Search

Metal-organic frameworks (MOFs) are a class of crystalline materials with promising applications in many areas such as carbon capture and drug delivery. In this work, we introduce MOFFlow, the first deep generative model tailored for MOF structure prediction. Existing approaches, including ab initio calculations and even deep generative models, struggle with the complexity of MOF structures due to the large number of atoms in the unit cells. To address this limitation, we propose a novel Riemannian flow matching framework that reduces the dimensionality of the problem by treating the metal nodes and organic linkers as rigid bodies, capitalizing on the inherent modularity of MOFs. By operating in the $SE(3)$ space, MOFFlow effectively captures the roto-translational dynamics of these rigid components in a scalable way. Our experiment demonstrates that MOFFlow accurately predicts MOF structures containing several hundred atoms, significantly outperforming conventional methods and state-of-the-art machine learning baselines while being much faster., Comment: 10 pages, 6 figures

Antibody design plays a pivotal role in advancing therapeutics. Although deep learning has made rapid progress in this field, existing methods jointly generate antibody sequences and structures, limiting task-specific optimization. In response, we propose an antibody sequence-structure decoupling (ASSD) framework, which separates sequence generation and structure prediction. Although our approach is simple, such a decoupling strategy has been overlooked in previous works. We also find that the widely used non-autoregressive generators promote sequences with overly repeating tokens. Such sequences are both out-of-distribution and prone to undesirable developability properties that can trigger harmful immune responses in patients. To resolve this, we introduce a composition-based objective that allows an efficient trade-off between high performance and low token repetition. Our results demonstrate that ASSD consistently outperforms existing antibody design models, while the composition-based objective successfully mitigates token repetition of non-autoregressive models. Our code is available at \url{https://github.com/lkny123/ASSD_public}., Comment: 18 pages, 6 figures

Designing for AI trustworthiness is challenging, with a lack of practical guidance despite extensive literature on trust. The Multisource AI Scorecard Table (MAST), a checklist rating system, addresses this gap in designing and evaluating AI-enabled decision support systems. We propose the Principled Approach for Designing Trustable Human-centered AI systems using MAST Methodology (PADTHAI-MM), a nine-step framework what we demonstrate through the iterative design of a text analysis platform called the REporting Assistant for Defense and Intelligence Tasks (READIT). We designed two versions of READIT, high-MAST including AI context and explanations, and low-MAST resembling a "black box" type system. Participant feedback and state-of-the-art AI knowledge was integrated in the design process, leading to a redesigned prototype tested by participants in an intelligence reporting task. Results show that MAST-guided design can improve trust perceptions, and that MAST criteria can be linked to performance, process, and purpose information, providing a practical and theory-informed basis for AI system design.

The abundance of social media data has presented opportunities for accurately determining public and group-specific stances around policy proposals or controversial topics. In contrast with sentiment analysis which focuses on identifying prevailing emotions, stance detection identifies precise positions (i.e., supportive, opposing, neutral) relative to a well-defined topic, such as perceptions toward specific global health interventions during the COVID-19 pandemic. Traditional stance detection models, while effective within their specific domain (e.g., attitudes towards masking protocols during COVID-19), often lag in performance when applied to new domains and topics due to changes in data distribution. This limitation is compounded by the scarcity of domain-specific, labeled datasets, which are expensive and labor-intensive to create. A solution we present in this paper combines counterfactual data augmentation with contrastive learning to enhance the robustness of stance detection across domains and topics of interest. We evaluate the performance of current state-of-the-art stance detection models, including a prompt-optimized large language model, relative to our proposed framework succinctly called STANCE-C3 (domain-adaptive Cross-target STANCE detection via Contrastive learning and Counterfactual generation). Empirical evaluations demonstrate STANCE-C3's consistent improvements over the baseline models with respect to accuracy across domains and varying focal topics. Despite the increasing prevalence of general-purpose models such as generative AI, specialized models such as STANCE-C3 provide utility in safety-critical domains wherein precision is highly valued, especially when a nuanced understanding of the concerns of different population segments could result in crafting more impactful public policies.

When a drop of a volatile liquid is deposited on a uniformly heated wettable, thermally conducting substrate, one expects to see it spread into a thin film and evaporate. Contrary to this intuition, due to thermal Marangoni contraction the deposited drop contracts into a spherical-cap-shaped puddle, with a finite apparent contact angle. Strikingly, this contracted droplet, above a threshold temperature, well below the boiling point of the liquid, starts to spontaneously move on the substrate in an apparently erratic way. We describe and quantify this self-propulsion of the volatile drop. It arises due to spontaneous symmetry breaking of thermal-Marangoni convection, which is induced by the non-uniform evaporation of the droplet. Using infra-red imaging, we reveal the characteristic interfacial flow patterns associated with the Marangoni convection in the evaporating drop. A scaling relation describes the correlation between the moving velocity of the drop and the apparent contact angle, both of which increase with the substrate temperature.

Debiasing word embeddings has been largely limited to individual and independent social categories. However, real-world corpora typically present multiple social categories that possibly correlate or intersect with each other. For instance, "hair weaves" is stereotypically associated with African American females, but neither African American nor females alone. Therefore, this work studies biases associated with multiple social categories: joint biases induced by the union of different categories and intersectional biases that do not overlap with the biases of the constituent categories. We first empirically observe that individual biases intersect non-trivially (i.e., over a one-dimensional subspace). Drawing from the intersectional theory in social science and the linguistic theory, we then construct an intersectional subspace to debias for multiple social categories using the nonlinear geometry of individual biases. Empirical evaluations corroborate the efficacy of our approach. Data and implementation code can be downloaded at https://github.com/GitHubLuCheng/Implementation-of-JoSEC-COLING-22., Comment: Accepted to COLING2022

With the onset of the COVID-19 pandemic, news outlets and social media have become central tools for disseminating and consuming information. Because of their ease of access, users seek COVID-19-related information from online social media (i.e., online news) and news outlets (i.e., offline news). Online and offline news are often connected, sharing common topics while each has unique, different topics. A gap between these two news sources can lead to misinformation propagation. For instance, according to the Guardian, most COVID-19 misinformation comes from users on social media. Without fact-checking social media news, misinformation can lead to health threats. In this paper, we focus on the novel problem of bridging the gap between online and offline data by monitoring their common and distinct topics generated over time. We employ Twitter (online) and local news (offline) data for a time span of two years. Using online matrix factorization, we analyze and study online and offline COVID-19-related data differences and commonalities. We design experiments to show how online and offline data are linked together and what trends they follow.

Recent advances in metasurfaces and optical nanostructures have enabled complex control of incident light with optically thin devices. However, it has thus far been unclear whether it is possible to achieve complete linear control of coherent light transmission, i.e., independent control of polarization, amplitude, and phase for both input polarization states, with just a single, thin nanostructure array. Here we prove that it is possible and propose a universal metasurface, a bilayer array of high-index elliptic cylinders, that possesses a complete degree of optical freedom with fully designable chirality and anisotropy. We mathematically show the completeness of achievable light control with corresponding Jones matrices, experimentally demonstrate new types of three-dimensional holographic schemes that were formerly impossible, and present a systematic way of realizing any input-state-sensitive vector linear optical device. Our results unlock previously inaccessible degrees of freedom in light transmission control., Comment: Main text: 30 pages, 5 figures. Supplementary discussion: 12 pages, 4 figures