Reposted by Dillon Cowerhardmaru @hardmaru.bsky.social · 20/02/2025Introducing The AI CUDA Engineer: An agentic AI system that automates the production of highly optimized CUDA kernels. sakana.ai/ai-cuda-engi... The AI CUDA Engineer can produce highly optimized CUDA kernels, reaching 10-100x speedup over common machine learning operations in PyTorch. Examples: 39017
Reposted by Dillon CowerBlake Richards @tyrellturing.bsky.social · 16/12/20241/ Okay, one thing that has been revealed to me from the replies to this is that many people don't know (or refuse to recognize) the following fact: The unts in ANN are actually not a terrible approximation of how real neurons work! A tiny 🧵. 🧠📈 #NeuroAI #MLSky 2115238
Reposted by Dillon CowerOmar @ocornut.bsky.social · 17/12/2024ImPlot3D: A 3D Plotting Library for Dear ImGui github.com/brenocq/impl... 614925
Reposted by Dillon CowerBart Wronski 🇺🇦🇵🇸 @bartwr.bsky.social · 11/12/2024Computer "Science" should look at real Science. :) Pre-registering any experiments/trials before research. (E.g., pre-register your prompts/examples!). Not showing a table with a PSNR of 36.142 but confidence intervals and a distribution of N training runs w different hyperparameters/seeds. 111
Reposted by Dillon CowerNenad Tomasev @nenadtomasev.bsky.social · 05/12/2024I'm excited to share a new paper: "Mastering Board Games by External and Internal Planning with Language Models" storage.googleapis.com/deepmind-med... (also soon to be up on Arxiv, once it's been processed there)storage.googleapis.com 47614
Reposted by Dillon Cowerruiqigao.bsky.social @ruiqigao.bsky.social · 02/12/2024A common question nowadays: Which is better, diffusion or flow matching? 🤔 Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably. 625459
Reposted by Dillon CowerQuanquan Gu @quanquangu.bsky.social · 22/11/2024In addition to the Deep Learning Theory starter pack, I've also put together a starter pack for Reinforcement Learning Theory. Let me know if you'd like to be included or suggest someone to add to the list! go.bsky.app/LWyGAAu 112910
