.org/abs/2310.04948