Skip to content Skip to sidebar Skip to footer

School of Engineering

This small, secure identification marker can verify the authenticity of nearly everything.

Researchers at MIT have developed a new cryptographic ID tag that is cheaper, smaller, and more secure than traditional radio frequency tags (RFIDs). Initially, the researchers developed a tiny tag using terahertz waves, which offered improved security over RFIDs. However, this tag shared a vulnerability with RFID tags: a counterfeiter could peel off the tag…

Read More

The new model highlights medicines that are not advisable to be combined.

Scientists from MIT, Brigham and Women’s Hospital, and Duke University have developed a method to track how oral drugs pass through the human digestive tract. This research is considered key as it can help predict potential drug interactions which improve patient treatment. The research used a combination of tissue models and machine learning algorithms. Oral…

Read More

A novel method allows AI chatbots to engage in conversations throughout the day without experiencing system failures.

A group of researchers from MIT and other institutions have pinpointed a key issue that causes performance degradation in AI chatbots during long conversations and have developed a simple solution to rectify it. Large language machine-learning models such as the ChatGPT use key-value cache to store data. However, when the cache needs to hold more…

Read More

This small, secure identification label has the ability to verify nearly everything.

Researchers at MIT have developed a highly advanced anti-tampering ID tag that is significantly smaller and cheaper than traditional Radio Frequency Identification (RFID) tags. It leverages the power of terahertz waves to improve upon conventional security tools and offers an innovative solution to safeguard items from counterfeit. Traditional security tags, much like this one, use radio…

Read More

The new design recognizes medications that are incompatible when taken concurrently.

Researchers from MIT, Brigham and Women’s Hospital, and Duke University have developed a research approach to identify how different drugs exit the digestive tract. The method uses tissue models and machine-learning algorithms to understand which transporters are used by drugs, revealing how a commonly prescribed antibiotic and blood thinners can interfere with each other. Transporter…

Read More

A novel method enables AI chatbots to engage in conversation all day without experiencing a system shutdown.

Researchers from MIT and other institutions have devised an innovative solution to prevent chatbots from crashing during prolonged dialogues. The method, known as StreamingLLM, makes a simple adjustment to the key-value cache, essentially the 'conversation memory,' of well-developed machine-learning models. By ensuring the first few data points don't get bumped out, the chatbot can maintain…

Read More

This small, secure identification label has the ability to verify nearly everything.

Researchers from the Massachusetts Institute of Technology (MIT) have developed a microchip identification tag that works with terahertz waves to offer a more secure verification method than traditional radio frequency identification (RFID) tags. Terahertz waves are smaller in wavelength, yet much higher in frequency than radio waves, which make the tag more difficult to clone…

Read More

The latest model recognizes medications that should not be concurrently administered.

Researchers from MIT, Brigham and Women’s Hospital, and Duke University have developed a novel approach combining machine-learning algorithms and tissue models to identify the specific transporters used by drugs in the gastrointestinal tract. This breakthrough could lead to improvements in patient treatment and drug development. Transporter proteins within the gastrointestinal system enable drug absorption. These proteins…

Read More

A novel method has been developed to allow AI chatbots to engage in conversation all day without experiencing any system breakdowns.

A team of researchers from MIT and other institutions has developed a method to stop the performance deterioration in AI language models involved in continuous dialogue, like the AI chatbot, ChatGPT. Named StreamingLLM, the solution revolves around a modification in the machine’s key-value cache, acting as a conversation memory. Conventionally, when the cache overflows, the…

Read More

This small, secure identification tag has the ability to verify nearly anything.

MIT researchers have developed a small, affordable, and secure cryptographic ID tag that improves upon traditional radio frequency identification (RFID) tags by using terahertz waves, which are smaller and have higher frequencies than radio waves. Traditional RFIDs are often attacked by counterfeiters who take them off genuine items and reattach to a fake one; the…

Read More

The new method pinpoints medications that should not be combined.

Researchers from MIT, Brigham and Women’s Hospital, and Duke University have developed a strategy to identify how different drugs are transported through the digestive tract. This new multipronged strategy combines the use of tissue models and machine learning algorithms to comprehend which transporters help various drugs to pass through the digestive tract. This is an important…

Read More

A novel method allows AI chatbots to engage in conversations throughout the day without experiencing a system crash.

Researchers from MIT have devised a method called StreamingLLM which enables chatbots to maintain long, uninterrupted dialogues without crashing or performance dips. It involves a modification to the key-value cache at the core of many large language models which serves as a conversation memory, ensuring the initial data points remain present. The method facilitates a…

Read More