Tagged: deep-learning

21 articles

Latest

Hugging Face's Accelerate cuts distributed training to five lines of code

Perceiver IO breaks the Transformer's quadratic bottleneck for images

fastai Models Now Hit Hugging Face Hub With One Line of Python

Hugging Face shows how to build a probabilistic Transformer for time series

How transfer learning taught AI to read proteins like English

Graph neural networks: Why your data isn't a sequence or a grid

Virgin Atlantic's AI pricing brain weighs hundreds of variables per flight

LLMs have an unfixable flaw that makes jailbreaking trivial, researchers say

With $1B Pledge, OpenAI Bets Non-Profit Structure Is AI's Safest Path

OpenAI Reveals the Messy Infrastructure Behind Deep Learning Wins

Deep inverse models close the sim-to-real gap for robots

Google's PATE approach trains AI without exposing private data

PixelCNN++ ditches softmax for logistics, speeds up training

Deep linear networks are secretly nonlinear, and now we can train them

Synthetic nonsense objects yield 80% real-world grasp rate

OpenAI puts $7.5k/month behind diversity in deep learning

OpenAI opens $22.5K scholar applications to diversify AI

Sparse Transformers crack sequences 30x longer than before

Why training AI against one attack can leave it exposed to another

OpenAI opens $34K stipend program to diversify AI

Hugging Face's Accelerate hits 1.0 after 3.5 years, baking in FP8 and bigger model support