Posted by Yang Zhao and Tingbo Hou, Software Engineers, Core ML In recent years, diffusion models have shown great success in text-to-image generation, achieving high image quality, improved inference performance, and expanding our creative inspiration. Nevertheless, it is still challenging to efficiently control the generation, especially with conditions that are difficult to describe with text….
<!– –>Figure 1: CoarsenConf architecture. <!– (I) The encoder $q_phi(z| X, mathcal{R})$ takes the fine-grained (FG) ground truth conformer $X$, RDKit approximate conformer $mathcal{R}$ , and coarse-grained (CG) conformer $mathcal{C}$ as inputs (derived from $X$ and a predefined CG strategy), and outputs a variable-length equivariant CG representation via equivariant message passing and point convolutions. (II)…
Computers possess two remarkable capabilities with respect to images: They can both identify them and generate them anew. Historically, these functions have stood separate, akin to the disparate acts of a chef who is good at creating dishes (generation), and a connoisseur who is good at tasting dishes (recognition). Yet, one can’t help but wonder:…
Disinformation generated by AI may be more convincing than disinformation written by humans, a new study suggests. The research found that people were 3% less likely to spot false tweets generated by AI than those written by humans. That credibility gap, while small, is concerning given that the problem of AI-generated disinformation seems poised to…
In a recent speech, Microsoft CEO Satya Nadella evoked the lofty power of artificial intelligence (AI) to accelerate progress, prosperity, and standards of living. “This technology reaches everyone in the world,” he said. Generative AI takes an idea born in tech communities such as Silicon Valley and Tel Aviv—the ability of algorithmic engines to synthesize…
When Erik Duhaime PhD ’19 was working on his thesis in MIT’s Center for Collective Intelligence, he noticed his wife, then a medical student, spending hours studying on apps that offered flash cards and quizzes. His research had shown that, as a group, medical students could classify skin lesions more accurately than professional dermatologists; the…
Posted by Kuniaki Saito, Student Researcher, Cloud AI Team, and Kihyuk Sohn, Research Scientist, Perception Team Pre-training visual language (VL) models on web-scale image-caption datasets has recently emerged as a powerful alternative to traditional pre-training on image classification data. Image-caption datasets are considered to be more “open-domain” because they contain broader scene types and vocabulary…
Whether you think next-generation AI heralds an exciting new world for humankind or sows the seeds for its destruction, few business leaders can afford to ignore it. But in this febrile environment, it can be hard to plot a course that neither falls foul of the hype nor misses the opportunity entirely. You need only…
Does your company plan to release an AI chatbot, similar to OpenAI’s ChatGPT or Google’s Bard? Doing so means giving the general public a freeform text box for interacting with your AI model. That doesn’t sound so bad, right? Here’s the catch: for every one of your users who has read a “Here’s how ChatGPT…
MIT Responsible AI for Social Empowerment and Education (RAISE) recently celebrated the second annual Day of AI with two flagship local events. The Edward M. Kennedy Institute for the U.S. Senate in Boston hosted a human rights and data policy-focused event that was streamed worldwide. Dearborn STEM Academy in Roxbury, Massachusetts, hosted a student workshop…