Title
Topic
-
‘A General Theory of Correct, Incorrect and Extrinsic Equivariance’
“Although equivariant machine learning has proven effective at many tasks, success depends heavily on the assumption that the ground truth function is symmetric over the entire domain matching the symmetry in an equivariant neural network. A missing piece in the equivariant learning literature is the analysis of equivariant networks when symmetry exists only partially in the domain. … We propose pointwise definitions of correct, incorrect, and extrinsic equivariance, which allow us to quantify continuously the degree of each type of equivariance a function displays.” Read the paper and see the full list of authors in ArXiv.
-
‘Automatically Summarizing Evidence From Clinical Trials: A Prototype Highlighting Current Challenges’
“We present TrialsSummarizer, a system that aims to automatically summarize evidence presented in the set of randomized controlled trials most relevant to a given query. Building on prior work, the system retrieves trial publications matching a query specifying a combination of condition, intervention(s), and outcome(s), and ranks these according to sample size and estimated study quality.” Read the paper and see the full list of authors in ArXiv.
-
‘Model Sketching: Centering Concepts in Early-Stage Machine Learning Model Design’
“Machine learning practitioners often end up tunneling on low-level technical details like model architectures and performance metrics. Could early model development instead focus on high-level questions of which factors a model ought to pay attention to? Inspired by the practice of sketching in design, which distills ideas to their minimal representation, we introduce model sketching: a technical framework for iteratively and rapidly authoring functional approximations of a machine learning model’s decision-making logic.” Read the paper and see the full list of authors in ArXiv.
-
‘Ungrading With Empathy: An Experiment in Ungrading for Intermediate Data Science’
“We implemented a model for grading weekly assignments in an intermediate data science course that explicitly gave students useful feedback on their code while not evaluating it on the traditional metrics of correctness or style. … Our ungrading policy was designed to extend empathy towards students and to give them useful, actionable feedback. Our policy reduced the stress that students felt each week, stabilized the amount of time they spent on assignments, and ask them to reflect on their code to request feedback from the teaching team.” Find the paper and the full list of authors in the SIGCSE 2023…
-
‘WADER at SemEval-2023 Task 9: A Weak-Labelling Framework for Data Augmentation in Text Regression Tasks’
“Intimacy is an essential element of human relationships and language is a crucial means of conveying it. Textual intimacy analysis can reveal social norms in different contexts and serve as a benchmark for testing computational models’ ability to understand social information. In this paper, we propose a novel weak-labeling strategy for data augmentation in text regression tasks called WADER.” Read the paper and see the full list of authors in ArXiv.
-
‘Online Paging With Heterogeneous Cache Slots’
“It is natural to generalize the online k-Server problem by allowing each request to specify not only a point p, but also a subset S of servers that may serve it. … We focus on uniform and star metrics. For uniform metrics, the problem is equivalent to a generalization of Paging in which each request specifies not only a page p, but also a subset S of cache slots, and is satisfied by having a copy of p in some slot in S.” Read the paper and see the full list of authors in the Dagstuhl Research Online Publication Server.
-
‘A Flexible Formative/Summative Grading System for Large Courses’
“We designed a formative/summative grading system in our CS0 and CS1 classes for both on-campus and online students to support a structured growth mindset. Students can redo formative assignments and are provided flexible deadlines. They demonstrate their mastery in summative assignments. While being inspired by other grading systems, our system works seamlessly with auto-grading tools used in large, structured courses. … These students went to the traditional follow-on CS2 course and 94% passed compared with 71% who took CS1 with a traditional grading system.” Read the paper and see the full list of authors in the proceedings of SIGCSE 2023.
-
‘Teaching Assistant Training: An Adjustable Curriculum for Computing Disciplines’
“We present an adaptable curriculum for training undergraduate and graduate teaching assistants (TAs) in computing disciplines that is modular, synchronous, and explicitly mirrors the teaching techniques that are used in our classes. Our curriculum is modular, with each component able to be expanded or compressed based on institutional needs and resources. It is appropriate for TAs from CS1 through advanced computing classes.” Read the paper and see the full list of authors in the proceedings of SIGCSE 2023.
-
‘Image as Set of Points’
“Convolutional Networks (ConvNets) consider an image as organized pixels in a rectangular shape and extract features via convolutional operation in local region; Vision Transformers (ViTs) treat an image as a sequence of patches and extract features via attention mechanism in a global range. In this work, we introduce a straightforward and promising paradigm for visual representation, which is called Context Clusters. Context clusters (CoCs) view an image as a set of unorganized points and extract features via simplified clustering algorithm.” Read the paper and see the full list of authors in ArXiv.
-
‘Multi-Objective Optimization of Custom Compound Prism Arrays for Multiplexed Optical Imaging’
“Compound prism arrays are a powerful, yet underutilized, solution for producing high transmission and customized chromatic dispersion profiles over broad bandwidths, the quality of which is unobtainable with commercially available prisms or diffraction gratings. However, the computational complexity associated with designing these prism arrays presents a barrier to the widespread adoption of their use. Here we introduce customizable prism designer software that facilitates high-speed optimization of compound arrays guided by target specifications for chromatic dispersion linearity and detector geometry.” Read the paper and see the full list of authors in Optics Express.
-
Odom lays out a ‘Road Map To Organizational Resilience’
Associate professor of management Curtis Odom has written “The Road Map To Organizational Resilience.” Some of the tenets he lays out include: soliciting “feedback from employees,” conducting “operational reviews,” and designing “continuous improvement initiatives, among others.
-
Fang receives patent for non-invasive brain imaging probe
“A flexible head probe and modular head probe system that includes an optical functional near-infrared spectroscopy (fNIRS) system and integrated position sensor. The head probe and modular head probe system determines physiological data based upon the optical information gathered by the fNIRS system and gathers motion and position data from the position sensor. The physiological data and motion and position data are combined to permit topographical and tomographic analyses of a user’s brain tissue.”
-
‘Co-Encapsulation of Drugs for Topical Application—A Review’
“Achieving the best possible outcome for the therapy is the main goal of a medicine. Therefore, nanocarriers and co-delivery strategies were invented to meet this need, as they can benefit many diseases. This approach was applied specifically for cancer treatment, with some success.” Read “Co-Encapsulation of Drugs for Topical Application—A Review” and see the full list of authors in Molecules.
-
‘High Probability Convergence of Stochastic Gradient Methods’
“In this work, we describe a generic approach to show convergence with high probability for both stochastic convex and non-convex optimization with sub-Gaussian noise. In previous works for convex optimization, either the convergence is only in expectation or the bound depends on the diameter of the domain. Instead, we show high probability convergence with bounds depending on the initial distance to the optimal solution. The algorithms use step sizes analogous to the standard settings and are universal to Lipschitz functions, smooth functions, and their linear combinations.” Read the paper and see the full list of authors in ArXiv.
-
‘Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction’
“Predicting the pose of objects from a single image is an important but difficult computer vision problem. Methods that predict a single point estimate do not predict the pose of objects with symmetries well and cannot represent uncertainty. Alternatively, some works predict a distribution over orientations in SO(3). However, training such models can be computation- and sample-inefficient. Instead, we propose a novel mapping of features from the image domain to the 3D rotation manifold. ” Read the paper and see the full list of authors in ArXiv.
-
Advances in ‘multimaterial 3D printers’
In the effort to create “multimaterial 3D printers,” the printers often only “allow printing of one material at a time, with limited ability of mixing multiple materials.” In this paper, researchers describe a “new 3D printer which eliminates the above shortcoming by merging the Fused Filament Fabrication and Direct Ink Write in one compact system.” Read “Closed-loop direct ink extruder system with multi-part materials mixing” and see the full list of authors in Additive Manufacturing.
-
‘SantaCoder: Don’t Reach for the Stars!
“The BigCode project is an open-scientific collaboration working on the responsible development of large language models for code. This tech report describes the progress of the collaboration until December 2022, outlining the current state of the Personally Identifiable Information (PII) redaction pipeline, the experiments conducted to de-risk the model architecture, and the experiments investigating better preprocessing methods for the training data. … We find that more aggressive filtering of near-duplicates can further boost performance and, surprisingly, that selecting files from repositories with 5+ GitHub stars deteriorates performance significantly.” Find the paper and the full list of authors at ArXiv.
-
‘Do Machine Learning Models Produce TypeScript Types that Type Check?’
“Type migration is the process of adding types to untyped code to gain assurance at compile time. TypeScript and other gradual type systems facilitate type migration by allowing programmers to start with imprecise types and gradually strengthen them. … Existing machine learning models report a high degree of accuracy in predicting individual TypeScript type annotations. However, in this paper we argue that accuracy can be misleading, and we should address a different question: can an automatic type migration tool produce code that passes the TypeScript type checker?” Read the paper and see the full list of authors in ArXiv.
-
‘CHiLL: Zero-Shot Custom Interpretable Feature Extraction From Clinical Notes With Large Language Models’
“Large Language Models (LLMs) have yielded fast and dramatic progress in NLP, and now offer strong few- and zero-shot capabilities on new tasks, reducing the need for annotation. This is especially exciting for the medical domain, in which supervision is often scant and expensive. At the same time, model predictions are rarely so accurate that they can be trusted blindly. … We propose CHiLL (Crafting High-Level Latents), which uses LLMs to permit natural language specification of high-level features for linear models via zero-shot feature extraction using expert-composed queries.” Find the paper and the full list of authors in ArXiv.
-
‘Certifiably Correct Range-Aided SLAM’
“We present the first algorithm capable of efficiently computing certifiably optimal solutions to range-aided simultaneous localization and mapping (RA-SLAM) problems. Robotic navigation systems are increasingly incorporating point-to-point ranging sensors, leading state estimation which takes the form of RA-SLAM. However, the RA-SLAM problem is more difficult to solve than traditional pose-graph SLAM … a single range measurement does not uniquely determine the relative transform between the involved sensors, and RA-SLAM inference is highly sensitive to initial estimates.” Read the paper and see the full list of authors in ArXiv.
-
‘Why is the State of Neural Network Pruning so Confusing?’
“The state of neural network pruning has been noticed to be unclear and even confusing for a while, largely due to ‘a lack of standardized benchmarks and metrics.’ To standardize benchmarks, first, we need to answer: what kind of comparison setup is considered fair? … Meanwhile, we observe several papers have used (severely) sub-optimal hyper-parameters in pruning experiments, while the reason behind them is also elusive. These sub-optimal hyper-parameters further exacerbate the distorted benchmarks, rendering the state of neural network pruning even more obscure.” Read the paper and see the full list of authors in ArXiv.
-
‘Adaptive Test Generation Using a Large Language Model’
“Unit tests play a key role in ensuring the correctness of software. However, manually creating unit tests is a laborious task, motivating the need for automation. This paper presents TestPilot, an adaptive test generation technique that leverages Large Language Models (LLMs). TestPilot uses Codex, an off-the-shelf LLM, to automatically generate unit tests for a given program without requiring additional training or few-shot learning on examples of existing tests.” Read the paper and see the full list of authors in ArXiv.
-
‘Improving Deep Policy Gradients With Value Function Search’
“Deep Policy Gradient (PG) algorithms employ value networks to drive the learning of parameterized policies and reduce the variance of the gradient estimates. However, value function approximation gets stuck in local optima and struggles to fit the actual return, limiting the variance reduction efficacy and leading policies to sub-optimal performance. This paper focuses on improving value approximation and analyzing the effects on Deep PG primitives such as value prediction, variance reduction, and correlation of gradient estimates with the true gradient.” Read the paper and see the full list of authors in ArXiv.