My headphones just got way better with iOS 17 so something is up.
AI
-
Curating Interesting and Useful AI Research Papers Monthly
By
–
yeah, that sounds about right. I spend a lot of time each month combing through papers that are interesting but also useful and probably worthwhile E.g., "AI Research Highlights In 3 Sentences Or Less (May-June 2023)" https://
magazine.sebastianraschka.com/p/ai-research-
highlights-in-3-sentences-2a1
… -
Interesting analysis of EU AI Act
By
–
Interesting analysis. https://
crfm.stanford.edu/2023/06/15/eu-
ai-act.html
… -
ML Debugging: Prioritize Reproducer Speed Over Bug Fixes
By
–
Bugs in ML code, no matter how surprising, are almost always fixable once you create a reproducer than runs in 5 minutes or less. If your reproducer takes an hour or longer, for a confusing bug often better to work on golfing down its runtime rather than trying to fix the bug.
-
UK Tech Policy Funding Gap Blame Culture Critique
By
–
Moral of the story in the UK tech policy world (and perhaps beyond too) is that if you’ve got a problem, no matter what it is, blame it on a “funding gap”.
-
Diffusion Models Training 70% Faster with Competitive Performance
By
–
In fig, comparison with diffusion models on ImageNet-256×256 with and without guidance. The area of each bubble indicates the FLOPs for a single forward pass during training. Our method is more compute-efficient with competitive performance: reduces training time by ~70%
-
Asymmetric Transformer Architecture with Masked Patch Reconstruction
By
–
Ours is an asymmetric transformer encoder-decoder architecture: encoder on unmasked patches + decoder on full patches. To promote learning, we add an auxiliary task of reconstructing masked patches to denoising score-matching objective that learns the score of unmasked patches.
-
AI’s Potential to Enhance Human Creativity and Humility
By
–
TY Arianna! Glad we both see potential for AI to enhance human creativity and humility. Here’s the op-ed w/out paywall: Let's Give AI a Chance https://
bit.ly/Boston-Globe-O
p-Ed-on-AI-May-2023
… -
Masked Training Reduces Diffusion Model Training Costs by 70%
By
–
Reduce training cost of diffusion models by ~70% through masked training of transformer backbones. Masked training is popular for self-supervised representation learning, but we are first to show for #GenerativeAI https://
github.com/Anima-Lab/Mask
DiT
… @wn8_nie @Kay12400259 @ArashVahdat -
Money is All You Need
By
–
$$ is all you need https://
x.com/ruima/status/1
/ruima/status/1670453343913746432
…