Machine Learning Research
A Transformer Alternative Emerges: Mamba, a new approach that may outperform transformers
An architectural innovation improves upon transformers — up to 2 billion parameters, at least...
Princeton University
Tech & Society
Language Models’ Impact on Jobs: The occupations likely to be most affected by language models
Telemarketers and college professors are most likely to find their jobs changing due to advances in language modeling, according to a new study. Researchers projected the jobs and industries in the U.S. likely to be most affected by language models.
Machine Learning Research
A Privacy Threat Revealed: How researchers cracked InstaHide for computer vision.
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.
Machine Learning Research
Making GANs More Inclusive: A technique to help GANs represent their datasets fairly
A typical GAN’s output doesn’t necessarily reflect the data distribution of its training set. Instead, GANs are prone to modeling the majority of the training distribution, sometimes ignoring rare attributes — say, faces that represent minority populations.
Machine Learning Research
Periscope Vision: Researchers used deep learning to see around corners.
Wouldn’t it be great to see around corners? Deep learning researchers are working on it. Researchers developed deep-inverse correlography, a technique that interprets reflected light to reveal objects outside the line of sight.
Tech & Society
ImageNet Gets a Makeover: The effort to remove bias from ImageNet
Computer scientists are struggling to purge bias from one of AI’s most important datasets. ImageNet’s 14 million photos are a go-to collection for training computer-vision systems, yet their descriptive labels have been rife with derogatory and stereotyped attitudes toward race, gender, and sex.