Recent advancements in pre-trained large foundation models (LFM) have yielded significant breakthroughs across various domains, including natural language processing and computer vision. These models have been particularly impactful in the domain of medical diagnostic tasks. With abundant unlabeled data, an LFM has been developed for fundus images using the Vision Transformer (VIT) and a self-supervised learning framework. This LFM has shown promising performance in fundus disease diagnosis across multiple datasets. On the other hand, deep learning models have long been challenged by dataset quality issues, such as image quality and dataset bias. To investigate the influence of data quality on LFM, we conducted explorations in two fundus diagnosis tasks using datasets of varying quality. Specifically, we explored the following questions: Is LFM more robust to image quality? Is LFM affected by dataset bias? Can fine-tuning techniques alleviate these effects? Our investigation found that LFM exhibits greater resilience to dataset quality issues, including image quality and dataset bias, compared to typical convolutional networks. Furthermore, we discovered that overall fine-tuning is an effective adapter for LFM to mitigate the impact of dataset quality issues.

Real-world applications such as logistics, security, minerals and oil exploration, personal and vehicle navigation, wireless communications, and surveillance, just to mention a few, struggle for achieving a solution for medium-high accuracy localization of some non cooperative targets. Most approaches for range-based localization do not assume agents can control the network motion to improve localization accuracy. Thus, a passive localization algorithm solely relies on a stream of sensor data. One of the first approaches for active localization is [1], where one robot attempts to self-localize with a Markovian approach: computing a belief for a discretized map of the region of interest, given sensor measurements, and maximizing the entropy of its next movement. However, when we envision large teams of moving artificial agents, with high-level tasks, like intercepting an intruder, the computational paradigm should accommodate scalability concerns.

Robotaxis may still be a few years out, but there are other industries that can be transformed by autonomous vehicles as they are today. MIT spin-off ISEE has identified one in the common shipping yard, where containers are sorted and stored -- today by a dwindling supply of human drivers, but tomorrow perhaps by the company's purpose-built robotic yard truck. With new funding and partnerships with major shippers, the company may be about to go big. Shipping yards are the buffer zone of the logistics industry. When a container is unloaded from a ship full of them, it can't exactly just sit there on the wharf where the crane dropped it. Maybe it's time sensitive and has to trucked out right away; maybe it needs to go through customs and inspections and must stay in the facility for a week; maybe it's refrigerated and needs power and air hookups.

Boston's notoriously unfriendly drivers and chaotic roads may be the perfect testing ground for a fundamentally different kind of self-driving car. An MIT spin-off called iSee is developing and testing the autonomous driving system using a novel approach to artificial intelligence. Instead of relying on simple rules or machine-learning algorithms to train cars to drive, the startup is taking inspiration from cognitive science to give machines a kind of common sense and the ability to quickly deal with new situations. It is developing algorithms that try to match the way humans understand and learn about the physical world, including interacting with other people. The approach could lead to self-driving vehicles that are much better equipped to deal with unfamiliar scenes and complex interactions on the road.

How long does it usually take you to pick out a new pair of glasses at the store? 10 minutes? When left unsupervised, I've admittedly taken over an hour. It's a big deal, as it is scientifically established that the type of glasses you wear impacts perception of your intelligence, success, and attractiveness. It's 2016; there must certainly be some sort of technology that has solved this problem. Of course there is! DITTO technologies developed a virtual mirror that allows customers to try on hundreds of products from the comfort of their homes.

The task of removing eyeglasses from faces is not a new one, by far. A hefty amount of scientific literature documents a variety of image processing algorithms to remove eyeglasses, often for the goal of improving facial recognition technologies. Using some thoughtful math with features such as contrast, edges, and congruency, these techniques typically detect and subtract the image pixels containing the glasses and then synthesize the obfuscated facial region through smoothing or inference. Despite the ingenuity, these algorithms can fall short at the recognition of the glasses and/or the reconstruction of the face. They can also notably struggle with generalizing across different skin tones and correcting for shadows, magnification, and glare caused by the frames and lenses.

Large-scale precision matrix estimation is of fundamental importance yet challenging in many contemporary applications for recovering Gaussian graphical models. In this paper, we suggest a new approach of innovated scalable efficient estimation (ISEE) for estimating large precision matrix. Motivated by the innovated transformation, we convert the original problem into that of large covariance matrix estimation. The suggested method combines the strengths of recent advances in high-dimensional sparse modeling and large covariance matrix estimation. Compared to existing approaches, our method is scalable and can deal with much larger precision matrices with simple tuning. Under mild regularity conditions, we establish that this procedure can recover the underlying graphical structure with significant probability and provide efficient estimation of link strengths. Both computational and theoretical advantages of the procedure are evidenced through simulation and real data examples.

Much of the ongoing explosion of digital content is in the form of text. This content is a virtual gold-mine of information that can inform a range of social, governmental, and business decisions. For example, using content available on blogs and social networking sites businesses can find out what its customers are saying about their products and services. In the digital age where customer is king, the business value of ascertaining consumer sentiment cannot be overstated. People express sentiments in myriad ways. At times, they use simple, direct assertions, but most often they use sentences involving comparisons, conjunctions expressing multiple and possibly opposing sentiments about multiple features and entities,and pronominal references whose resolution requires discourse level context. Frequently people use abbreviations, slang, SMSese, idioms and metaphors. Understanding the latter also requires common sense reasoning. In this paper, we present iSEE, a fully implemented sentiment extraction engine, which makes use of statistical methods, classical NLU techniques, common sense reasoning, and probabilistic inference to extract entity and feature specific sentiment from complex sentences and dialog. Most of the components of iSEE are domain independent and the system can be generalized to new domains by simply adding domain relevant lexicons.