Excited to share with everyone an accessible, intuitive tutorial on diffusion models! If you're curious about the math behind diffusion models and how their different interpretations can be unified, please check it out! Stay tuned for a blog post soon! arxiv.org/abs/2208.11970

Finding truth lies in experimenting with unproductive paths, explore dead ends, make space for doubts and boredom, and allow little seeds of insight to slowly grow and blossom. #quote #quotes #21lessonsforthe21stcentury

men will literally try to build agi instead of going to therapy

Callistus Gero, PhD PhD Voice - Independently Run @PhDfriendSana PhD Chatter You can start writing your lit review or methods before completing your data collection and analysis. I wouldn't recommend waiting to complete it before beginning to write. I managed to finish my thesis in a year if you're interest in reading about it thephdplace.com/phd-spotlight/…

Secret Panel HERE 💭 tapas.io/episode/841867

Attention is one of the most important breakthroughs in AI - the foundation of Transformers This Distill is the best explanation of it I've seen. For #100DaysOfMLCode / #100DaysOfCode folks - try building an attention mechanism from scratch! distill.pub/2016/augmented…

Not every is a priority.

Matrix factorizations are the pinnacle results of linear algebra. From theory to applications, they are behind many theorems, algorithms, and methods. However, it is easy to get lost in the vast jungle of decompositions. This is how to make sense of them.

Gather round, Twitter folks, it's time for our beloved **Alice's adventures in a differentiable wonderland**, our magical tour of autodiff and backpropagation. 🔥 Slides below 1/n 👇

“Above all, do not lose your desire to walk: Every day I walk myself into a state of well-being and walk away from every illness; I have walked myself into my best thoughts, and I know of no thought so burdensome that one cannot walk away from it.” — Søren Kierkegaard

This is the most important plot of alignment lore: Whenever you optimize a proxy, you make progress on your true objective for a while. At some point you start overoptimizing and do worse on your true objective (hard to know when). This applies to all proxy measures ever.

Addiction is a progressive narrowing of the things that bring you pleasure. Happiness is a progressive expansion of the things that bring you pleasure. The former emerges passively. The latter takes work.

I'm so excited to share my PhD thesis publicly. It's 88 pages long, I wrote it from scratch, and I tried to create a useful document for anyone wanting to gain a rigorous but unfussy understanding of the mathematics of deep learning. It's here: arxiv.org/abs/2210.10101 (1/7)

“Caffeine equips us to cope with a world caffeine helped us create.” -Michael Pollan

"What Makes Convolutional Models Great on Long Sequence Modeling?" CNNs—not transformers—now dominate the hardest sequence modeling benchmark. Here's how this happened: [1/14]

How to get unstuck? "It doesn't work." 🤷‍♀️🤷‍♂️ In most research projects, ~99% of the time your experiments DO NOT work. What should we do to get ourselves unstuck? 🤔 Sharing some tips I found useful. 🧵

Insanely fast whisper now with Speaker Diarisation! 🔥 100% local and works on your Mac or on Nvidia GPUs. All thanks to Hervé "pyannote" Bredin's Pyannote library, you can now get blazingly fast transcriptions and speaker segmentations! ⚡️ Here's how you can use it too: pipx install

It gives us great pleasure to pre-announce the 8th CHiME Speech Separation and Recognition Challenge (CHiME-8) that will launch in February 2024. CHiME-8 TASKS includes: Task 1 - DASR Task 2 - NOTSOFAR-1 Task 3 - MMCSG Please check chimechallenge.org/#current