Researchers from the University of Austin and Carnegie Mellon have proposed a new way to run computationally expensive machine learning models on mobile devices such as...
A new study from South Korea has proposed a method to determine whether image synthesis systems are producing genuinely novel images, or ‘minor’ variants on the...
New research developed at Adobe is offering the first viable and effective deepfakes method based on Neural Radiance Fields (NeRF) – perhaps the first real innovation...
In light of growing concern about the energy requirements of large machine learning models, a recent study from MIT Lincoln Laboratory and Northeastern University has investigated...
New research from the US indicates that pretrained language models (PLMs) such as GPT-3 can be successfully queried for real-world email addresses that were included in...
New research from the US finds that one of the popular computer vision models behind the much feted DALL-E series, as well as many other image...
A new research collaboration between China and the US offers a way of detecting malicious ecommerce reviews designed to undermine competitors or to facilitate blackmail, by...
New research from China reports state-of-the-art results – as well as an impressive improvement in efficiency – for a new video inpainting system that can adroitly...
New research from Canada offers a possible method by which attackers could steal the fruits of expensive machine learning frameworks, even when the only access to...
Earlier this year NVIDIA advanced Neural Radiance Fields (NeRF) research notably with InstantNeRF, apparently capable of generating explorable neural scenes in mere seconds – from a...
A new study from Google Research and UC Berkeley adds to longstanding criticism regarding the computer vision (CV) research sector’s reliance on the venerable ImageNet dataset,...
A research collaboration between China and the UK has devised a new method to reshape faces in video. The technique allows for convincing broadening and narrowing...
New research from UC Berkeley and Adobe offers a way to directly edit the hyperreal content that can be created by a Generative Adversarial Network (GAN),...
Researchers from France have devised a method for identifying newly-registered domains that are likely to be used in a ‘hit and run’ fashion by high-volume email...
A joint research collaboration between US universities and IBM has formulated a proof-of-concept adversarial attack that’s theoretically capable of causing stock market losses, simply by changing...
