Posted by Kihyuk Sohn and Dilip Krishnan, Research Scientists, Google Research Text-to-image models trained on large volumes of image-text pairs have enabled the creation of rich and diverse images encompassing many genres and themes. Moreover, popular styles such as “anime” or “steampunk”, when added to the input text prompt, may translate to specific visual outputs….
Imagine you are scrolling through the photos on your phone and you come across an image that at first you can’t recognize. It looks like maybe something fuzzy on the couch; could it be a pillow or a coat? After a couple of seconds it clicks — of course! That ball of fluff is your…
During a chemical reaction, molecules gain energy until they reach what’s known as the transition state — a point of no return from which the reaction must proceed. This state is so fleeting that it’s nearly impossible to observe it experimentally. The structures of these transition states can be calculated using techniques based on quantum…
The MIT Energy and Climate Hack brought together participants from myriad fields and disciplines to develop rapid, innovative solutions to one of the most complex challenges facing society today: the global energy and climate crisis. Hundreds of students from MIT and colleges across the globe convened on MIT’s campus and virtually for this year’s event, which…
OpenAI has announced the first results from its superalignment team, the firm’s in-house initiative dedicated to preventing a superintelligence—a hypothetical future computer that can outsmart humans—from going rogue. Unlike many of the company’s announcements, this heralds no big breakthrough. In a low-key research paper, the team describes a technique that lets a less powerful large…
Google DeepMind has used a large language model to crack a famous unsolved problem in pure mathematics. In a paper published in Nature today, the researchers say it is the first time a large language model has been used to discover a solution to a long-standing scientific puzzle—producing verifiable and valuable new information that did…
A new system that teaches robots a domestic task in around 20 minutes could help the field of robotics overcome one of its biggest challenges: a lack of training data. The open-source system, called Dobb-E, was trained using data collected from real homes. It can help to teach a robot how to open an air…
MIT-Pillar AI Collective has announced three inaugural fellows for the fall 2023 semester. With support from the program, the graduate students, who are in their final year of a master’s or PhD program, will conduct research in the areas of artificial intelligence, machine learning, and data science with the aim of commercializing their innovations. Launched…
Computational models that mimic the structure and function of the human auditory system could help researchers design better hearing aids, cochlear implants, and brain-machine interfaces. A new study from MIT has found that modern computational models derived from machine learning are moving closer to this goal. In the largest study yet of deep neural networks…
Photolithography involves manipulating light to precisely etch features onto a surface, and is commonly used to fabricate computer chips and optical devices like lenses. But tiny deviations during the manufacturing process often cause these devices to fall short of their designers’ intentions. To help close this design-to-manufacturing gap, researchers from MIT and the Chinese University…