Graph with difference in test error in keeping hard versus easy examples
Machine Learning Research

Unsupervised Data Pruning: New method removes useless machine learning data.

Large datasets often contain overly similar examples that consume training cycles without contributing to learning. A new paper identifies similar training examples, even if they’re not labeled.
MuLan text tokens computed from text prompt as conditioning signal
Machine Learning Research

He Who Types the Prompt Calls the Tune: Google introduces an AI that generates music from text.

As AI-generated text and images capture the world’s attention, music is catching up. Andrea Agostinelli, Timo I. Denk, and colleagues at Google and Sorbonne Université introduced MusicLM, a system that generates music from text descriptions.
Dataset FOLIO example based on the Wild Turkey Wikipedia page
Machine Learning Research

Language Models Defy Logic: Large NLP models struggle with logical reasoning.

Who would disagree that, if all people are mortal and Socrates is a person, Socrates must be mortal? GPT-3, for one. Recent work shows that bigger language models are not necessarily better when it comes to logical reasoning.
Screen captures of the Sparrow Chatbot
Machine Learning Research

Google’s Rule-Respecting Chatbot: Research helps AI chatbots be more truthful and less hateful.

Amid speculation about the threat posed by OpenAI’s ChatGPT chatbot to Google’s search business, a paper shows how the search giant might address the tendency of such models to produce offensive, incoherent, or untruthful dialog.
High-level overview of the STEGO architecture at train and prediction steps
Machine Learning Research

Segmented Images, No Labeled Data: Improved unsupervised learning for semantic segmentation

Training a model to separate the objects in a picture typically requires labeled images for best results. Recent work upped the ante for training without labels.
Outline of the text-embedding and inversion process.
Machine Learning Research

Precision-Guided Image Generation: Better text-to-image results with latent diffusion

Typical text-to-image generators can generate pictures of a cat, but not your cat. That’s because it’s hard to describe in a text prompt precisely all the things that distinguish your pet from other members of the same species.
Diagram explaining Atlas, a retrieval-augmented language model that exhibits strong few-shot performance on knowledge tasks
Machine Learning Research

Memorize Less; Retrieve More: How small language models can perform specialized tasks.

Large language models are trained only to predict the next word based on previous ones. Yet, given a modest fine-tuning set, they acquire enough information to learn how to perform tasks such as answering questions.
Ground truth video of a road on the left and predicted video with MaskViT on the right
Machine Learning Research

Seeing What Comes Next: Transformers predict future video frames.

If a robot can predict what it’s likely to see next, it may have a better basis for choosing an appropriate action — but it has to predict quickly. Transformers, for all their utility in computer vision, aren’t well suited to this because of their steep computational and memory requirements...
Illustration of the multiresolution hash encoding in 2D
Machine Learning Research

Novel Views of 3D Scenes — Pronto: Using NeRF Algorithms to Quickly Generate New 3D Views

Given a number of images of the same scene, a neural network can synthesize images from novel vantage points, but it can take hours to train. A new approach cuts training time to a few minutes.
Charts showing benchmark on medium-sized datasets
Machine Learning Research

When Trees Outdo Neural Networks: Decision Trees Perform Best on Most Tabular Data

While neural networks perform well on image, text, and audio datasets, they fall behind decision trees and their variations for tabular datasets. New research looked into why.
Network architecture of Reasoner
Machine Learning Research

What the Missing Frames Showed: Machine Learning Describes Masked Video Events

Neural networks can describe in words what’s happening in pictures and videos — but can they make sensible guesses about things that happened before or will happen afterward? Researchers probed this ability.
Dependency between compute budget and number of parameters
Machine Learning Research

Right-Sizing Models for the Dataset: Finding the Best Data-To-Parameter Ratio for NLP Models

The route to improving transformer-based language models like GPT-3 and Gopher, which are trained on immense quantities of text scraped from the web, has been to increase their size. But research shows that, given a processing budget, bigger doesn’t necessarily mean better.
Plot demonstrating the relative sizes of parallel and monolingual examples
Machine Learning Research

Massively Multilingual Translation: Machine Learning Model Trained to Translate 1,000 Languages

Recent work showed that models for multilingual machine translation can increase the number of languages they translate by scraping the web for pairs of equivalent sentences in different languages. A new study radically expanded the language repertoire through training on untranslated web text.
Technical components of No Language Left Behind and how they fit together
Machine Learning Research

The Net Speaks in Many Tongues: NLP Model Translates 200 Different Languages

Sentence pairs that have equivalent meanings in different languages — typically used to train machine translation systems — have been available in sufficient quantities for only around 100 languages. New work doubled that number and produced a more capable model.
Example of a video produced from a story-like description
Machine Learning Research

Long-Form Videos from Text Stories: Google's Phenaki Generates Long-Form Video from Text

Only a week ago, researchers unveiled a system that generates a few seconds of video based on a text prompt. New work enables a text-to-video system to produce an entire visual narrative from several sentences of text.

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox