Applying massive language models in the real world with Cohere
A little less than a year ago, I joined the awesome Cohere team. The company trains massive language models (both GPT-like and BERT-like) and offers them…
Full feed
Feed 5,539 posts
Every story across every category, newest first. Each card links to the original publisher; daily-brief posts open as editorial pages.
Learning with not Enough Data Part 2: Active Learning
This is part 2 of what to do when facing a limited amount of labeled data for supervised learning tasks. This time we will get some…
The Illustrated Retrieval Transformer
Discussion: Discussion Thread for comments, corrections, or any feedback. Translations: Korean, Russian Summary: The latest batch of language models can be much smaller yet achieve GPT-3…
Learning with not Enough Data Part 1: Semi-Supervised Learning
When facing a limited amount of labeled data for supervised learning tasks, four approaches are commonly discussed.
How to Train Really Large Models on Many GPUs?
[Updated on 2022-03-13: add expert choice routing.] [Updated on 2022-06-10]: Greg and I wrote a shorted and upgraded version of this post, published on OpenAI Blog:…
Understanding Convolutions on Graphs
Understanding the building blocks and design choices of graph neural networks.
A Gentle Introduction to Graph Neural Networks
What components are needed for building learning algorithms that leverage the structure and properties of graphs?
What are Diffusion Models?
[Updated on 2021-09-19: Highly recommend this blog post on score-based generative modeling by Yang Song (author of several key papers in the references)]. [Updated on 2022-08-27:…
Distill Hiatus
After five years, Distill will be taking a break.
Contrastive Representation Learning
The goal of contrastive representation learning is to learn such an embedding space in which similar sample pairs stay close to each other while dissimilar ones…
Adversarial Reprogramming of Neural Cellular Automata
Reprogramming Neural CA to exhibit novel behaviour, using adversarial attacks.
Explainable AI Cheat Sheet
Introducing the Explainable AI Cheat Sheet, your high-level guide to the set of tools and methods that helps humans understand AI/ML models and their predictions. I…
Weight Banding
Weights in the final layer of common visual models appear as horizontal bands. We investigate how and why.
Branch Specialization
When a neural network layer is divided into multiple branches, neurons self-organize into coherent groupings.
Reducing Toxicity in Language Models
Large pretrained language models are trained over a sizable collection of online data. They unavoidably acquire certain toxic behavior and biases from the Internet. Pretrained language…
Multimodal Neurons in Artificial Neural Networks
We report the existence of multimodal neurons in artificial neural networks, similar to those found in the human brain.
Self-Organising Textures
Neural Cellular Automata learn to generate textures, exhibiting surprising properties.
Visualizing Weights
We present techniques for visualizing, contextualizing, and understanding neural network weights.
Curve Circuits
Reverse engineering the curve detection algorithm from InceptionV1 and reimplementing it from scratch.
High-Low Frequency Detectors
A family of early-vision neurons reacting to directional transitions from high to low spatial frequency.
Finding the Words to Say: Hidden State Visualizations for Language Models
By visualizing the hidden state between a model's layers, we can get some clues as to the model's "thought process". Figure: Finding the words to say…
Controllable Neural Text Generation
[Updated on 2021-02-01: Updated to version 2.0 with several work added and many typos fixed.] [Updated on 2021-05-26: Add P-tuning and Prompt Tuning in the “prompt…
Interfaces for Explaining Transformer Language Models
Interfaces for exploring transformer language models by looking at input saliency and neuron activation. Explorable #1: Input saliency of a list of countries generated by a…
Naturally Occurring Equivariance in Neural Networks
Neural networks naturally learn many transformed copies of the same feature, connected by symmetric weights.