Researchers from MIT, Brigham and Women’s Hospital, and Duke University have developed a system using tissue models and machine-learning algorithms to identify how different drugs navigate through the lining of the digestive tract, which could have significant implications for the world of medicine.
Orally-taken drugs often rely on transporter proteins within the digestive tract's cells to…
In 2010, MIT Media Lab students Karthik Dinakar SM ’12, PhD ’17 and Birago Jones SM ’12 embarked on creating a tool to assist content moderation teams at companies like Twitter (now X) and YouTube. Their demo, which was presented at a cyberbullying summit at the White House, identified troublesome posts through machine learning. However,…
Creating high-quality, diverse media from text is often a challenging task for existing models. Such models either generate low-quality outcomes, are slow, or need a significant level of computational power. Current solutions that resolve individual tasks such as text-to-image or text-to-video generation need to be merged with other models to achieve the desired effect. Moreover,…
Generating high-quality, diverse media content from textual input is a complex task. Traditional models have suffered from several limitations such as poor output quality, slow processing or high computational resource requirements, making them less efficient and widespread. Even for individual tasks like text-to-image or text-to-video, these models often need to be used in conjunction with…
Genomic research, which seeks to understand the structure and function of genomes, plays a significant role in a variety of sectors, including medicine, biotechnology, and evolutionary biology. It provides valuable insights into potential therapies for genetic disorders and fundamental life processes. However, the field also faces major challenges, particularly when it comes to modelling and…
Researchers from MIT and other institutions have developed a solution to maintain continuous human-AI interactions without the chatbot crashing or slowing down. The solution, known as StreamingLLM, involves tweaking the key-value cache (like a conversation memory) that forms the heart of many large language models. Under the conventional setup, the cache, when filled beyond its…
A team of researchers from MIT has developed an innovative antitampering cryptographic ID tag, which is smaller, cheaper, and more secure than traditional radio frequency identification (RFID) tags. Traditional RFIDs can be detached from a genuine item and reattached on counterfeit products, compromising the authenticity of the item. As a solution, the MIT team creates…
American researchers at MIT, Brigham and Women’s Hospital, and Duke University have designed an innovative approach to identifying the transporters used by different drugs that are taken orally. The strategy involves the use of both tissue models and machine-learning algorithms, and has already revealed that a commonly prescribed antibiotic and a blood thinner can interfere…
Federated learning is an ML approach that decentralizes the AI training process, offering enhanced privacy and security. This approach keeps data localized on various devices which then compute and share model updates, while a central server collects these updates to enhance the overall model. This differs from traditional AI methods which amass data from multiple…