Dina Katabi
YOU?
Author Swipe
View article: Transformer Model Detects Antidepressant Use From a Single Night of Sleep, Unlocking an Adherence Biomarker
Transformer Model Detects Antidepressant Use From a Single Night of Sleep, Unlocking an Adherence Biomarker Open
Antidepressant nonadherence is pervasive, driving relapse, hospitalization, suicide risk, and billions in avoidable costs. Clinicians need tools that detect adherence lapses promptly, yet current methods are either invasive (serum assays, …
View article: RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning Open
Reinforcement learning (RL) has recently emerged as a compelling approach for enhancing the reasoning capabilities of large language models (LLMs), where an LLM generator serves as a policy guided by a verifier (reward model). However, cur…
View article: Quantifying Itch and its Impact on Sleep Using Machine Learning and Radio Signals
Quantifying Itch and its Impact on Sleep Using Machine Learning and Radio Signals Open
Chronic itch affects 13% of the US population, is highly debilitating, and underlies many medical conditions. A major challenge in clinical care and new therapeutics development is the lack of an objective measure for quantifying itch, lea…
View article: Language-Guided Image Tokenization for Generation
Language-Guided Image Tokenization for Generation Open
Image tokenization, the process of transforming raw image pixels into a compact low-dimensional latent representation, has proven crucial for scalable and efficient image generation. However, mainstream image tokenization methods generally…
Accelerating Parkinson’s Disease drug development with federated learning approaches Open
Parkinson's Disease is a progressive neurodegenerative disorder afflicting almost 12 million people. Increased understanding of its complex and heterogenous disease pathology, etiology and symptom manifestations has resulted in the need to…
View article: What radio waves tell us about sleep!
What radio waves tell us about sleep! Open
The ability to assess sleep at home, capture sleep stages, and detect the occurrence of apnea (without on-body sensors) simply by analyzing the radio waves bouncing off people’s bodies while they sleep is quite powerful. Such a capability …
View article: What Radio Waves Tell Us about Sleep
What Radio Waves Tell Us about Sleep Open
The ability to assess sleep at home, capture sleep stages, and detect the occurrence of apnea (without on-body sensors) simply by analyzing the radio waves bouncing off people's bodies while they sleep is quite powerful. Such a capability …
View article: Learning Vision from Models Rivals Learning Vision from Data
Learning Vision from Models Rivals Learning Vision from Data Open
We introduce SynCLR, a novel approach for learning visual representations exclusively from synthetic images and synthetic captions, without any real data. We synthesize a large dataset of image captions using LLMs, then use an off-the-shel…
View article: The Limits of Fair Medical Imaging AI In The Wild
The Limits of Fair Medical Imaging AI In The Wild Open
As artificial intelligence (AI) rapidly approaches human-level performance in medical imaging, it is crucial that it does not exacerbate or propagate healthcare disparities. Prior research has established AI's capacity to infer demographic…
View article: Scaling Laws of Synthetic Images for Model Training ... for Now
Scaling Laws of Synthetic Images for Model Training ... for Now Open
Recent significant advances in text-to-image models unlock the possibility of training vision systems using synthetic images, potentially overcoming the difficulty of collecting curated data at scale. It is unclear, however, how these mode…
View article: Return of Unconditional Generation: A Self-supervised Representation Generation Method
Return of Unconditional Generation: A Self-supervised Representation Generation Method Open
Unconditional generation -- the problem of modeling data distribution without relying on human-annotated labels -- is a long-standing and fundamental challenge in generative models, creating a potential of learning from large-scale unlabel…
View article: Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency
Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency Open
Current vision-language generative models rely on expansive corpora of paired image-text data to attain optimal performance and generalization capabilities. However, automatically collecting such data (e.g. via large-scale web scraping) le…
View article: Unsupervised Object Localization with Representer Point Selection
Unsupervised Object Localization with Representer Point Selection Open
We propose a novel unsupervised object localization method that allows us to explain the predictions of the model by utilizing self-supervised pre-trained models without additional finetuning. Existing unsupervised and self-supervised obje…
View article: Improving CLIP Training with Language Rewrites
Improving CLIP Training with Language Rewrites Open
Contrastive Language-Image Pre-training (CLIP) stands as one of the most effective and scalable methods for training transferable vision models using paired image and text data. CLIP models are trained using contrastive loss, which typical…
View article: Reparo: Loss-Resilient Generative Codec for Video Conferencing
Reparo: Loss-Resilient Generative Codec for Video Conferencing Open
Packet loss during video conferencing often results in poor quality and video freezing. Retransmitting lost packets is often impractical due to the need for real-time playback, and using Forward Error Correction (FEC) for packet recovery i…
View article: Change is Hard: A Closer Look at Subpopulation Shift
Change is Hard: A Closer Look at Subpopulation Shift Open
Machine learning models often perform poorly on subgroups that are underrepresented in the training data. Yet, little is understood on the variation in mechanisms that cause subpopulation shifts, and how algorithms generalize across such d…
View article: Contactless Oxygen Monitoring with Gated Transformer
Contactless Oxygen Monitoring with Gated Transformer Open
With the increasing popularity of telehealth, it becomes critical to ensure that basic physiological signals can be monitored accurately at home, with minimal patient overhead. In this paper, we propose a contactless approach for monitorin…
View article: MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis
MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis Open
Generative modeling and representation learning are two key tasks in computer vision. However, these models are typically trained independently, which ignores the potential for each task to help the other, and leads to training and model m…
View article: SimPer: Simple Self-Supervised Learning of Periodic Targets
SimPer: Simple Self-Supervised Learning of Periodic Targets Open
From human physiology to environmental evolution, important processes in nature often exhibit meaningful and strong periodic or quasi-periodic changes. Due to their inherent label scarcity, learning useful representations for periodic task…
View article: Rank-N-Contrast: Learning Continuous Representations for Regression
Rank-N-Contrast: Learning Continuous Representations for Regression Open
Deep regression models typically learn in an end-to-end fashion without explicitly emphasizing a regression-aware representation. Consequently, the learned representations exhibit fragmentation and fail to capture the continuous nature of …
Artificial intelligence-enabled detection and assessment of Parkinson’s disease using nocturnal breathing signals Open
There are currently no effective biomarkers for diagnosing Parkinson’s disease (PD) or tracking its progression. Here, we developed an artificial intelligence (AI) model to detect PD and track its progression from nocturnal breathing signa…
View article: Unsupervised Learning for Human Sensing Using Radio Signals
Unsupervised Learning for Human Sensing Using Radio Signals Open
There is a growing literature demonstrating the feasibility of using Radio Frequency (RF) signals to enable key computer vision tasks in the presence of occlusions and poor lighting. It leverages that RF signals traverse walls and occlusio…
View article: CornerRadar
CornerRadar Open
Unmanned robots are increasingly used around humans in factories, malls, and hotels. As they navigate our space, it is important to ensure that such robots do not collide with people who suddenly appear as they turn a corner. Today, howeve…
View article: On Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization and Beyond
On Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization and Beyond Open
Real-world data often exhibit imbalanced label distributions. Existing studies on data imbalance focus on single-domain settings, i.e., samples are from the same data distribution. However, natural data can originate from distinct domains,…
View article: Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning
Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning Open
Indiscriminate data poisoning attacks are quite effective against supervised learning. However, not much is known about their impact on unsupervised contrastive learning (CL). This paper is the first to consider indiscriminate poisoning at…
View article: Unsupervised Domain Generalization by Learning a Bridge Across Domains
Unsupervised Domain Generalization by Learning a Bridge Across Domains Open
The ability to generalize learned representations across significantly different visual domains, such as between real photos, clipart, paintings, and sketches, is a fundamental capacity of the human visual system. In this paper, different …
View article: Targeted Supervised Contrastive Learning for Long-Tailed Recognition
Targeted Supervised Contrastive Learning for Long-Tailed Recognition Open
Real-world data often exhibits long tail distributions with heavy class imbalance, where the majority classes can dominate the training process and alter the decision boundaries of the minority classes. Recently, researchers have investiga…
View article: Contactless In-Home Monitoring of the Long-Term Respiratory and Behavioral Phenotypes in Older Adults With COVID-19: A Case Series
Contactless In-Home Monitoring of the Long-Term Respiratory and Behavioral Phenotypes in Older Adults With COVID-19: A Case Series Open
Currently, there is a limited understanding of long-term outcomes of COVID-19, and a need for in-home measurements of patients through the whole course of their disease. We study a novel approach for monitoring the long-term trajectories o…