Probabilistic topic models are a powerful tool for extracting latent themes from large text datasets. In many text datasets, we also observe per-document covariates (e.g., source, style, political affiliation) that act as environments that modulate a "global" (environment-agnostic) topic representation. Accurately learning these representations is important for prediction on new documents in unseen environments and for estimating the causal effect of topics on real-world outcomes. To this end, we introduce the Multi-environment Topic Model (MTM), an unsupervised probabilistic model that separates global and environment-specific terms. Through experimentation on various political content, from ads to tweets and speeches, we show that the MTM produces interpretable global topics with distinct environment-specific words. On multi-environment data, the MTM outperforms strong baselines in and out-of-distribution. It also enables the discovery of accurate causal effects.

Recent advances in deep learning architectures have enabled efficient and accurate classification of pre-trained targets in Synthetic Aperture Radar (SAR) images. Nevertheless, the presence of unknown targets in real battlefield scenarios is unavoidable, resulting in misclassification and reducing the accuracy of the classifier. Over the past decades, various feature-based out-of-distribution (OOD) approaches have been developed to address this issue, yet defining the decision boundary between known and unknown targets remains challenging. Additionally, unlike optical images, detecting unknown targets in SAR imagery is further complicated by high speckle noise, the presence of clutter, and the inherent similarities in back-scattered microwave signals. In this work, we propose transforming feature-based OOD detection into a class-localized feature-residual-based approach, demonstrating that this method can improve stability across varying unknown targets' distribution conditions. Transforming feature-based OOD detection into a residual-based framework offers a more robust reference space for distinguishing between in-distribution (ID) and OOD data, particularly within the unique characteristics of SAR imagery. This adaptive residual transformation method standardizes feature-based inputs into distributional representations, enhancing OOD detection in noisy, low-information images. Our approach demonstrates promising performance in real-world SAR scenarios, effectively adapting to the high levels of noise and clutter inherent in these environments. These findings highlight the practical relevance of residual-based OOD detection for SAR applications and suggest a foundation for further advancements in unknown target detection in complex, operational settings.

Recently, there has been an explosion of large language models created through fine-tuning with data from larger models. These small models able to produce outputs that appear qualitatively similar to significantly larger models. However, one of the key limitations that have been observed with these models is their propensity to hallucinate significantly more often than larger models. In particular, they have been observed to generate coherent outputs that involve factually incorrect information and spread misinformation, toxicity, and stereotypes. There are many potential causes of hallucination, of which, one hypothesis is that fine-tuning a model on data produced by a larger model leads to a knowledge mismatch which contributes to hallucination. In particular, it is hypothesized that there is a mismatch between the knowledge that is fed to the model to fine-tune it and the knowledge that is already present in the graph. Fine-tuning the model on data that has such mismatch could contribute to an increased propensity to hallucinate. We show that on an unseen test set, a smaller model fine-tuned on data generated from a larger model produced more wrong answers when compared to models fine-tuned on data created by the small model, which confirms the hypothesis.

Model Compression has drawn much attention within the deep learning community recently. Compressing a dense neural network offers many advantages including lower computation cost, deployability to devices of limited storage and memories, and resistance to adversarial attacks. This may be achieved via weight pruning or fully discarding certain input features. Here we demonstrate a novel strategy to emulate principles of Bayesian model selection in a deep learning setup. Given a fully connected Bayesian neural network with spike-and-slab priors trained via a variational algorithm, we obtain the posterior inclusion probability for every node that typically gets lost. We employ these probabilities for pruning and feature selection on a host of simulated and real-world benchmark data and find evidence of better generalizability of the pruned model in all our experiments.

National Statistical Organisations every year spend time and money to collect information through surveys. Some of these surveys include follow-up studies, and usually, some participants due to factors such as death, immigration, change of employment, health, etc, do not participate in future surveys. In this study, we focus on the English Longitudinal Study of Ageing (ELSA) COVID-19 Substudy, which was carried out during the COVID-19 pandemic in two waves. In this substudy, some participants from wave 1 did not participate in wave 2. Our purpose is to predict non-responses using Machine Learning (ML) algorithms such as K-nearest neighbours (KNN), random forest (RF), AdaBoost, logistic regression, neural networks (NN), and support vector classifier (SVC). We find that RF outperforms other models in terms of balanced accuracy, KNN in terms of precision and test accuracy, and logistics regressions in terms of the area under the receiver operating characteristic curve (ROC), i.e. AUC.

Federated learning (FL) is a distributed learning framework that leverages commonalities between distributed client datasets to train a global model. Under heterogeneous clients, however, FL can fail to produce stable training results. Personalized federated learning (PFL) seeks to address this by learning individual models tailored to each client. One approach is to decompose model training into shared representation learning and personalized classifier training. Nonetheless, previous works struggle to navigate the bias-variance trade-off in classifier learning, relying solely on limited local datasets or introducing costly techniques to improve generalization. In this work, we frame representation learning as a generative modeling task, where representations are trained with a classifier based on the global feature distribution. We then propose an algorithm, pFedFDA, that efficiently generates personalized models by adapting global generative classifiers to their local feature distributions. Through extensive computer vision benchmarks, we demonstrate that our method can adjust to complex distribution shifts with significant improvements over current state-of-the-art in data-scarce settings.

Large Language Models (LLMs) are distinguished by their architecture, which dictates their parameter size and performance capabilities. Social scientists have increasingly adopted LLMs for text classification tasks, which are difficult to scale with human coders. While very large, closed-source models often deliver superior performance, their use presents significant risks. These include lack of transparency, potential exposure of sensitive data, challenges to replicability, and dependence on proprietary systems. Additionally, their high costs make them impractical for large-scale research projects. In contrast, open-source models, although available in various sizes, may underperform compared to commercial alternatives if used without further fine-tuning. However, open-source models offer distinct advantages: they can be run locally (ensuring data privacy), fine-tuned for specific tasks, shared within the research community, and integrated into reproducible workflows. This study demonstrates that small, fine-tuned open-source LLMs can achieve equal or superior performance to models such as ChatGPT-4. We further explore the relationship between training set size and fine-tuning efficacy in open-source models. Finally, we propose a hybrid workflow that leverages the strengths of both open and closed models, offering a balanced approach to performance, transparency, and reproducibility.

In machine learning research, it is common to evaluate algorithms via their performance on standard benchmark datasets. While a growing body of work establishes guidelines for -- and levies criticisms at -- data and benchmarking practices in machine learning, comparatively less attention has been paid to the data repositories where these datasets are stored, documented, and shared. In this paper, we analyze the landscape of these $\textit{benchmark data repositories}$ and the role they can play in improving benchmarking. This role includes addressing issues with both datasets themselves (e.g., representational harms, construct validity) and the manner in which evaluation is carried out using such datasets (e.g., overemphasis on a few datasets and metrics, lack of reproducibility). To this end, we identify and discuss a set of considerations surrounding the design and use of benchmark data repositories, with a focus on improving benchmarking practices in machine learning.

Recent advances in Large Language Models (LLMs) have helped facilitate exciting progress for robotic planning in real, open-world environments. 3D scene graphs (3DSGs) offer a promising environment representation for grounding such LLM-based planners as they are compact and semantically rich. However, as the robot's environment scales (e.g., number of entities tracked) and the complexity of scene graph information increases (e.g., maintaining more attributes), providing the 3DSG as-is to an LLM-based planner quickly becomes infeasible due to input token count limits and attentional biases present in LLMs. Inspired by the successes of Retrieval-Augmented Generation (RAG) methods that retrieve query-relevant document chunks for LLM question and answering, we adapt the paradigm for our embodied domain. Specifically, we propose a 3D scene subgraph retrieval framework, called EmbodiedRAG, that we augment an LLM-based planner with for executing natural language robotic tasks. Notably, our retrieved subgraphs adapt to changes in the environment as well as changes in task-relevancy as the robot executes its plan. We demonstrate EmbodiedRAG's ability to significantly reduce input token counts (by an order of magnitude) and planning time (up to 70% reduction in average time per planning step) while improving success rates on AI2Thor simulated household tasks with a single-arm, mobile manipulator. Additionally, we implement EmbodiedRAG on a quadruped with a manipulator to highlight the performance benefits for robot deployment at the edge in real environments.

However, this growth has also introduced new challenges in ensuring the integrity, traceability, and verifiability of AI systems throughout their lifecycle [1]. As AI increasingly influences critical decision-making processes, the need for robust mechanisms to guarantee the trustworthiness of these systems has become paramount. Traditional approaches to data integrity and system verification fall short when applied to the complex, often opaque nature of AI systems. The dynamic nature of AI models, the vast amounts of data they process, and the intricate relationships between different stages of their lifecycle demand a more comprehensive and AI-specific approach to integrity assurance. This paper introduces Meta-Sealing, a novel integrity protocol designed specifically for AI systems. Meta-Sealing provides a cryptographic framework for sealing and verifying each stage of the AI lifecycle, from data collection to model retirement. By doing so, it addresses critical needs in enterprise AI deployment, including: 1. Ensuring the integrity of training data and model artifacts 2. Creating verifiable audit trails of AI development and deployment processes 3. Enhancing the reproducibility of AI experiments and results 4. Facilitating compliance with emerging AI regulations and governance frameworks 5. Building trust in AI systems among stakeholders and end-users We present a detailed architecture for implementing Meta-Sealing, including core components, cryptographic operations, and integration strategies. Furthermore, we discuss performance optimizations and security considerations crucial for enterprise-grade deployments.