We introduce adaptive learn-then-test (aLTT), an efficient hyperparameter selection procedure that provides finite-sample statistical guarantees on the population risk of AI models. Unlike the existing learn-then-test (LTT) technique, which relies on conventional p-value-based multiple hypothesis testing (MHT), aLTT implements sequential data-dependent MHT with early termination by leveraging e-processes. As a result, aLTT can reduce the number of testing rounds, making it particularly well-suited for scenarios in which testing is costly or presents safety risks. Apart from maintaining statistical validity, in applications such as online policy selection for offline reinforcement learning and hyperparameter tuning for engineering systems, aLTT is shown to achieve the same performance as LTT while requiring only a fraction of the testing rounds.

Large Language Models (LLMs) have the promise to revolutionize computing broadly, but their complexity and extensive training data also expose significant privacy vulnerabilities. One of the simplest privacy risks associated with LLMs is their susceptibility to membership inference attacks (MIAs), wherein an adversary aims to determine whether a specific data point was part of the model's training set. Although this is a known risk, state of the art methodologies for MIAs rely on training multiple computationally costly shadow models, making risk evaluation prohibitive for large models. Here we adapt a recent line of work which uses quantile regression to mount membership inference attacks; we extend this work by proposing a low-cost MIA that leverages an ensemble of small quantile regression models to determine if a document belongs to the model's training set or not. We demonstrate the effectiveness of this approach on fine-tuned LLMs of varying families (OPT, Pythia, Llama) and across multiple datasets. Across all scenarios we obtain comparable or improved accuracy compared to state of the art shadow model approaches, with as little as 6% of their computation budget. We demonstrate increased effectiveness across multi-epoch trained target models, and architecture miss-specification robustness, that is, we can mount an effective attack against a model using a different tokenizer and architecture, without requiring knowledge on the target model.

Antibody-drug conjugates (ADCs) have emerged as a promising class of targeted cancer therapeutics, but the design and optimization of their cytotoxic payloads remain challenging. This study introduces DumplingGNN, a novel hybrid Graph Neural Network architecture specifically designed for predicting ADC payload activity based on chemical structure. By integrating Message Passing Neural Networks (MPNN), Graph Attention Networks (GAT), and GraphSAGE layers, DumplingGNN effectively captures multi-scale molecular features and leverages both 2D topological and 3D structural information. We evaluate DumplingGNN on a comprehensive ADC payload dataset focusing on DNA Topoisomerase I inhibitors, as well as on multiple public benchmarks from MoleculeNet. DumplingGNN achieves state-of-the-art performance across several datasets, including BBBP (96.4\% ROC-AUC), ToxCast (78.2\% ROC-AUC), and PCBA (88.87\% ROC-AUC). On our specialized ADC payload dataset, it demonstrates exceptional accuracy (91.48\%), sensitivity (95.08\%), and specificity (97.54\%). Ablation studies confirm the synergistic effects of the hybrid architecture and the critical role of 3D structural information in enhancing predictive accuracy. The model's strong interpretability, enabled by attention mechanisms, provides valuable insights into structure-activity relationships. DumplingGNN represents a significant advancement in molecular property prediction, with particular promise for accelerating the design and optimization of ADC payloads in targeted cancer therapy development.

The use of cryptocurrencies has led to an increase in illicit activities such as money laundering, with traditional rule-based approaches becoming less effective in detecting and preventing such activities. In this paper, we propose a novel approach to tackling this problem by applying graph attention networks with residual network-like architecture (GAT-ResNet) to detect illicit transactions related to anti-money laundering/combating the financing of terrorism (AML/CFT) in blockchains. We train various models on the Elliptic Bitcoin Transaction dataset, implementing logistic regression, Random Forest, XGBoost, GCN, GAT, and our proposed GAT-ResNet model. Our results demonstrate that the GAT-ResNet model has a potential to outperform the existing graph network models in terms of accuracy, reliability and scalability. Our research sheds light on the potential of graph related machine learning models to improve efforts to combat financial crime and lays the foundation for further research in this area.

Plant morphological traits, their observable characteristics, are fundamental to understand the role played by each species within their ecosystem. However, compiling trait information for even a moderate number of species is a demanding task that may take experts years to accomplish. At the same time, massive amounts of information about species descriptions is available online in the form of text, although the lack of structure makes this source of data impossible to use at scale. To overcome this, we propose to leverage recent advances in large language models (LLMs) and devise a mechanism for gathering and processing information on plant traits in the form of unstructured textual descriptions, without manual curation. We evaluate our approach by automatically replicating three manually created species-trait matrices. Our method managed to find values for over half of all species-trait pairs, with an F1-score of over 75%. Our results suggest that large-scale creation of structured trait databases from unstructured online text is currently feasible thanks to the information extraction capabilities of LLMs, being limited by the availability of textual descriptions covering all the traits of interest.

Target selection is crucial in pharmaceutical drug discovery, directly influencing clinical trial success. Despite its importance, drug development remains resource-intensive, often taking over a decade with significant financial costs. High failure rates highlight the need for better early-stage target selection. We present GATher, a graph attention network designed to predict therapeutic gene-disease links by integrating data from diverse biomedical sources into a graph with over 4.4 million edges. GATher incorporates GATv3, a novel graph attention convolution layer, and GATv3HeteroConv, which aggregates transformations for each edge type, enhancing its ability to manage complex interactions within this extensive dataset. Utilizing hard negative sampling and multi-task pre-training, GATher addresses topological imbalances and improves specificity. Trained on data up to 2018 and evaluated through 2024, our results show GATher predicts clinical trial outcomes with a ROC AUC of 0.69 for unmet efficacy failures and 0.79 for positive efficacy. Feature attribution methods, using Captum, highlight key nodes and relationships, enhancing model interpretability. By 2024, GATher improved precision in prioritizing the top 200 clinical trial targets to 14.1%, an absolute increase of over 3.5% compared to other methods. GATher outperforms existing models like GAT, GATv2, and HGT in predicting clinical trial outcomes, demonstrating its potential in enhancing target validation and predicting clinical efficacy and safety.

The discovery of novel magnetic materials with greater operating temperature ranges and optimized performance is essential for advanced applications. Current data-driven approaches are challenging and limited due to the lack of accurate, comprehensive, and feature-rich databases. This study aims to address this challenge by introducing a new approach that uses Large Language Models (LLMs) to create a comprehensive, experiment-based, magnetic materials database named the Northeast Materials Database (NEMAD), which consists of 26,706 magnetic materials (www.nemad.org). The database incorporates chemical composition, magnetic phase transition temperatures, structural details, and magnetic properties. Enabled by NEMAD, machine learning models were developed to classify materials and predict transition temperatures. Our classification model achieved an accuracy of 90% in categorizing materials as ferromagnetic (FM), antiferromagnetic (AFM), and non-magnetic (NM). The regression models predict Curie (N\'eel) temperature with a coefficient of determination (R2) of 0.86 (0.85) and a mean absolute error (MAE) of 62K (32K). These models identified 62 (19) FM (AFM) candidates with a predicted Curie (N\'eel) temperature above 500K (100K) from the Materials Project. This work shows the feasibility of combining LLMs for automated data extraction and machine learning models in accelerating the discovery of magnetic materials.

In this paper, we present Safe Guard, an LLM-agent for the detection of hate speech in voice-based interactions in social VR (VRChat). Our system leverages Open AI GPT and audio feature extraction for real-time voice interactions. We contribute a system design and evaluation of the system that demonstrates the capability of our approach in detecting hate speech, and reducing false positives compared to currently available approaches. Our results indicate the potential of LLM-based agents in creating safer virtual environments and set the groundwork for further advancements in LLM-driven moderation approaches.

This involves taking multiple images to detect an object more than once within a short enough time for the detections to be linked. The actual linkage of detection can include decision trees or the connection of several detections together within similar co-moving velocities (Kubica et al., 2005; Masci et al., 2019). Multiple detection linking algorithms can link the detections of both point-source, asteroidal detections and those that are extended, as for comets. Even for comets, whose detections have a large, extended appearance, multiple detections can be linked as for point sources if the measurement of the comet's position relative to the moving frame of the object is consistent from detection to detection (Denneau et al., 2013). However, in some survey imaging pipelines, extended objects, defined as having a width more expansive than the measured width for known point sources, can be flagged as potential outliers and removed from further processing (Duev et al., 2019).

Many time series, particularly health data streams, can be best understood as a sequence of phenomenon or events, which we call motifs. A time series motif is a short trace segment which may implicitly capture an underlying phenomenon within the time series. Specifically, we focus on glucose traces collected from continuous glucose monitors (CGMs), which inherently contain motifs representing underlying human behaviors such as eating and exercise. The ability to identify and quantify causal relationships amongst motifs can provide a mechanism to better understand and represent these patterns, useful for improving deep learning and generative models and for advanced technology development (e.g., personalized coaching and artificial insulin delivery systems). However, no previous work has developed causal discovery methods for time series motifs. Therefore, in this paper we develop MotifDisco (motif disco-very of causality), a novel causal discovery framework to learn causal relations amongst motifs from time series traces. We formalize a notion of Motif Causality (MC), inspired from Granger Causality and Transfer Entropy, and develop a Graph Neural Network-based framework that learns causality between motifs by solving an unsupervised link prediction problem. We also integrate MC with three model use cases of forecasting, anomaly detection and clustering, to showcase the use of MC as a building block for other downstream tasks. Finally, we evaluate our framework and find that Motif Causality provides a significant performance improvement in all use cases.