Graphs and data related to ImageNet performance
Machine Learning Research

ImageNet Performance: No Panacea

It’s commonly assumed that models pretrained to achieve high performance on ImageNet will perform better on other visual tasks after fine-tuning. But is it always true? A new study reached surprising conclusions.
2 min read
Neural Body, a procedure that generates novel views of a single human character, working
Machine Learning Research

Seeing People From a New Angle

The University of Hong Kong, and Cornell University to create Neural Body, a procedure that generates novel views of a single human character based on shots from only a few angles.
2 min read
Graph showing system that examines X-ray images to predict which Covid-19 patients are at greatest risk of decline
Machine Learning Research

Covid-19 Triage

The pandemic has pushed hospitals to their limits. A new machine learning system could help doctors make sure the most severe cases get timely, appropriate care.
2 min read
Graph showing information about different transformer models
Machine Learning Research

Transformer Variants Head to Head

The transformer architecture has inspired a plethora of variations. Yet researchers have used a patchwork of metrics to evaluate their performance, making them hard to compare. New work aims to level the playing field.
2 min read
System Oscar+ working
Machine Learning Research

Sharper Eyes For Vision+Language

Models that interpret the interplay of words and images tend to be trained on richer bodies of text than images. Recent research worked toward giving such models a more balanced knowledge of the two domains.
2 min read
Different graphs showing switch transformer data
Machine Learning Research

Bigger, Faster Transformers

Performance in language tasks rises with the size of the model — yet, as a model’s parameter count rises, so does the time it takes to render output. New work pumps up the number of parameters without slowing down the network.
2 min read
Different data related to the phenomenon called underspecification
Machine Learning Research

Facing Failure to Generalize

The same models trained on the same data may show the same performance in the lab, and yet respond very differently to data they haven’t seen before. New work finds this inconsistency to be pervasive.
2 min read
Series of images showing improvements in a multilingual language translator
Machine Learning Research

Better Zero-Shot Translations

Train a multilingual language translator to translate between Spanish and English and between English and German, and it may be able to translate directly between Spanish and German as well. New work proposes a simple path to better machine translation between languages.
2 min read
Series of images and graphs related to cancer detection
Machine Learning Research

Shortcut to Cancer Treatment

Doctors who treat breast cancer typically use a quick, inexpensive tumor-tissue stain test to diagnose the illness and a slower, more costly one to determine treatment. A new neural network could help doctors to go straight from diagnosis to treatment.
2 min read
Graphs and data related to visualized tokens (or vokens)
Machine Learning Research

Better Language Through Vision

For children, associating a word with a picture that illustrates it helps them learn the word’s meaning. Research aims to do something similar for machine learning models. Researchers improved a BERT model’s performance on some language tasks by training it on a large dataset of image-word pairs.
2 min read
Graphs and data related to recurrent neural nets (RNNs)
Machine Learning Research

Performance Guaranteed

Bayes-optimal algorithms always make the best decisions given their training and input, if certain assumptions hold true. New work shows that some neural networks can approach this kind of performance.
2 min read
Examples of InstaHide scrambling images
Machine Learning Research

A Privacy Threat Revealed

With access to a trained model, an attacker can use a reconstruction attack to approximate its training data. A method called InstaHide recently won acclaim for promising to make such examples unrecognizable to human eyes while retaining their utility for training.
2 min read
Data related to a language model that predicts mutations that would enable infectious viruses
Machine Learning Research

The Language of Viruses

A neural network learned to read the genes of viruses as though they were text. That could enable researchers to page ahead for potentially dangerous mutations. Researchers at MIT trained a language model to predict mutations that would enable infectious viruses to become even more virulent.
2 min read
Data and graphs related to a new model capable of detecting tremors
Machine Learning Research

Quake Watch

Detecting earthquakes is an important step toward warning surrounding communities that damaging seismic waves may be headed their way. A new model detects tremors and provides clues to their epicenter.
2 min read
Examples of images being produced from noise
Machine Learning Research

Images From Noise

Generative adversarial networks and souped-up language models aren’t the only image generators around. Researchers recently upgraded an alternative known as score-based generative models.
3 min read

Subscribe to The Batch

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