Author: Martin Anderson

If 2022 marked the moment when generative AI’s disruptive potential first captured wide public attention, 2024 has been the year when questions about the legality of its underlying data have taken center stage for businesses eager to harness its power. The USA’s fair use doctrine, along with the implicit scholarly license that had long allowed

A recent study from the US has found that the real-world performance of popular Retrieval Augmented Generation (RAG) research systems such as Perplexity and Bing Copilot falls far short of both the marketing hype and popular adoption that has garnered headlines over the last 12 months. The project, which involved extensive survey participation featuring 21

Disney’s Research arm is offering a new method of compressing images, leveraging the open source Stable Diffusion V1.2 model to produce more realistic images at lower bitrates than competing methods. The Disney compression method compared to prior approaches. The authors claim improved recovery of detail, while offering a model that does not require hundreds of

Video frame interpolation (VFI) is an open problem in generative video research. The challenge is to generate intermediate frames between two existing frames in a video sequence. https://www.unite.ai/wp-content/uploads/2024/10/FILM-example.mp4 Click to play. The FILM framework, a collaboration  between Google and the University of Washington, proposed an effective frame interpolation method that remains popular in hobbyist and

New research from China has proposed a method for improving the quality of images generated by Latent Diffusion Models (LDMs) models such as Stable Diffusion. The method focuses on optimizing the salient regions of an image –  areas most likely to attract human attention. The new research has found that saliency maps (fourth column from

OPINION Nobody in the fictional Star Wars universe takes AI seriously. In the historic human timeline of George Lucas’s 47 year-old science-fantasy franchise, threats from singularities and machine learning consciousness are absent, and AI is confined to autonomous mobile robots ( ‘droids’ ) – which are habitually dismissed by protagonists as mere ‘machines’. Yet most

A new research collaboration between Singapore and China has proposed a method for attacking the popular synthesis method 3D Gaussian Splatting (3DGS). The new attack method uses crafted source data  to overload the available GPU memory of the target system, and to make training so lengthy as to potentially incapacitate the target server, equivalent to

A new research paper from Canada has proposed a framework that deliberately introduces JPEG compression into the training scheme of a neural network, and manages to obtain better results – and better resistance to adversarial attacks. This is a fairly radical idea, since the current general wisdom is that JPEG artifacts, which are optimized for

Apple has just published a paper, in collaboration with USC, that explores the machine learning methods employed to give users of its iOS18 operating system more choice about gender when it comes to translation. In iOS18, users can select alternative gender suggestions for a translated word in the native Translate app. Source: https://support.apple.com/guide/iphone/translate-text-voice-and-conversations-iphd74cb450f/ios Though the

New research from the US presents a method to extract significant portions of training data from fine-tuned models. This could potentially provide legal evidence in cases where an artist’s style has been copied, or where copyrighted images have been used to train generative models of public figures, IP-protected characters, or other content. From the new