Ten years of neuroscience at Google yields maps of human brain

VideoPrism: A foundational visual encoder for video understanding

English learners can now practice speaking on Google Search

Finetune Llama-3 2x faster in a Colab notebook

Solving the minimum cut problem for undirected graphs

ScreenAI: A visual LLM for UI and visually-situated language understanding

Patchscopes: A framework for viewing hidden representations of language models

Colab notebook to create Magic cards from image with Claude

MANATEE(lm): Market Analysis based on language model architectures

Croissant: A metadata format for ML-ready datasets

Social learning: Collaborative learning with large language models

A decoder-only foundation model for time-series forecasting

Large sequence models for software development activities

I made this charts of programming languages characteristics, do you agree?

A confusing probability question: Red and green balls in an urn

MobileDiffusion: Rapid text-to-image generation on-device

Advancements in machine learning for machine learning

2023: A year of groundbreaking advances in AI and computing

VideoPoet A large language model for zero-shot video generation

Unsupervised speech-to-speech translation from monolingual data

A new quantum algorithm for classical mechanics with an exponential speedup

MetNet-3: A state-of-the-art neural weather model

Google AI: "Introducing AltUp, a method that takes advantage of increasing scale in Transformer networks w/out increasing the computation cost — it’s easy to implement…

Show HN: Dlt – Python library to automate the creation of datasets

Outperforming larger language models with less training data and smaller models

Hand encode transformer weights to do long form addition

Show HN: ReliableGPT run 200 GPT-4 requests in parallel

CoLab Notebook for Reverse Image Search

The unreasonable effectiveness of character-level language models (2015)

Universal Speech Model

More →