Within the study of machine learning, you'll often hear that the objective is to find the solution that maximizes likelihood . We have a...

Calibrated Attention Calibrated Attention NanoGPT Attention is the magic ingredient of modern neural networks. It is the core of what has...

A short attempt at a small portion of the diffusion Family Tree https://www.canva.com/design/DAGgnVB3x2s/b52Y3Kg-frWdRlPzI3_5pA/edit?utm_...

Mandelbrot function: Zn+1 = (Zn)^2 + C | Location: -1.4732524061369524549 + -0.0058138265122775765014 i , Radius:...

One of the most interesting things about the development of AI was the order of achieved milestones. Relatively small models can create convincingly masterful lifelike art while a much larger language model may fail common sense problems that your average 10 year old may have no problem with . But then at the same time, they are incredibly capable. The same language models failing at some trivial tasks may also explain difficult math concepts in a very intuitive manner and

It's a bit hard to see in the diagram but in addition to being convolved with a gaussian, these points are also drifting towards zero....

https://sweet-hall-e72.notion.site/Classifier-Free-Guidance-to-Approximate-RL-9f78c02801c6434da61f37c8d843c5bf

"Would someone without free will do this?" is one of the most common responses I've heard to the proposition that free will might not...

Art from "In the Aeroplane over the Sea" by Neutral Milk Hotel There are several dimensions by which we may feel small. You may feel...

Empathy through technology

https://sweet-hall-e72.notion.site/Why-are-Modern-Neural-Nets-the-way-they-are-And-Hidden-Hypernetworks-6c7195709e7b4abbada921875a951c54

https://sweet-hall-e72.notion.site/Do-Diffusion-Transformers-Deserve-The-Hype-9b9ca7bead374b47aac96558714c203b

https://sweet-hall-e72.notion.site/Automated-LoRA-Discovery-and-Teaching-Neural-Networks-to-make-Neural-Networks-22aa3b5ad66e4bc985ff2c93...

https://sweet-hall-e72.notion.site/Diffusion-and-Autoregressive-Models-for-Learning-to-Solve-Mazes-c3bc4bcdfa304ecd9531ee5445a4da66

https://arxiv.org/pdf/2208.03998

https://sweet-hall-e72.notion.site/Traversing-through-CLIP-Space-PCA-and-Latent-Directions-b898932e13684d58957405b4a2747a79

https://sweet-hall-e72.notion.site/LoraNorm-91f5927c7c3a48f9beeec7c2910c82ad?pvs=4

https://sweet-hall-e72.notion.site/2-UNet-Classifier-Free-Guidance-e2eb8833d01e4e77869a2eff4631ebbc?pvs=4

https://sweet-hall-e72.notion.site/SGDImagePrompt-and-QuickEmbedding-502cf95e48ff4a4db44823e117b7f779?pvs=4

https://sweet-hall-e72.notion.site/Learning-Space-Filling-Curves-with-Autoencoders-e39e41ce75894c3a8fecfee0f3bbfb23?pvs=4