Research

  • Research Areas
  • Impact Areas

Algorithms & Theory

Foundational work that includes complexity, parallel computing and game theory

AI & Machine Learning

Spanning natural language processing, deep-learning, computer vision and more

Computational Biology

Understanding disease via epigenomics, gene regulation and bioinformatics

Computer Architecture

How CPUs, memory and other systems are designed and organized

Graphics & Vision

Teaching computers to interpret, create and animate visual data

Human-Computer Interaction

Software and hardware that let us naturally interact with technology

Programming Languages & Software

From compilers and verification to software design and engineering

Robotics

Vision, actuation, sensing and manipulation of machines

Security & Cryptography

Developing technologies to prevent and recover from cyber-attacks

Systems & Networking

From distributed systems and databases to wireless

Filter options
Filter options

Filter options Close

Role

Media

Research Areas

Impact Areas

Reset Filters

21 Group Results matching all criteria

Research Group

Vision Group

Our researchers create state-of-the-art systems to better recognize objects, people, scenes, behaviors and more, with applications in health-care, gaming, tagging systems and more.

Leads

Ted Adelson

Ted Adelson

Durand

Fredo Durand

Fisher

John Fisher

Freeman

William Freeman

Polina Golland

Polina Golland

Grimson

Eric Grimson

Horn

Berthold Horn

oliva-headshot

Aude Oliva

Ruth Rosenholtz

Ruth Rosenholtz

Torralba

Antonio Torralba

Research Areas

AI & Machine Learning
Graphics & Vision

Impact Areas

Entertainment
Health Care
Transportation

Lead

Ted Adelson

Ted Adelson

Durand

Fredo Durand

Fisher

John Fisher

Freeman

William Freeman

Polina Golland

Polina Golland

Grimson

Eric Grimson

Horn

Berthold Horn

oliva-headshot

Aude Oliva

Ruth Rosenholtz

Ruth Rosenholtz

Torralba

Antonio Torralba

55 Project Results matching all criteria

Project

Aspect-Augmented Adversarial Networks for Domain Adaptation

Natural Language Processing Group
We propose a novel aspect-augmented adversarial network for cross-aspect and cross-domain adaptation tasks. The effectiveness of our approach suggests the potential application of adversarial networks to a broader range of NLP tasks for improved representation learning, such as machine translation and language generation.
Regina Barzilay
Tommi Jaakkola
Regina Barzilay

Regina Barzilay

Tommi Jaakkola

Tommi Jaakkola

Leads

Regina Barzilay

Regina Barzilay

Tommi Jaakkola

Tommi Jaakkola

Research Areas

Algorithms & Theory
AI & Machine Learning
Systems & Networking
Regina Barzilay
Tommi Jaakkola
 
Regina Barzilay

Regina Barzilay

Tommi Jaakkola

Tommi Jaakkola

Project

Synthetically-Identified Clinical Notes

Clinical notes often describe the most important aspects of a patient's physiology and are therefore critical to medical research. However, these notes are typically inaccessible to researchers without prior removal of sensitive protected health information (PHI), a natural language processing (NLP) task referred to as de-identification. In order to build tools that perform deid, one typically needs the very same data that is private, thus creating a chicken-and-the-egg problem. In this work, we generate "fake" clinical notes where the deidentified information is replaced with real-seeming values (e.g. "Tim Lywood" instead of "George Beveridge") that still respect reasonable distributional semantics. We evaluate models trained on this synthetic data and show that they perform just as well as models trained on the sensitive PHI-bearing notes.
Card Image of Tristan Naumann
Willie

William Boag

Szolovits

Peter Szolovits

Leads

Willie

William Boag

Szolovits

Peter Szolovits

Research Areas

AI & Machine Learning

Impact Areas

Health Care
Card Image of Tristan Naumann
 
Willie

William Boag

Szolovits

Peter Szolovits

Project

Information Retrieval for Cancer Treatments in Clinical Literature and Trial Eligibility

A "precision medicine" approach for finding relevant cancer treatments in clinical literature and eligible trials. For a given patient with associated demographics (age, gender) and disease (cancer type, genetic variants), we query a database of all pubmed articles and clinicaltrials.gov trials using NLP techniques to find the most useful and relevant treatments for the patient. Our ensemble-based system performed very well in the TREC 2016 Precision Medicine challenge.

Leads

Michele Filannino

Szolovits

Peter Szolovits

Willie

William Boag

Research Areas

AI & Machine Learning

Impact Areas

Health Care

Project

CliNER: Clinical Concept Extraction

Clinical concept extraction (CCE) of named entities - such as problems, tests, and treatments - aids in forming an understanding of notes and provides a foundation for many downstream clinical decision-making tasks. Historically, this task has been posed as a standard named entity recognition (NER) sequence tagging problem, and solved with feature-based methods using hand-engineered domain knowledge. Recent advances, however, have demonstrated the efficacy of LSTM-based models for NER tasks, including CCE. This work presents CliNER 2.0, a simple-to-install, open-source tool for extracting concepts from clinical text. CliNER 2.0 uses a word- and character- level LSTM model, and achieves state-of-the-art performance. For ease of use, the tool also includes pre-trained models available for public use.

Leads

Willie

William Boag

Card Image of Tristan Naumann

Tristan Naumann

Elena Sergeeva

Elena Sergeeva

Szolovits

Peter Szolovits

Anna Rumshisky

Research Areas

AI & Machine Learning

Impact Areas

Energy

Project

Quantifying Racial Disparities in End-of-Life Care

When discussing racial disparities in medical treatments, critics often cite social factors as confounders which explain away any differences. Comparing the health of whites to that of non-whites we do see that environmental and social factors conspire to yield higher rates of disease and shorter life spans in non-white populations. But does that really show that medical treatment itself is free from bias? We examine end-of-life care in the ICU, stratified by ethnicity, and controlled for acuity using severity assessment scores. Our analysis agrees with previous studies that nonwhites tend to receive more aggressive (high-risk, high reward) treatments, such as mechanical ventilation than non-whites, despite receiving comparable-or-moderately-less noninvasive treatments. Going further, we show that using treatment patterns and clinical notes, we are able to infer a patient's race. Finally, we show evidence suggesting nonwhite have a much greater distrust of the medical community among than whites do. We find that race, even in the great equalizer of end-of-life care, does continue to influence the treatments administered to a patient.

Leads

Marzyeh Ghassemi

Willie

William Boag

Szolovits

Peter Szolovits

Research Areas

AI & Machine Learning

Impact Areas

Health Care

Project

Unsupervised Learning of Interpretable Representations from Sequential Data

Spoken Language Systems Group
Generation of sequential data involves multiple factors operating at different temporal scales. Take natural speech for example, the speaker identity tends to be consistent within an utterance, while the phonetic content changes from frame to frame. By explicitly modeling such hierarchical generative process under a probabilistic framework, we proposed a model that learns to factorizes sequence-level factors and sub-sequence-level factors into different sets of representations without any supervision.
weining_hsu

Wei-Ning Hsu

Jim Glass

Jim Glass

Leads

weining_hsu

Wei-Ning Hsu

Jim Glass

Jim Glass

Research Areas

AI & Machine Learning

Impact Areas

Big Data
 
weining_hsu

Wei-Ning Hsu

Jim Glass

Jim Glass

Project

Automatic Speech Recognition

Spoken Language Systems Group
Automatic speech recognition (ASR) has been a grand challenge machine learning problem for decades. Our ongoing research in this area examines the use of deep learning models for distant and noisy recording conditions, multilingual, and low-resource scenarios.

Leads

Hao Tang

Hao Tang

weining_hsu

Wei-Ning Hsu

Harwath-headshot

David Harwath

alhanai-headshot

Tuka Al Hanai

MIT CSAIL Spoken Language Systems PhD student

Sameer Khurana

Di-Chia Chueh Profile Image

Di-Chia Chueh

Jim Glass

Jim Glass

Research Areas

AI & Machine Learning
Human-Computer Interaction

Impact Areas

Big Data
Education
Entertainment
Health Care
Internet of Things

Project

Unsupervised Speech Processing

Spoken Language Systems Group
All humans process vast quantities of unannotated speech and manage to learn phonetic inventories, word boundaries, etc., and can use these abilities to acquire new word. Why can't ASR technology have similar capabilities? Our goal in this research project is to build speech technology using unannotated speech corpora.
Jim Glass

Leads

image

Jennifer Drexler

Yu-An Chung (Andy)

Yu-An Chung

MIT CSAIL Spoken Language Systems PhD student

Sameer Khurana

Harwath-headshot

David Harwath

Research Areas

AI & Machine Learning
Human-Computer Interaction

Impact Areas

Big Data
Education
Health Care
Jim Glass

32 News Results matching all criteria

F. Harrell
AI & Machine Learning Programming Languages & Software Education Entertainment

3Q: D. Fox Harrell on his video game for the #MeToo era

The Imagination, Computation, and Expression Laboratory at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) has released a new video game called Grayscale, which is designed to sensitize players to problems of sexism, sexual harassment, and sexual assault in the workplace.

3Q: D. Fox Harrell on his video game for the #MeToo era

A new system from MIT's Computer Science and Artificial Intelligence Laboratory works by analyzing light at the edge of walls, which is impacted by the reflections of objects around the corner from the camera.
AI & Machine Learning Graphics & Vision Transportation

An algorithm for your blind spot

Light lets us see the things that surround us, but what if we could also use it to see things hidden around corners? It sounds like science fiction, but that’s the idea behind a new algorithm out of MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) — and its discovery has implications for everything from emergency response to self-driving cars.

An algorithm for your blind spot

Machine learning approach could aid the design of industrial processes for drug manufacturing.
AI & Machine Learning Computational Biology Health Care

Computer system predicts products of chemical reactions

When organic chemists identify a useful chemical compound — a new drug, for instance — it’s up to chemical engineers to determine how to mass-produce it. There could be 100 different sequences of reactions that yield the same end product. But some of them use cheaper reagents and lower temperatures than others, and perhaps most importantly, some are much easier to run continuously, with technicians occasionally topping up reagents in different reaction chambers.

Computer system predicts products of chemical reactions

Researchers at MIT and Massachusetts General Hospital have designed a new system that can efficiently search through hundreds of hours of video of laparoscopic surgeries to identify relevant events and visual features.
AI & Machine Learning Big Data Health Care

Shrinking data for surgical training

Laparoscopy is a surgical technique in which a fiber-optic camera is inserted into a patient’s abdominal cavity to provide a video feed that guides the surgeon through a minimally invasive procedure. Laparoscopic surgeries can take hours, and the video generated by the camera — the laparoscope — is often recorded. Those recordings contain a wealth of information that could be useful for training both medical providers and computer systems that would aid with surgery, but because reviewing them is so time consuming, they mostly sit idle.

Shrinking data for surgical training

Daniel Jackson was awarded the Outstanding Research Award and Impact Paper Award (photo credit Sharona Jacobs)
Algorithms & Theory AI & Machine Learning Big Data Cybersecurity

CSAIL's Daniel Jackson receives two ACM awards

This week the Association for Computer Machinery presented CSAIL principal investigator Daniel Jackson with the 2017 ACM SIGSOFT Outstanding Research Award for his pioneering work in software engineering. (This fall he also received the ACM SIGSOFT Impact Paper Award for his research method for finding bugs in code.)An EECS professor and associate director of CSAIL, Jackson was given the Outstanding Research Award for his “foundational contributions to software modeling, the creation of the modeling language Alloy, and the development of a widely used tool supporting model verification.”

CSAIL's Daniel Jackson receives two ACM awards

PhD student Danielle Olson believes we can make digital information-sharing more natural and interpersonal, by creating immersive media to better understand each other’s feelings and backgrounds.
AI & Machine Learning Human-Computer Interaction Entertainment

Danielle Olson: Building empathy through computer science and art

Communicating through computers has become an extension of our daily reality. But as speaking via screens has become commonplace, our exchanges are losing inflection, body language, and empathy. Danielle Olson ’14, a first-year PhD student at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), believes we can make digital information-sharing more natural and interpersonal, by creating immersive media to better understand each other’s feelings and backgrounds.

Danielle Olson: Building empathy through computer science and art

System directs camera-equipped drones to maintain framing of an aerial shot.
Algorithms & Theory AI & Machine Learning Graphics & Vision Robotics Entertainment Transportation

Cinematography on the fly

In recent years, a host of Hollywood blockbusters — including “The Fast and the Furious 7,” “Jurassic World,” and “The Wolf of Wall Street” — have included aerial tracking shots provided by drone helicopters outfitted with cameras. Those shots required separate operators for the drones and the cameras, and careful planning to avoid collisions. But a team of researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and ETH Zurich hope to make drone cinematography more accessible, simple, and reliable.

Cinematography on the fly

WaitSuite opens up new possibilities for "micro-learning," leveraging idle moments like when you're waiting to connect to WiFi or refresh your email.
AI & Machine Learning Human-Computer Interaction Education Internet of Things

Learn a language while you wait for WiFi

Hyper-connectivity has changed the way we communicate, wait, and productively use our time. Even in a world of 5G wireless and “instant” messaging, there are countless moments throughout the day when we’re waiting for messages, texts, and Snapchats to refresh. But our frustrations with waiting a few extra seconds for our emails to push through doesn’t mean we have to simply stand by.

Learn a language while you wait for WiFi

21 Group Results

Research Group

Vision Group

Our researchers create state-of-the-art systems to better recognize objects, people, scenes, behaviors and more, with applications in health-care, gaming, tagging systems and more.

Leads

Ted Adelson

Ted Adelson

Durand

Fredo Durand

Fisher

John Fisher

Freeman

William Freeman

Polina Golland

Polina Golland

Grimson

Eric Grimson

Horn

Berthold Horn

oliva-headshot

Aude Oliva

Ruth Rosenholtz

Ruth Rosenholtz

Torralba

Antonio Torralba

Research Areas

AI & Machine Learning
Graphics & Vision

Impact Areas

Entertainment
Health Care
Transportation

Lead

Ted Adelson

Ted Adelson

Durand

Fredo Durand

Fisher

John Fisher

Freeman

William Freeman

Polina Golland

Polina Golland

Grimson

Eric Grimson

Horn

Berthold Horn

oliva-headshot

Aude Oliva

Ruth Rosenholtz

Ruth Rosenholtz

Torralba

Antonio Torralba

55 Project Results

Project

An Interlock for Self Driving Cars

Software Design Group
Computer-Aided Programming
Self-driving cars are likely to be safer, on average, than human-driven cars. But they may fail in new and catastrophic ways that a human driver could prevent. This project is designing a new architecture for a highly dependable self-driving car.
Jackson image

Daniel Jackson

Solar-Lezama

Armando Solar-Lezama

Leads

Jackson image

Daniel Jackson

Solar-Lezama

Armando Solar-Lezama

Research Areas

AI & Machine Learning
Human-Computer Interaction
Programming Languages & Software
Robotics
Systems & Networking

Impact Areas

Transportation
 
Jackson image

Daniel Jackson

Solar-Lezama

Armando Solar-Lezama

Project

Arabic Language Processing

Spoken Language Systems Group
The Arabic language is spoken by over one billion people around the world. Arabic presents a variety of challenges for speech and language processing technologies. In our group, we have several research topics examining Arabic, including dialect identification, speech recognition, machine translation, and language processing.
Shon
alhanai-headshot
Jim Glass

Leads

cannot load image

Ramy Baly

Belinkov-headshot

Yonatan Belinkov

Mitra Mohtarami

Mitra Mohtarami

Research Areas

AI & Machine Learning
Human-Computer Interaction
Shon
alhanai-headshot
Jim Glass

Project

Aspect-Augmented Adversarial Networks for Domain Adaptation

Natural Language Processing Group
We propose a novel aspect-augmented adversarial network for cross-aspect and cross-domain adaptation tasks. The effectiveness of our approach suggests the potential application of adversarial networks to a broader range of NLP tasks for improved representation learning, such as machine translation and language generation.
Regina Barzilay
Tommi Jaakkola
Regina Barzilay

Regina Barzilay

Tommi Jaakkola

Tommi Jaakkola

Leads

Regina Barzilay

Regina Barzilay

Tommi Jaakkola

Tommi Jaakkola

Research Areas

Algorithms & Theory
AI & Machine Learning
Systems & Networking
Regina Barzilay
Tommi Jaakkola
 
Regina Barzilay

Regina Barzilay

Tommi Jaakkola

Tommi Jaakkola

Project

Automatic Speech Recognition

Spoken Language Systems Group
Automatic speech recognition (ASR) has been a grand challenge machine learning problem for decades. Our ongoing research in this area examines the use of deep learning models for distant and noisy recording conditions, multilingual, and low-resource scenarios.

Leads

Hao Tang

Hao Tang

weining_hsu

Wei-Ning Hsu

Harwath-headshot

David Harwath

alhanai-headshot

Tuka Al Hanai

MIT CSAIL Spoken Language Systems PhD student

Sameer Khurana

Di-Chia Chueh Profile Image

Di-Chia Chueh

Jim Glass

Jim Glass

Research Areas

AI & Machine Learning
Human-Computer Interaction

Impact Areas

Big Data
Education
Entertainment
Health Care
Internet of Things

Project

CliNER: Clinical Concept Extraction

Clinical concept extraction (CCE) of named entities - such as problems, tests, and treatments - aids in forming an understanding of notes and provides a foundation for many downstream clinical decision-making tasks. Historically, this task has been posed as a standard named entity recognition (NER) sequence tagging problem, and solved with feature-based methods using hand-engineered domain knowledge. Recent advances, however, have demonstrated the efficacy of LSTM-based models for NER tasks, including CCE. This work presents CliNER 2.0, a simple-to-install, open-source tool for extracting concepts from clinical text. CliNER 2.0 uses a word- and character- level LSTM model, and achieves state-of-the-art performance. For ease of use, the tool also includes pre-trained models available for public use.

Leads

Willie

William Boag

Card Image of Tristan Naumann

Tristan Naumann

Elena Sergeeva

Elena Sergeeva

Szolovits

Peter Szolovits

Anna Rumshisky

Research Areas

AI & Machine Learning

Impact Areas

Energy

32 News Results

F. Harrell
AI & Machine Learning Programming Languages & Software Education Entertainment

3Q: D. Fox Harrell on his video game for the #MeToo era

The Imagination, Computation, and Expression Laboratory at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) has released a new video game called Grayscale, which is designed to sensitize players to problems of sexism, sexual harassment, and sexual assault in the workplace.

3Q: D. Fox Harrell on his video game for the #MeToo era

A new system from MIT's Computer Science and Artificial Intelligence Laboratory works by analyzing light at the edge of walls, which is impacted by the reflections of objects around the corner from the camera.
AI & Machine Learning Graphics & Vision Transportation

An algorithm for your blind spot

Light lets us see the things that surround us, but what if we could also use it to see things hidden around corners? It sounds like science fiction, but that’s the idea behind a new algorithm out of MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) — and its discovery has implications for everything from emergency response to self-driving cars.

An algorithm for your blind spot

Machine learning approach could aid the design of industrial processes for drug manufacturing.
AI & Machine Learning Computational Biology Health Care

Computer system predicts products of chemical reactions

When organic chemists identify a useful chemical compound — a new drug, for instance — it’s up to chemical engineers to determine how to mass-produce it. There could be 100 different sequences of reactions that yield the same end product. But some of them use cheaper reagents and lower temperatures than others, and perhaps most importantly, some are much easier to run continuously, with technicians occasionally topping up reagents in different reaction chambers.

Computer system predicts products of chemical reactions

Researchers at MIT and Massachusetts General Hospital have designed a new system that can efficiently search through hundreds of hours of video of laparoscopic surgeries to identify relevant events and visual features.
AI & Machine Learning Big Data Health Care

Shrinking data for surgical training

Laparoscopy is a surgical technique in which a fiber-optic camera is inserted into a patient’s abdominal cavity to provide a video feed that guides the surgeon through a minimally invasive procedure. Laparoscopic surgeries can take hours, and the video generated by the camera — the laparoscope — is often recorded. Those recordings contain a wealth of information that could be useful for training both medical providers and computer systems that would aid with surgery, but because reviewing them is so time consuming, they mostly sit idle.

Shrinking data for surgical training

Daniel Jackson was awarded the Outstanding Research Award and Impact Paper Award (photo credit Sharona Jacobs)
Algorithms & Theory AI & Machine Learning Big Data Cybersecurity

CSAIL's Daniel Jackson receives two ACM awards

This week the Association for Computer Machinery presented CSAIL principal investigator Daniel Jackson with the 2017 ACM SIGSOFT Outstanding Research Award for his pioneering work in software engineering. (This fall he also received the ACM SIGSOFT Impact Paper Award for his research method for finding bugs in code.)An EECS professor and associate director of CSAIL, Jackson was given the Outstanding Research Award for his “foundational contributions to software modeling, the creation of the modeling language Alloy, and the development of a widely used tool supporting model verification.”

CSAIL's Daniel Jackson receives two ACM awards

PhD student Danielle Olson believes we can make digital information-sharing more natural and interpersonal, by creating immersive media to better understand each other’s feelings and backgrounds.
AI & Machine Learning Human-Computer Interaction Entertainment

Danielle Olson: Building empathy through computer science and art

Communicating through computers has become an extension of our daily reality. But as speaking via screens has become commonplace, our exchanges are losing inflection, body language, and empathy. Danielle Olson ’14, a first-year PhD student at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), believes we can make digital information-sharing more natural and interpersonal, by creating immersive media to better understand each other’s feelings and backgrounds.

Danielle Olson: Building empathy through computer science and art

System directs camera-equipped drones to maintain framing of an aerial shot.
Algorithms & Theory AI & Machine Learning Graphics & Vision Robotics Entertainment Transportation

Cinematography on the fly

In recent years, a host of Hollywood blockbusters — including “The Fast and the Furious 7,” “Jurassic World,” and “The Wolf of Wall Street” — have included aerial tracking shots provided by drone helicopters outfitted with cameras. Those shots required separate operators for the drones and the cameras, and careful planning to avoid collisions. But a team of researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and ETH Zurich hope to make drone cinematography more accessible, simple, and reliable.

Cinematography on the fly

WaitSuite opens up new possibilities for "micro-learning," leveraging idle moments like when you're waiting to connect to WiFi or refresh your email.
AI & Machine Learning Human-Computer Interaction Education Internet of Things

Learn a language while you wait for WiFi

Hyper-connectivity has changed the way we communicate, wait, and productively use our time. Even in a world of 5G wireless and “instant” messaging, there are countless moments throughout the day when we’re waiting for messages, texts, and Snapchats to refresh. But our frustrations with waiting a few extra seconds for our emails to push through doesn’t mean we have to simply stand by.

Learn a language while you wait for WiFi