Sketch design concepts are recurring patterns found in parametric CAD sketches. Though rarely explicitly formalized by the CAD designers, these concepts are implicitly used in design for modularity and regularity. In this paper, we propose a learning based approach that discovers the modular concepts by induction over raw sketches. We propose the dual implicit-explicit representation of concept structures that allows implicit detection and explicit generation, and the separation of structure generation and parameter instantiation for parameterized concept generation, to learn modular concepts by end-to-end training. We demonstrate the design concept learning on a large scale CAD sketch dataset and show its applications for design intent interpretation and auto-completion.

When an Agent visits a platform recommending a menu of content to select from, their choice of item depends not only on fixed preferences, but also on their prior engagements with the platform. The Recommender's primary objective is typically to encourage content consumption which optimizes some reward, such as ad revenue, but they often also aim to ensure that a wide variety of content is consumed by the Agent over time. We formalize this problem as an adversarial bandit task. At each step, the Recommender presents a menu of $k$ (out of $n$) items to the Agent, who selects one item in the menu according to their unknown preference model, which maps their history of past items to relative selection probabilities. The Recommender then observes the Agent's chosen item and receives bandit feedback of the item's reward. In addition to optimizing reward from selected items, the Recommender must also ensure that the total distribution of chosen items has sufficiently high entropy. We define a class of preference models which are locally learnable, i.e. behavior over the entire domain can be estimated by only observing behavior in a small region; this includes models representable by bounded-degree polynomials as well as functions with a sparse Fourier basis. For this class, we give an algorithm for the Recommender which obtains $\tilde{O}(T^{3/4})$ regret against all item distributions satisfying two conditions: they are sufficiently diversified, and they are instantaneously realizable at any history by some distribution over menus. We show that these conditions are closely connected: all sufficiently high-entropy distributions are instantaneously realizable at any item history. We also give a set of negative results justifying our assumptions, in the form of a runtime lower bound for non-local learning and linear regret lower bounds for alternate benchmarks.

The ability of generative language models (GLMs) to generate text has improved considerably in the last few years, enabling their use for generative data augmentation. In this work, we propose CONDA, an approach to further improve GLMs' ability to generate synthetic data by reformulating data generation as context generation for a given question-answer (QA) pair and leveraging QA datasets for training context generators. Then, we cast downstream tasks into the same question answering format and adapt the fine-tuned context generators to the target task domain. Finally, we use the fine-tuned GLM to generate relevant contexts, which are in turn used as synthetic training data for their corresponding tasks. We perform extensive experiments on multiple classification datasets and demonstrate substantial improvements in performance for both few- and zero-shot settings. Our analysis reveals that QA datasets that require high-level reasoning abilities (e.g., abstractive and common-sense QA datasets) tend to give the best boost in performance in both few-shot and zero-shot settings.

We introduce fastcoref, a python package for fast, accurate, and easy-to-use English coreference resolution. The package is pip-installable, and allows two modes: an accurate mode based on the LingMess architecture, providing state-of-the-art coreference accuracy, and a substantially faster model, F-coref, which is the focus of this work. F-coref allows to process 2.8K OntoNotes documents in 25 seconds on a V100 GPU (compared to 6 minutes for the LingMess model, and to 12 minutes of the popular AllenNLP coreference model) with only a modest drop in accuracy. The fast speed is achieved through a combination of distillation of a compact model from the LingMess model, and an efficient batching implementation using a technique we call leftover batching. Our code is available at https://github.com/shon-otmazgin/fastcoref

We propose a method to infer a dense depth map from a single image, its calibration, and the associated sparse point cloud. In order to leverage existing models (teachers) that produce putative depth maps, we propose an adaptive knowledge distillation approach that yields a positive congruent training process, wherein a student model avoids learning the error modes of the teachers. In the absence of ground truth for model selection and training, our method, termed Monitored Distillation, allows a student to exploit a blind ensemble of teachers by selectively learning from predictions that best minimize the reconstruction error for a given image. Monitored Distillation yields a distilled depth map and a confidence map, or ``monitor'', for how well a prediction from a particular teacher fits the observed image. The monitor adaptively weights the distilled depth where if all of the teachers exhibit high residuals, the standard unsupervised image reconstruction loss takes over as the supervisory signal. On indoor scenes (VOID), we outperform blind ensembling baselines by 17.53% and unsupervised methods by 24.25%; we boast a 79% model size reduction while maintaining comparable performance to the best supervised method. For outdoors (KITTI), we tie for 5th overall on the benchmark despite not using ground truth. Code available at: https://github.com/alexklwong/mondi-python.

Finding professors in machine learning and climate change is difficult, because they are spread across various departments and research a wide breadth of optics. Whether you're applying for graduate school, look for collaborators, or inspiring projects - this list is intended to get you started by finding the right people. This is a safe, open, and inclusive community. The list is most surely incomplete, so please add your favorite professors through commenting in an issue or creating a pull request. Students in CCML include Vincent Meijer.

Remote working environments and social distancing have caused people to become more comfortable with technology and developing employment relationships remotely, rather than face-to-face. Bringing artificial intelligence (AI) into the equation can add an additional layer of complexity and potential pitfalls to the human resources industry. In this webinar, Lee Moylan and Widener University Delaware School of Law law student Kamia McDaniels will explore AI and the algorithms behind it, the applications of AI in the hiring process and the pros and cons of utilizing it -- particularly, its impacts on diversity. This complimentary program will qualify for 1 hour of PA CLE ethics credit.* Please register here to access this Zoom webinar.

The School of Engineering has announced that MIT has granted tenure to 14 members of its faculty in the departments of Biological Engineering, Civil and Environmental Engineering, Electrical Engineering and Computer Science (which reports jointly to the School of Engineering and MIT Schwarzman College of Computing), Materials Science and Engineering, and Mechanical Engineering. "I am truly amazed by our newest cohort of tenured faculty," says Anantha Chandrakasan, dean of the School of Engineering and the Vannevar Bush Professor of Electrical Engineering and Computer Science. "They are a diverse group of educators and scholars whose research and commitment to teaching has had a tremendous impact on our community, in the classroom, as well as in the lab." This year's newly tenured associate professors are: Guy Bresler, an associate professor of electrical engineering and computer science, conducts research at the interface of information theory, statistics, theoretical computer science, and probability. His work aims to understand the fundamental interplay between information properties, computational complexity, and combinatorial structure in modern statistical inference problems.

If you've ever used a text-based artificial-intelligence image generator like Craiyon or DALL-E, you know with a few word prompts that the AI tools create images that are both realistic and completely synthesized. The machine learning that powers such websites will scan millions of images on the internet, analyze them and assemble facets of them into fresh, but fake, images. Now, University of Kansas researchers are working to use a similar machine-learning process to build new proteins designed to detect water pollutants. With a new three-year, $1.5 million grant from the National Science Foundation's Molecular Foundations for Biotechnology program, a KU researcher will use machine learning to create "deep-fake" membrane beta-barrel proteins -- a class of naturally successful biosensors -- designed to detect polluting metal ions in water. "These beta barrels are super useful because they can bring things across membranes," said principal investigator Joanna Slusky, associate professor of molecular biosciences at KU. "Barrels make good enzymes -- there are so many different things that barrels can do."

We often hear of the dark side of artificial intelligence (AI), how it will plunge us into a dystopian world of lost privacy and bad automated decisions, culminating in the robots killing us all. Professor Orly Lobel's The Equality Machine: Harnessing Digital Technology for a Brighter, More Inclusive Future (Public Affairs, October 2022) offers a very different view – one of optimism. Orly's book is an exuberant and insightful account of the bright side of AI and related digital technologies. Her book is filled with fascinating facts and engaging stories. Orly Lobel is the Warren Distinguished Professor of Law; University Professor; and Director, Center for Employment and Labor Policy at the U.C. San Diego School of Law.