Title
Topic
-
‘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.
-
‘Safe Deep Reinforcement Learning by Verifying Task-Level Properties’
“Cost functions are commonly employed in Safe Deep Reinforcement Learning (DRL). However, the cost is typically encoded as an indicator function due to the difficulty of quantifying the risk of policy decisions in the state space. Such an encoding requires the agent to visit numerous unsafe states to learn a cost-value function to drive the learning process toward safety. … In this paper, we investigate an alternative approach that uses domain knowledge to quantify the risk in the proximity of such states by defining a violation metric.” Read the paper and see the full list of authors in ArXiv.
-
Flood dangers rise as shipping channels deepen
Maqsood Mansur, graduate teaching assistant, assistant professor Julia Hopkins and professor Qin Jim Chen, have published a study investigating if “depth increase in a navigational channel in an estuarine region results in the amplification of the inland penetration of storm surge, thereby increasing the flood vulnerability,” concluding “that even the most conservative scenario of [sea-level rise] will cause an approximately 51% increase in flooded area in … the deepest ship channel.” Find “Estuarine Response to Storm Surge and Sea-Level Rise Associated with Channel Deepening: A Flood Vulnerability Assessment of Southwest Louisiana, USA” and the full list of authors in Natural…
-
‘Efficient Resilient Functions’
“An n-bit boolean function is resilient to coalitions of size q if no fixed set of q bits is likely to influence the value of the function when the other n — q bits are chosen uniformly at random, even though the function is nearly balanced. We construct explicit functions resilient to coalitions of size q = n/(log n)O(log log n) = n1-o(1) computable by linear-size circuits and linear-time algorithms. We also obtain a tight size-depth tradeoff for computing such resilient functions.” Read the paper and see the full list of authors at SIAM.
-
Innovations in printed electronics: Transistors in silicon
Professor of electrical and computer engineering Ravinder Dahiya, in collaboration with researchers from the University of Glasgow, has published research that advances electronic printing. Printing “high-performance and stable transistors … remains a major challenge. This is because of the difficulties to print high-mobility semiconducting materials and the lack of high-resolution printing techniques,” they write. Crucially, the researchers now propose “silicon based … transistors to demonstrate the possibility of developing high-performance complementary metal–oxide–semiconductor… computing architecture.” Read “Printed n- and p-Channel Transistors using Silicon Nanoribbons Enduring Electrical, Thermal, and Mechanical Stress” and see the full list of authors in ACS Publications.
-
‘NapSS: Paragraph-Level Medical Text Simplification via Narrative Prompting and Sentence-Matching Summarization’
“Accessing medical literature is difficult for laypeople as the content is written for specialists and contains medical jargon. Automated text simplification methods offer a potential means to address this issue. In this work, we propose a summarize-then-simplify two-stage strategy, which we call NapSS, identifying the relevant content to simplify while ensuring that the original narrative flow is preserved. In this approach, we first generate reference summaries via sentence matching between the original and the simplified abstracts.” Read the paper and see the full list of authors in ArXiv.
-
Patent for ultrasonic, underwater communication system
“Electrical and computer engineering assistant professor Francesco Restuccia, research assistant professor Emrecan Demirors and professor Tommaso Melodia were awarded a patent for “Underwater ultrasonic communication system and method.”
-
‘Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion’
“Graph neural networks are widely used tools for graph prediction tasks. Motivated by their empirical performance, prior works have developed generalization bounds for graph neural networks, which scale with graph structures in terms of the maximum degree. In this paper, we present generalization bounds that instead scale with the largest singular value of the graph neural network’s feature diffusion matrix.” Read the paper and see the full list of authors in ArXiv.
-
‘How Many and Which Training Points Would Need To Be Removed To Flip this Prediction?’
“We consider the problem of identifying a minimal subset of training data St such that if the instances comprising St had been removed prior to training, the categorization of a given test point xt would have been different. … We propose comparatively fast approximation methods to find St based on influence functions, and find that—for simple convex text classification models—these approaches can often successfully identify relatively small sets of training examples which, if removed, would flip the prediction.” Read the paper and see the full list of authors in ArXiv.
-
‘An Optimized Acidic Digestion for the Isolation of Microplastics From Biota-Rich Samples’
“Plastic pollution is a growing concern. To analyze plastics in environmental samples, plastics need to be isolated. We present an acidic/oxidative method optimized to preserve plastics while digesting synthetic cellulose acetate and a range of organics encountered in environmental samples.” Find the paper and the full list of authors in Environmental Pollution.
-
‘Generative Adversarial Symmetry Discovery’
“Despite the success of equivariant neural networks in scientific applications, they require knowing the symmetry group a priori. However, it may be difficult to know which symmetry to use as an inductive bias in practice. Enforcing the wrong symmetry could even hurt the performance. In this paper, we propose a framework, LieGAN, to automatically discover equivariances from a dataset using a paradigm akin to generative adversarial training.” Read the paper and see the full list of authors in ArXiv.
-
‘One-Shot Empirical Privacy Estimation for Federated Learning’
“Privacy estimation techniques for differentially private (DP) algorithms are useful for comparing against analytical bounds, or to empirically measure privacy loss in settings where known analytical bounds are not tight. … In this work, we present a novel “one-shot” approach that can systematically address these challenges, allowing efficient auditing or estimation of the privacy loss of a model during the same, single training run used to fit model parameters, and without requiring any a priori knowledge about the model architecture or task.” Read the paper and see the full list of authors in ArXiv.
-
Reasoning through the picture: Machine learning between words and images
Researchers have identified a new “cross-modal retrieval” method to operate between “language and vision domains.” From their abstract: “To address this issue, we introduce an intuitive and interpretable model to learn a common embedding space for alignments between images and text descriptions. Specifically, our model first incorporates the semantic relationship information into visual and textual features by performing region or word relationship reasoning.” Read “Image-Text Embedding Learning via Visual and Textual Semantic Reasoning” and see the full list of authors in the IEEE Transactions on Pattern Analysis and Machine Intelligence.
-
‘Dissociation Between Linguistic and Nonlinguistic Statistical Learning in Children With Autism’
“Statistical learning (SL), the ability to detect and extract regularities from inputs, is considered a domain-general building block for typical language development. We compared 55 verbal children with autism (ASD, 6–12 years) and 50 typically-developing children in four SL tasks. The ASD group exhibited reduced learning in the linguistic SL tasks (syllable and letter), but showed intact learning for the nonlinguistic SL tasks (tone and image).” Read the paper and see the full list of authors in the Journal of Autism and Developmental Disorders.
-
‘Backdoor Attacks in Peer-to-Peer Federated Learning’
“We study backdoor attacks in peer-to-peer federated learning systems on different graph topologies and datasets. We show that only 5% attacker nodes are sufficient to perform a backdoor attack with 42% attack success without decreasing the accuracy on clean data by more than 2%. We also demonstrate that the attack can be amplified by the attacker crashing a small number of nodes.” Read the paper and see the full list of authors in ArXiv.
-
‘Stochastic Minimum Vertex Cover in General Graphs: A 3/2-Approximation’
“Our main result is designing an algorithm that returns a vertex cover of G* with size at most (3/2+ϵ) times the expected size of the minimum vertex cover, using only O(n/ϵp) non-adaptive queries. This improves over the best-known 2-approximation algorithm by Behnezhad, Blum, and Derakhshan [SODA’22], who also show that Ω(n/p) queries are necessary to achieve any constant approximation.” Read the paper and see the full list of authors in ArXiv.
-
‘A Closed-Form Solution of the Smoke Filling Time and Descent History in Enclosure Growing Fires With Floor Leaks’
“For the smoke filling time or smoke descent history in enclosure fires with floor leaks, the existing close-formed solutions are all based on the hypothesis that the expansion term is negligible. However, when the smoke interface is near to the floor level, the expansion term is more important than the plume entrainment term and the existing solutions give unrealistic predictions.” Read the paper and see the full list of authors in Fire Technology.
-
‘From Robustness to Privacy and Back’
“We study the relationship between two desiderata of algorithms in statistical inference and machine learning: differential privacy and robustness to adversarial data corruptions. … Dwork and Lei (STOC 2009) … observed that private algorithms satisfy robustness, and gave a general method for converting robust algorithms to private ones. However, all general methods for transforming robust algorithms into private ones lead to suboptimal error rates. Our work gives the first black-box transformation that converts any adversarially robust algorithm into one that satisfies pure differential privacy.” Read the paper and see the full list of authors in ArXiv.
-
‘Effects of Inhaled Cannabis High in Δ9-THC or CBD on the Aging Brain: A Translational MRI and Behavioral Study’
“To understand the neurobiological effects of cannabis on the aging brain, 19–20 months old mice were divided into three groups exposed to vaporized cannabis containing. … Voxel based morphometry, diffusion weighted imaging, and resting state functional connectivity data were gathered after 28 days of exposure and following a two-week washout period. … Chronic inhaled CBD resulted in enhanced global network connectivity that persisted after drug cessation. The behavioral consequences of this sustained change in brain connectivity remain to be determined.” Read the paper and see the full list of authors in Frontiers in Aging Neuroscience.
-
Reframing disability as ‘a property of both humans and machines’
Laura Forlano, professor of art and design and communication studies, has a new article titled “Living Intimately with Machines: Can AI Be Disabled?” Forlano proposes to take seriously the idea that we can “understand disability to be a property of both humans and machines.”
-
‘Do Multi-Document Summarization Models Synthesize?’
“Multi-document summarization entails producing concise synopses of collections of inputs. For some applications, the synopsis should accurately synthesize inputs with respect to a key property or aspect. … In this paper we ask: To what extent do modern multi-document summarization models implicitly perform this type of synthesis? To assess this we perform a suite of experiments that probe the degree to which conditional generation models trained for summarization using standard methods yield outputs that appropriately synthesize inputs.” Read the paper and see the full list of authors in ArXiv.
-
Foregrounding care in the co-creation of urban spaces: How to find ‘liveable urban futures’
This article asks, “Can participatory engagements in the form of more-than-human co-creation be a generative form of socially and ecologically-just and critical urban placemaking?” It goes on to explore “three interrelated examples of critical urban placemaking in the arts, interrogating how we might design for liveable urban futures as matters of care.” In foregrounding care, the authors explore “co-creation” practices that are “responsive and dynamic rather than prescriptive… [and that] “can transform the status quo, rather than merely reproduce it.” Read “Care-full co-curation: critical urban placemaking for more-than-human futures” and see the full list of authors in City: Analysis of Urban Change,…
-
‘Explaining Dataset Changes for Semantic Data Versioning with Explain-Da-V (Technical Report)’
“In multi-user environments in which data science and analysis is collaborative, multiple versions of the same datasets are generated. While managing and storing data versions has received some attention in the research literature, the semantic nature of such changes has remained under-explored. In this work, we introduce \texttt{Explain-Da-V}, a framework aiming to explain changes between two given dataset versions.” Read the paper and see the full list of authors in ArXiv.
-
‘Thought Bubbles: A Proxy into Players’ Mental Model Development’
“Studying mental models has recently received more attention, aiming to understand the cognitive aspects of human-computer interaction. However, there is not enough research on the elicitation of mental models in complex dynamic systems. We present Thought Bubbles as an approach for eliciting mental models and an avenue for understanding players’ mental model development in interactive virtual environments.” Read the paper and see the full list of authors at ArXiv.
-
‘A Bias-Variance-Privacy Trilemma for Statistical Estimation’
“The canonical algorithm for differentially private mean estimation is to first clip the samples to a bounded range and then add noise to their empirical mean. Clipping controls the sensitivity and, hence, the variance of the noise that we add for privacy. But clipping also introduces statistical bias. We prove that this tradeoff is inherent: no algorithm can simultaneously have low bias, low variance, and low privacy loss for arbitrary distributions.” Read the paper and see the full list of authors in ArXiv.
-
‘Making Reconstruction-Based Method Great Again for Video Anomaly Detection’
“Anomaly detection in videos is a significant yet challenging problem. Previous approaches based on deep neural networks employ either reconstruction-based or prediction-based approaches. … existing reconstruction-based methods 1) rely on old-fashioned convolutional autoencoders and are poor at modeling temporal dependency; 2) are prone to overfit the training samples, leading to indistinguishable reconstruction errors. … To address such issues, firstly, we get inspiration from transformer and propose Spatio-Temporal Auto-Trans-Encoder, dubbed as STATE, as a new autoencoder model for enhanced consecutive frame reconstruction.” Find the paper and the full list of authors in ArXiv.