Foivos Georgiadis, Sara Larivière, David Glahn, L. Elliot Hong, Peter Kochunov, Bryan Mowry, Carmel Loughland, Christos Pantelis, Frans A. Henskens, Melissa J. Green, Murray J. Cairns, Patricia T. Michie, Paul E. Rasser, Stanley Catts, Paul Tooney, Rodney J. Scott, Ulrich Schall, Vaughan Carr, Yann Quidé, Axel Krug, Frederike Stein, Igor Nenadić, Katharina Brosch, Tilo Kircher, Raquel Gur, Ruben Gur, Theodore D. Satterthwaite, Andriana Karuk, Edith Pomarol- Clotet, Joaquim Radua, Paola Fuentes-Claramonte, Raymond Salvador, Gianfranco Spalletta, Aristotle Voineskos, Kang Sim, Benedicto Crespo-Facorro, Diana Tordesillas Gutiérrez, Stefan Ehrlich, Nicolas Crossley, Dominik Grotegerd, Jonathan Repple, Rebekka Lencer, Udo Dannlowski, Vince Calhoun, Kelly Rootes-Murdy, Caroline Demro, Ian S. Ramsay, Scott R. Sponheim, Andre Schmidt, Stefan Borgwardt, Alexander Tomyshev, Irina Lebedeva, Cyril Höschl, Filip Spaniel, Adrian Preda, Dana Nguyen, Anne Uhlmann, Dan J. Stein, Fleur Howells, Henk S. Temmingh, Ana M. Diaz Zuluaga, Carlos López Jaramillo, Felice Iasevoli, Ellen Ji, Stephanie Homan, Wolfgang Omlor, Philipp Homan, Stefan Kaiser, Erich Seifritz, Bratislav Misic, Sofie L. Valk, Paul Thompson, Theo G. M. van Erp, Jessica A. Turner, , Boris Bernhardt, Matthias Kirschner <<<

AbstractSchizophrenia is a prototypical network disorder with widespread brain-morphological alterations, yet it remains unclear whether these distributed alterations robustly reflect the underlying network layout. We tested whether large-scale structural alterations in schizophrenia relate to normative structural and functional connectome architecture, and systematically evaluated robustness and generalizability of these network-level alterations. Leveraging anatomical MRI scans from 2439 adults with schizophrenia and 2867 healthy controls from 26 ENIGMA sites and normative data from the Human Connectome Project (n = 207), we evaluated structural alterations of schizophrenia against two network susceptibility models: (i) hub vulnerability, which examines associations between regional network centrality and magnitude of disease-related alterations; (ii) epicenter mapping, which identifies regions whose typical connectivity profile most closely resembles the disease-related morphological alterations. To assess generalizability and specificity, we contextualized the influence of site, disease stages, and individual clinical factors and compared network associations of schizophrenia with that found in affective disorders. Our findings show schizophrenia-related cortical thinning is spatially associated with functional and structural hubs, suggesting that highly interconnected regions are more vulnerable to morphological alterations. Predominantly temporo-paralimbic and frontal regions emerged as epicenters with connectivity profiles linked to schizophrenia’s alteration patterns. Findings were robust across sites, disease stages, and related to individual symptoms. Moreover, transdiagnostic comparisons revealed overlapping epicenters in schizophrenia and bipolar, but not major depressive disorder, suggestive of a pathophysiological continuity within the schizophrenia-bipolar-spectrum. In sum, cortical alterations over the course of schizophrenia robustly follow brain network architecture, emphasizing marked hub susceptibility and temporo-frontal epicenters at both the level of the group and the individual. Subtle variations of epicenters across disease stages suggest interacting pathological processes, while associations with patient-specific symptoms support additional inter-individual variability of hub vulnerability and epicenters in schizophrenia. Our work outlines potential pathways to better understand macroscale structural alterations, and inter- individual variability in schizophrenia. <<<

Weixin Liang, Zachary Izzo, Yaohui Zhang, Haley Lepp, Hancheng Cao, Xuandong Zhao, Lingjiao Chen, Haotian Ye, Sheng Liu, Zhi Huang, Daniel A. McFarland, James Y. Zou <<<

We present an approach for estimating the fraction of text in a large corpuswhich is likely to be substantially modified or produced by a large languagemodel (LLM). Our maximum likelihood model leverages expert-written andAI-generated reference texts to accurately and efficiently examine real-worldLLM-use at the corpus level. We apply this approach to a case study ofscientific peer review in AI conferences that took place after the release ofChatGPT: ICLR 2024, NeurIPS 2023, CoRL 2023 and EMNLP 2023. Our results suggestthat between 6.5% and 16.9% of text submitted as peer reviews to theseconferences could have been substantially modified by LLMs, i.e. beyondspell-checking or minor writing updates. The circumstances in which generatedtext occurs offer insight into user behavior: the estimated fraction ofLLM-generated text is higher in reviews which report lower confidence, weresubmitted close to the deadline, and from reviewers who are less likely torespond to author rebuttals. We also observe corpus-level trends in generatedtext which may be too subtle to detect at the individual level, and discuss theimplications of such trends on peer review. We call for futureinterdisciplinary work to examine how LLM use is changing our information andknowledge practices. <<<

This paper shows that masked autoencoders (MAE) are scalable self-supervisedlearners for computer vision. Our MAE approach is simple: we mask randompatches of the input image and reconstruct the missing pixels. It is based ontwo core designs. First, we develop an asymmetric encoder-decoder architecture,with an encoder that operates only on the visible subset of patches (withoutmask tokens), along with a lightweight decoder that reconstructs the originalimage from the latent representation and mask tokens. Second, we find thatmasking a high proportion of the input image, e.g., 75%, yields a nontrivialand meaningful self-supervisory task. Coupling these two designs enables us totrain large models efficiently and effectively: we accelerate training (by 3xor more) and improve accuracy. Our scalable approach allows for learninghigh-capacity models that generalize well: e.g., a vanilla ViT-Huge modelachieves the best accuracy (87.8%) among methods that use only ImageNet-1Kdata. Transfer performance in downstream tasks outperforms supervisedpre-training and shows promising scaling behavior. <<<

Arun C. Habermann, Austin J. Gutierrez, Linh T. Bui, Stephanie L. Yahn, Nichelle I. Winters, Carla L. Calvi, Lance Peter, Mei-I Chung, Chase J. Taylor, Christopher Jetter, Latha Raju, Jamie Roberson, Guixiao Ding, Lori Wood, Jennifer M. S. Sucre, Bradley W. Richmond, Ana P. Serezani, Wyatt J. McDonnell, Simon B. Mallal, Matthew J. Bacchetta, James E. Loyd, Ciara M. Shaver, Lorraine B. Ware, Ross Bremner, Rajat Walia, Timothy S. Blackwell, Nicholas E. Banovich, Jonathan A. Kropski <<<

Single-cell RNA sequencing provides new insights into pathologic epithelial and mesenchymal remodeling in the human lung. <<<

Most robotic hands and grippers rely on actuators with large gearboxes andforce sensors for controlling gripping force. However, this might not be idealfor tasks that require the robot to interact with an unstructured and unknownenvironment. In this paper, we introduce a novel quasi-direct-drivetwo-fingered robotic hand with variable impedance control in the joint spaceand Cartesian space. The hand has a total of four degrees of freedom,backdrivable differential gear trains, and four brushless direct current (BLDC)motors. Motor torque is controlled through Field-Oriented Control (FOC) withcurrent sensing. Variable impedance control enables the robotic hand to executedexterous manipulation tasks safely during environment-robot and human-robotinteractions. The quasi-direct-drive actuators eliminate the need for complextactile/force sensors or precise motion planning when handling environmentalcontact. A majority-3D-printed assembly makes this a low-cost research platformbuilt with affordable, readily available off-the-shelf components. Experimentalvalidation demonstrates the robotic hand's capability for stable force-closureand form-closure grasps in the presence of disturbances, reliable in-handmanipulation, and safe dynamic manipulations despite contact with theenvironment. <<<

This paper proposes a new game-search algorithm, PN-MCTS, which combinesMonte-Carlo Tree Search (MCTS) and Proof-Number Search (PNS). These twoalgorithms have been successfully applied for decision making in a range ofdomains. We define three areas where the additional knowledge provided by theproof and disproof numbers gathered in MCTS trees might be used: final moveselection, solving subtrees, and the UCB1 selection mechanism. We test allpossible combinations on different time settings, playing against vanilla UCTon several games: Lines of Action ($7$$\times$$7$ and $8$$\times$$8$ boardsizes), MiniShogi, Knightthrough, and Awari. Furthermore, we extend this newalgorithm to properly address games with draws, like Awari, by adding anadditional layer of PNS on top of the MCTS tree. The experiments show thatPN-MCTS is able to outperform MCTS in all tested game domains, achieving winrates up to 96.2% for Lines of Action. <<<

Wolfram Höps, Marjan M. Weiss, Ronny Derks, Jordi Corominas Galbany, Amber den Ouden, Simone van den Heuvel, Raoul Timmermans, Jos Smits, Tom Mokveld, Egor Dolzhenko, Xiao Chen, Arthur van den Wijngaard, Michael A. Eberle, Helger G. Yntema, Alexander Hoischen, Christian Gilissen, Lisenka E.L.M. Vissers <<<

Simeng Hu, Can Hu, Jingli Xu, Pengfei Yu, Li Yuan, Ziyu Li, Haohong Liang, Yanqiang Zhang, Jiahui Chen, Qing Wei, Shengjie Zhang, Litao Yang, Dan Su, Yian Du, Zhiyuan Xu, Fan Bai, Xiangdong Cheng <<<

This work considers the category distribution heterogeneity in federatedlearning. This issue is due to biased labeling preferences at multiple clientsand is a typical setting of data heterogeneity. To alleviate this issue, mostprevious works consider either regularizing local models or fine-tuning theglobal model, while they ignore the adjustment of aggregation weights andsimply assign weights based on the dataset size. However, based on ourempirical observations and theoretical analysis, we find that the dataset sizeis not optimal and the discrepancy between local and global categorydistributions could be a beneficial and complementary indicator for determiningaggregation weights. We thus propose a novel aggregation method, FederatedLearning with Discrepancy-aware Collaboration (FedDisco), whose aggregationweights not only involve both the dataset size and the discrepancy value, butalso contribute to a tighter theoretical upper bound of the optimization error.FedDisco also promotes privacy-preservation, communication and computationefficiency, as well as modularity. Extensive experiments show that our FedDiscooutperforms several state-of-the-art methods and can be easily incorporatedwith many existing methods to further enhance the performance. Our code will beavailable at https://github.com/MediaBrain-SJTU/FedDisco. <<<

L. F. Johansson, E. N. de Boer, H. A. de Weerd, F. van Dijk, M. G. Elferink, G. H. Schuring-Blom, R. F. Suijkerbuijk, R. J. Sinke, G. J. te Meerman, R. H. Sijmons, M. A. Swertz, B. Sikkema-Raddatz <<<

AbstractNon-invasive prenatal testing (NIPT) of cell-free DNA in maternal plasma, which is a mixture of maternal DNA and a low percentage of fetal DNA, can detect fetal aneuploidies using massively parallel sequencing. Because of the low percentage of fetal DNA, methods with high sensitivity and precision are required. However, sequencing variation lowers sensitivity and hampers detection of trisomy samples. Therefore, we have developed three algorithms to improve sensitivity and specificity: the chi-squared-based variation reduction (χ2VR), the regression-based Z-score (RBZ) and the Match QC score. The χ2VR reduces variability in sequence read counts per chromosome between samples, the RBZ allows for more precise trisomy prediction, and the Match QC score shows if the control group used is representative for a specific sample. We compared the performance of χ2VR to that of existing variation reduction algorithms (peak and GC correction) and that of RBZ to trisomy prediction algorithms (standard Z-score, normalized chromosome value and median-absolute-deviation-based Z-score). χ2VR and the RBZ both reduce variability more than existing methods, and thereby increase the sensitivity of the NIPT analysis. We found the optimal combination of algorithms was to use both GC correction and χ2VR for pre-processing and to use RBZ as the trisomy prediction method. <<<

Jiawang Tao, Zichao Wu, Yanran Liang, Jiongliang Wang, Miaoxiu Tang, Sunan Huang, Fan Jiang, Guangqi Zhou, Lin Guo, Shengxian Yuan, Yinxiong Li, Jie Wang <<<

Background and Aims: Promoting liver regeneration while inhibiting fibrogenesis represented an attractive strategy for treating liver diseases, with hepatic stellate cells (HSCs) being crucial to both processes. This study aimed to identify specific targets in HSCs that simultaneously facilitated regeneration and suppressed fibrosis, and elucidated their molecular mechanisms. Approach and Results: Through comparing acute and chronic liver injury mouse models induced by CCl4 injections, we revealed that HSCs exhibited dual functionality, expressing pro-regenerative and pro-fibrogenic genes following injury. Analyzing RNA-seq data from primary HSCs of these models, along with publicly available single-cell RNA-seq data of HSCs, we identified transcription factor Lhx2, specifically expressed in HSCs, emerged as a potential regulator of the dual functions. Notably, Lhx2 showed significantly higher expression in HSCs from healthy liver tissue compared to fibrotic liver, in both mouse and human models. Lhx2 knockdown impaired liver function recovery and cellular proliferation after acute liver injury. Consistent changes were observed in mice with HSC-specific Lhx2 overexpression. Additionally, Lhx2 overexpression not only promoted hepatocyte proliferation but also exhibited an anti-fibrogenic function after chronic injury. Mechanistically, Lhx2 suppressed multiple functions of activated HSCs, including fibrogenesis, proliferation and migration, and up-regulated SMAD6 to block TGF-β signaling pathway. Moreover, Lhx2 was an upstream regulator of various pro-regenerative factors, especially HGF, which is crucial for liver regeneration. Conclusions: We demonstrated that Lhx2 had pro-regenerative and anti-fibrogenic functions, and elucidated its regulatory mechanism. The study provided a potential target with dual effects for treating liver diseases. <<<

This paper shows that masked autoencoders (MAE) are scalable self-supervisedlearners for computer vision. Our MAE approach is simple: we mask randompatches of the input image and reconstruct the missing pixels. It is based ontwo core designs. First, we develop an asymmetric encoder-decoder architecture,with an encoder that operates only on the visible subset of patches (withoutmask tokens), along with a lightweight decoder that reconstructs the originalimage from the latent representation and mask tokens. Second, we find thatmasking a high proportion of the input image, e.g., 75%, yields a nontrivialand meaningful self-supervisory task. Coupling these two designs enables us totrain large models efficiently and effectively: we accelerate training (by 3xor more) and improve accuracy. Our scalable approach allows for learninghigh-capacity models that generalize well: e.g., a vanilla ViT-Huge modelachieves the best accuracy (87.8%) among methods that use only ImageNet-1Kdata. Transfer performance in downstream tasks outperforms supervisedpre-training and shows promising scaling behavior. <<<

Lovisa Franzén, Martina Olsson Lindvall, Michael Hühn, Victoria Ptasinski, Laura Setyo, Benjamin P. Keith, Astrid Collin, Steven Oag, Thomas Volckaert, Annika Borde, Joakim Lundeberg, Julia Lindgren, Graham Belfield, Sonya Jackson, Anna Ollerstam, Marianna Stamou, Patrik L. Ståhl, Jorrit J. Hornberg <<<

AbstractIdiopathic pulmonary fibrosis (IPF) is a progressive lung disease with poor prognosis and limited treatment options. Efforts to identify effective treatments are thwarted by limited understanding of IPF pathogenesis and poor translatability of available preclinical models. Here we generated spatially resolved transcriptome maps of human IPF (n = 4) and bleomycin-induced mouse pulmonary fibrosis (n = 6) to address these limitations. We uncovered distinct fibrotic niches in the IPF lung, characterized by aberrant alveolar epithelial cells in a microenvironment dominated by transforming growth factor beta signaling alongside predicted regulators, such as TP53 and APOE. We also identified a clear divergence between the arrested alveolar regeneration in the IPF fibrotic niches and the active tissue repair in the acutely fibrotic mouse lung. Our study offers in-depth insights into the IPF transcriptional landscape and proposes alveolar regeneration as a promising therapeutic strategy for IPF. <<<