Title
Topic
-
‘Multilingual Simplification of Medical Texts’
“Automated text simplification aims to produce simple versions of complex texts. This task is especially useful in the medical domain, where the latest medical findings are typically communicated via complex and technical articles. This creates barriers for laypeople seeking access to up-to-date medical findings, consequently impeding progress on health literacy. … This work addresses this limitation via multilingual simplification, i.e., directly simplifying complex texts into simplified texts in multiple languages. We introduce MultiCochrane, the first sentence-aligned multilingual text simplification dataset for the medical domain in four languages: English, Spanish, French, and Farsi.” Find the paper and full list of authors…
-
‘Appraising the Potential Uses and Harms of LLMs for Medical Systematic Reviews’
“Medical systematic reviews are crucial for informing clinical decision making and healthcare policy. But producing such reviews is onerous and time-consuming. Thus, high-quality evidence synopses are not available for many questions and may be outdated even when they are available. Large language models (LLMs) are now capable of generating long-form texts, suggesting the tantalizing possibility of automatically generating literature reviews on demand. However, LLMs sometimes generate inaccurate (and potentially misleading) texts by hallucinating or omitting important information. … [Here], we seek to qualitatively characterize the potential utility and risks of LLMs.” Find the paper and full list of authors at ArXiv.
-
‘USB: A Unified Summarization Benchmark Across Tasks and Domains’
“An abundance of datasets exist for training and evaluating models on the task of summary generation. However, these datasets are often derived heuristically, and lack sufficient annotations to support research into all aspects of summarization. … We introduce a benchmark comprising 8 tasks that require multi-dimensional understanding of summarization, e.g., surfacing evidence for a summary, assessing its correctness, and gauging its relevance to different topics. We compare various methods on this benchmark and discover that on multiple tasks, moderately-sized fine-tuned models consistently outperform much larger few-shot prompted language models.” Find the paper and the full list of authors at ArXiv.
-
‘Automated Metrics for Medical Multi-Document Summarization Disagree with Human Evaluations’
“Evaluating multi-document summarization (MDS) quality is difficult. This is especially true in the case of MDS for biomedical literature reviews, where models must synthesize contradicting evidence reported across different documents. … We introduce a dataset of human-assessed summary quality facets and pairwise preferences to encourage and support the development of better automated evaluation methods for literature review MDS. We take advantage of community submissions to the Multi-document Summarization for Literature Review (MSLR) shared task to compile a diverse and representative sample of generated summaries.” Find the paper and the full list of authors at ArXiv.
-
‘Evaluating the Zero-Shot Robustness of Instruction-tuned Language Models’
“Instruction fine-tuning has recently emerged as a promising approach for improving the zero-shot capabilities of Large Language Models (LLMs) on new tasks. This technique has shown particular strength in improving the performance of modestly sized LLMs, sometimes inducing performance competitive with much larger model variants. In this paper we ask two questions: (1) How sensitive are instruction-tuned models to the particular phrasings of instructions, and, (2) How can we make them more robust to such natural language variation?” Find the paper and the full list of authors at ArXiv.
-
‘On Robot Grasp Learning Using Equivariant Models’
“Real-world grasp detection is challenging due to the stochasticity in grasp dynamics and the noise in hardware. Ideally, the system would adapt to the real world by training directly on physical systems. However, this is generally difficult due to the large amount of training data required by most grasp learning models. In this paper, we note that the planar grasp function is $\SE(2)$-equivariant and demonstrate that this structure can be used to constrain the neural network used during learning.” Find the paper and the full list of authors at ArXiv.
-
‘Probabilistic Symmetry for Multi-Agent Dynamics’
“Learning multi-agent dynamics is a core AI problem with broad applications in robotics and autonomous driving. While most existing works focus on deterministic prediction, producing probabilistic forecasts to quantify uncertainty and assess risks is critical for downstream decision-making tasks. … By leveraging symmetry, specifically rotation equivariance, we can improve not only the prediction accuracy but also uncertainty calibration. We introduce Energy Score, a proper scoring rule, to evaluate probabilistic predictions. We propose a novel deep dynamics model, Probabilistic Equivariant Continuous COnvolution (PECCO) for probabilistic prediction of multi-agent trajectories.” Find the paper and full list of authors in Proceedings of Machine Learning…
-
‘One-shot Imitation Learning via Interaction Warping’
“Imitation learning of robot policies from few demonstrations is crucial in open-ended applications. We propose a new method, Interaction Warping, for learning SE(3) robotic manipulation policies from a single demonstration. We infer the 3D mesh of each object in the environment using shape warping. … Then, we represent manipulation actions as keypoints on objects. … We show successful one-shot imitation learning on three simulated and real-world object re-arrangement tasks. We also demonstrate the ability of our method to predict object meshes and robot grasps in the wild.” Find the paper and the full list of authors at ArXiv.
-
‘Topology-Enhanced Mechanical Stability of Swelling Nanoporous Electrodes’
“Materials like silicon and germanium offer a 10-fold improvement in charge capacity over conventional graphite anodes in lithium-ion batteries but experience a roughly threefold volume increase during lithiation, which challenges ensuring battery integrity. Nanoporous silicon, created by liquid-metal-dealloying, is a potentially attractive anode design to mitigate this challenge, exhibiting both higher capacity and extended cycle lifetimes. However, how nanoporous structures accommodate the large volume change is unknown. Here, we address this question by using phase-field modeling to produce nanoporous particles and to investigate their elastoplastic swelling behavior and fracture.” Find the paper and full list of authors at NPJ Computational Materials.
-
‘Multi-Modal Interactive Perception in Human Control of Complex Objects’
“Tactile sensing has been increasingly utilized in robot control of unknown objects to infer physical properties and optimize manipulation. However, there is limited understanding about the contribution of different sensory modalities … in robots and in humans. This study investigated the effect of visual and haptic information on humans’ exploratory interactions with a ‘cup of coffee,’ an object with nonlinear internal dynamics. … The results highlight how visual and haptic information regarding nonlinear internal dynamics have distinct roles for the interactive perception of complex objects.” Find the paper and full list of authors in the International Conference on Robotics and…
-
‘Indistinguishable Telecom Band Photons From a Single Erbium Ion in the Solid State’
“Atomic defects in the solid state are a key component of quantum repeater networks for long-distance quantum communication. Recently, there has been significant interest in rare earth ions, in particular Er3+ for its telecom-band optical transition, but their application has been hampered by optical spectral diffusion precluding indistinguishable single photon generation. In this work we implant Er3+ into CaWO4, a material that combines a non-polar site symmetry, low decoherence from nuclear spins, and is free of background rare earth ions, to realize significantly reduced optical spectral diffusion.” Find the paper and the full list of authors at ArXiv.
-
‘SHAI 2023: Workshop on Designing for Safety in Human-AI Interactions’
“Generative ML models present a novel opportunity for a wider group of societal members to engage with AI, imagine new use cases, and applications. … However, owing to the novelty and despite best intentions, inadvertent outcomes might accrue leading to harms, especially to marginalized groups in society. …. Our workshop is aimed at such practitioners and researchers at the intersection of AI and HCI who are interested in collaboratively identifying challenges and solutions to create safer outcomes with Generative ML models.” Find the paper and full list of authors in the Companion Proceedings of the 28th International Conference on Intelligent…
-
‘Exploring the Use of Personalized AI for Identifying Misinformation on Social Media’
“This work aims to explore how human assessments and AI predictions can … identify misinformation on social media. To do so, we design a personalized AI which iteratively takes as training data a single user’s assessment of content and predicts how the same user would assess other content. We conduct a user study in which participants interact with a personalized AI that learns their assessments of a feed of tweets, shows its predictions of whether a user would find other tweets (in)accurate, and evolves according to the user feedback.” Find the paper and list of authors in the 2023 CHI…
-
‘Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language Explanations’
“Human-annotated labels and explanations are critical for training explainable NLP models. However, … human-crafted free-form explanations can be quite subjective. Before blindly using them as ground truth to train ML models, a vital question needs to be asked: How do we evaluate a human-annotated explanation’s quality? In this paper, we build on the view that the quality of a human-annotated explanation can be measured based on its helpfulness (or impairment) to the ML models’ performance for the desired NLP tasks for which the annotations were collected.” Find the paper and the full list of authors at ArXiv.
-
‘Beyond Labels: Empowering Human with Natural Language Explanations through a Novel Active-Learning Architecture’
“Data annotation is a costly task; thus, researchers have proposed low-scenario learning techniques like Active-Learning (AL) to support human annotators; Yet, existing AL works focus only on the label, but overlook the natural language explanation of a data point, despite that real-world humans (e.g., doctors) often need both the labels and the corresponding explanations at the same time. This work proposes a novel AL architecture to support and reduce human annotations of both labels and explanations in low-resource scenarios.” Find the paper and the full list of authors at ArXiv.
-
‘Are Fairy Tales Fair? Analyzing Gender Bias in Temporal Narrative Event Chains of Children’s Fairy Tales’
“Social biases and stereotypes are embedded in our culture in part through their presence in our stories, as evidenced by the rich history of humanities and social science literature analyzing such biases in children stories. … Such investigations can benefit from the use of more recent natural language processing methods that examine social bias in models and data corpora. … We propose a computational pipeline that automatically extracts a story’s temporal narrative verb-based event chain for each of its characters as well as character attributes such as gender.” Find the paper and the full list of authors at ArXiv.
-
‘Identification of Negative Transfers in Multitask Learning Using Surrogate Models’
“Multitask learning is widely used in practice to train a low-resource target task by augmenting it with multiple related source tasks. Yet, naively combining all the source tasks with a target task does not always improve the prediction performance for the target task due to negative transfers. Thus, a critical problem in multitask learning is identifying subsets of source tasks that would benefit the target task. … In this paper, we introduce an efficient procedure to address this problem via surrogate modeling.” Find the paper and the full list of authors at ArXiv.
-
‘Optimal Intervention on Weighted Networks via Edge Centrality’
“Suppose there is a spreading process such as an infectious disease propagating on a graph. How would we reduce the number of affected nodes in the spreading process? … A practical algorithm to reduce infections on unweighted graphs is to remove edges with the highest edge centrality score (Tong et al. (2012)), which is the product of two adjacent nodes’ eigenscores. However, mobility networks have weighted edges. … We revisit the problem of minimizing top eigenvalue(s) on weighted graphs by decreasing edge weights up to a fixed budget.” Find the paper and the full list of authors at ArXiv.
-
‘Understanding Dark Patterns in Home IoT Devices’
“Internet-of-Things (IoT) devices are ubiquitous, but little attention has been paid to how they may incorporate dark patterns despite consumer protections and privacy concerns arising from their unique access to intimate spaces and always-on capabilities. … We update manual interaction and annotation methods for the IoT context, then analyze dark pattern frequency across device types, manufacturers, and interaction modalities. We find that dark patterns are pervasive in IoT experiences, but manifest in diverse ways across device traits.” Find the paper and the full list of authors in the Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems.
-
‘Somewhere Randomness Extraction and Security Against Bounded-Storage Mass Surveillance’
“Consider a state-level adversary who observes and stores large amounts of encrypted data from all users on the Internet, but does not have the capacity to store it all. Later, it may target certain ‘persons of interest.’ … We would like to guarantee that, if the adversary’s storage capacity is only (say) 1% of the total encrypted data size, then even if it can later obtain the decryption keys of arbitrary users, it can only learn something about the contents of (roughly) 1% of the ciphertexts.” Find the paper and the full list of authors in the Cryptology EPrint Archive.
-
‘A Map of Witness Maps: New Definitions and Connections’
“A witness map deterministically maps a witness w of some NP statement x into computationally sound proof that x is true. … A unique witness map (UWM) ensures that for any fixed statement x, the witness map should output the same unique proof for x, no matter what witness w it is applied to. … In this work, we study [compact witness maps] and UWMs as primitives of independent interest and present a number of interesting connections to various notions in cryptography.” Find the paper and the full list of authors in the Cryptology EPrint Archive.
-
‘Boosting Batch Arguments and RAM Delegation’
“We show how to generically improve the succinctness of non-interactive publicly verifiable batch argument (BARG) systems. In particular, we show (under a mild additional assumption) how to convert a BARG that generates proofs of length poly (m)· k1−є, where m is the length of a single instance and k is the number of instances being batched, into one that generates proofs of length poly (m, logk), which is the gold standard for succinctness of BARGs.” Find the paper and the full list of authors in the Proceedings of the 55th Annual ACM Symposium on Theory of Computing.
-
‘Doubly Efficient Private Information Retrieval and Fully Homomorphic RAM Computation From Ring LWE’
“A (single server) private information retrieval (PIR) allows a client to read data from a public database held on a remote server, without revealing to the server which locations she is reading. In a doubly efficient PIR (DEPIR), the database is first preprocessed, but the server can subsequently answer any client’s query in time that is sub-linear in the database size. … In this work we construct the stronger unkeyed notion of DEPIR, where the preprocessing is a deterministic procedure that the server can execute on its own.” Find the paper and full list of authors in the STOC 2023 proceedings.
-
‘Identification of Novel Anti-Amoebic Pharmacophores From Kinase Inhibitor Chemotypes’
“Acanthamoeba species, Naegleria fowleri, and Balamuthia mandrillaris are opportunistic pathogens that cause a range of brain, skin, eye, and disseminated diseases in humans and animals. These pathogenic free-living amoebae (pFLA) are commonly misdiagnosed and have sub-optimal treatment regimens which contribute to the extremely high mortality rates (>90%) when they infect the central nervous system. … Herein, we report the activity of the compounds against the trophozoite stage of each of the three amoebae, ranging from nanomolar to low micromolar potency.” Find the paper and the full list of authors at Frontiers in Microbiology.
-
‘Exploratory Thematic Analysis of Crowdsourced Photosensitivity Warnings’
“Films often include sequences of flashing lights for visual effect that may inadvertently trigger seizures when viewed by individuals with photosensitive epilepsy (PSE). Warnings about photosensitive risk in films can help people with PSE make informed decisions about their personal safety, but little is known about how to design such warnings and what information to include. To better understand the design space for photosensitive risk warnings, we conducted a qualitative analysis of 265 crowdsourced warnings about flashing lights in films.” Find the paper and the full list of authors at Conference on Human Factors in Computing Systems 2023 proceedings.
-
‘Is “Categorical Imperative” Metaversal?: A Kantian Ethical Framework for Social Virtual Reality’
“The increasing adoption of social virtual reality (VR) environments for socializing and collaborating with others has led to a growing concern about ethical issues in these immersive environments. Beyond the introduction of some practical guidelines, theoretical work on this topic has been scant. In this paper, we propose an ethical framework for social VR based on Kant’s Theory of Morality. In so doing, we argue that the Kantian concept of categorical imperative does apply to social VR.” Find the paper and the full list of authors in the Conference on Human Factors in Computing Systems 2023 proceedings.
-
‘Noise Stability Optimization for Flat Minima With Optimal Convergence Rates’
“We consider finding flat, local minimizers by adding average weight perturbations. Given a nonconvex function f:ℝd→ℝ and a d-dimensional distribution P which is symmetric at zero, we perturb the weight of f and define F(W)=𝔼[f(W+U)], where U is a random sample from P. This injection induces regularization through the Hessian trace of f for small, isotropic Gaussian perturbations. … Still, convergence rates are not known for finding minima under the average perturbations of the function F. This paper considers an SGD-like algorithm that injects random noise before computing gradients while leveraging the symmetry of P to reduce variance.” Find the paper and the full list of authors at ArXiv.