The broad adoption of Generative AI (GenAI) is impacting Computer Science education, and recent studies found its benefits and potential concerns when students use it for programming learning. However, most existing explorations focus on GenAI tools that primarily support text-to-text interaction. With recent developments, GenAI applications have begun supporting multiple modes of communication, known as multimodality. In this work, we explored how undergraduate programming novices choose and work with multimodal GenAI tools, and their criteria for choices. We selected a commercially available multimodal GenAI platform for interaction, as it supports multiple input and output modalities, including text, audio, image upload, and real-time screen-sharing. Through 16 think-aloud sessions that combined participant observation with follow-up semi-structured interviews, we investigated student modality choices for GenAI tools when completing programming problems and the underlying criteria for modality selections. With multimodal communication emerging as the future of AI in education, this work aims to spark continued exploration on understanding student interaction with multimodal GenAI in the context of CS education.

Predicting the final hardness of steel after heat treatment is a challenging regression task due to the many-to-one nature of the process -- different combinations of input parameters (such as temperature, duration, and chemical composition) can result in the same hardness value. This ambiguity makes the inverse problem, estimating input parameters from a desired hardness, particularly difficult. In this work, we propose a novel solution using a Teacher-Student learning framework. First, a forward model (Teacher) is trained to predict final hardness from 13 metallurgical input features. Then, a backward model (Student) is trained to infer plausible input configurations from a target hardness value. The Student is optimized by leveraging feedback from the Teacher in an iterative, supervised loop. We evaluate our method on a publicly available tempered steel dataset and compare it against baseline regression and reinforcement learning models. Results show that our Teacher-Student framework not only achieves higher inverse prediction accuracy but also requires significantly less computational time, demonstrating its effectiveness and efficiency for inverse process modeling in materials science.

Meaningful human-AI collaboration requires more than processing language; it demands a deeper understanding of symbols and their socially constructed meanings. While humans naturally interpret symbols through social interaction, AI systems often miss the dynamic interpretations that emerge in conversation. Drawing on Symbolic Interactionism theory, we conducted two studies to investigate how humans and AI co-construct symbols and their meanings. Findings provide empirical insights into how humans and conversational AI agents collaboratively shape meanings during interaction. We show how participants shift their initial definitions of meaning in response to the symbols and interpretations suggested by the conversational AI agents, especially when social context is introduced. We also observe how participants project their personal and social values into these interactions, refining meanings over time. These findings reveal that shared understanding does not emerge from mere agreement but from the bi-directional exchange and reinterpretation of symbols, suggesting new paradigms for human-AI interaction design.

Adversarial training is the most effective defense against adversarial attacks. The effectiveness of the adversarial attacks has been on the design of its loss function and regularization term. The most widely used loss function in adversarial training is cross-entropy and mean squared error (MSE) as its regularization objective. However, MSE enforces overly uniform optimization between two output distributions during training, which limits its robustness in adversarial training scenarios. To address this issue, we revisit the idea of mutual learning (originally designed for knowledge distillation) and propose two novel regularization strategies tailored for adversarial training: (i) weighted adversarial mutual regularization and (ii) adversarial generalization regularization. In the former, we formulate a decomposed adversarial mutual Kullback-Leibler divergence (KL-divergence) loss, which allows flexible control over the optimization process by assigning unequal weights to the main and auxiliary objectives. In the latter, we introduce an additional clean target distribution into the adversarial training objective, improving generalization and enhancing model robustness. Extensive experiments demonstrate that our proposed methods significantly improve adversarial robustness compared to existing regularization-based approaches.

We study a class of misspecified saddle point (SP) problems, where the optimization objective depends on an unknown parameter that must be learned concurrently from data. Unlike existing studies that assume parameters are fully known or pre-estimated, our framework integrates optimization and learning into a unified formulation, enabling a more flexible problem class. To address this setting, we propose two algorithms based on the accelerated primal-dual (APD) by Hamedani & Aybat 2021. In particular, we first analyze the naive extension of the APD method by directly substituting the evolving parameter estimates into the primal-dual updates; then, we design a new learning-aware variant of the APD method that explicitly accounts for parameter dynamics by adjusting the momentum updates. Both methods achieve a provable convergence rate of $\mathcal{O}(\log K / K)$, while the learning-aware approach attains a tighter $\mathcal{O}(1)$ constant and further benefits from an adaptive step-size selection enabled by a backtracking strategy. Furthermore, we extend the framework to problems where the learning problem admits multiple optimal solutions, showing that our modified algorithm for a structured setting achieves an $\mathcal{O}(1/\sqrt{K})$ rate. To demonstrate practical impact, we evaluate our methods on a misspecified portfolio optimization problem and show superior empirical performance compared to state-of-the-art algorithms.

Large language models (LLMs) have shown remarkable progress in coding and math problem-solving, but evaluation on advanced research-level problems in hard sciences remains scarce. To fill this gap, we present CMT-Benchmark, a dataset of 50 problems covering condensed matter theory (CMT) at the level of an expert researcher. Topics span analytical and computational approaches in quantum many-body, and classical statistical mechanics. The dataset was designed and verified by a panel of expert researchers from around the world. We built the dataset through a collaborative environment that challenges the panel to write and refine problems they would want a research assistant to solve, including Hartree-Fock, exact diagonalization, quantum/variational Monte Carlo, density matrix renormalization group (DMRG), quantum/classical statistical mechanics, and model building. We evaluate LLMs by programmatically checking solutions against expert-supplied ground truth. We developed machine-grading, including symbolic handling of non-commuting operators via normal ordering. They generalize across tasks too. Our evaluations show that frontier models struggle with all of the problems in the dataset, highlighting a gap in the physical reasoning skills of current LLMs. Notably, experts identified strategies for creating increasingly difficult problems by interacting with the LLMs and exploiting common failure modes. The best model, GPT5, solves 30\% of the problems; average across 17 models (GPT, Gemini, Claude, DeepSeek, Llama) is 11.4$\pm$2.1\%. Moreover, 18 problems are solved by none of the 17 models, and 26 by at most one. These unsolved problems span Quantum Monte Carlo, Variational Monte Carlo, and DMRG. Answers sometimes violate fundamental symmetries or have unphysical scaling dimensions. We believe this benchmark will guide development toward capable AI research assistants and tutors.

This systematic literature review examines the role of machine learning in fraud detection within digital banking, synthesizing evidence from 118 peer-reviewed studies and institutional reports. Following the PRISMA guidelines, the review applied a structured identification, screening, eligibility, and inclusion process to ensure methodological rigor and transparency. The findings reveal that supervised learning methods, such as decision trees, logistic regression, and support vector machines, remain the dominant paradigm due to their interpretability and established performance, while unsupervised anomaly detection approaches are increasingly adopted to address novel fraud patterns in highly imbalanced datasets. Deep learning architectures, particularly recurrent and convolutional neural networks, have emerged as transformative tools capable of modeling sequential transaction data and detecting complex fraud typologies, though challenges of interpretability and real-time deployment persist. Hybrid models that combine supervised, unsupervised, and deep learning strategies demonstrate superior adaptability and detection accuracy, highlighting their potential as convergent solutions.

Large language models (LLMs) are solidifying their position in the modern world as effective tools for the automatic generation of text. Their use is quickly becoming commonplace in fields such as education, healthcare, and scientific research. There is a growing need to study the linguistic features present in AI-generated text, as the increasing presence of such texts has profound implications in various disciplines such as corpus linguistics, computational linguistics, and natural language processing. Many observations have already been made, however a broader synthesis of the findings made so far is required to provide a better understanding of the topic. The present survey paper aims to provide such a synthesis of extant research. We categorize the existing works along several dimensions, including the levels of linguistic description, the models included, the genres analyzed, the languages analyzed, and the approach to prompting. Additionally, the same scheme is used to present the findings made so far and expose the current trends followed by researchers. Among the most-often reported findings is the observation that AI-generated text is more likely to contain a more formal and impersonal style, signaled by the increased presence of nouns, determiners, and adpositions and the lower reliance on adjectives and adverbs. AI-generated text is also more likely to feature a lower lexical diversity, a smaller vocabulary size, and repetitive text. Current research, however, remains heavily concentrated on English data and mostly on text generated by the GPT model family, highlighting the need for broader cross-linguistic and cross-model investigation. In most cases authors also fail to address the issue of prompt sensitivity, leaving much room for future studies that employ multiple prompt wordings in the text generation phase.

Synthetic data generated by large language models has become integral to modern NLP training pipelines, from bootstrapping reasoning capabilities to augmenting instruction-following datasets. While recent work demonstrates successful applications maintaining high external data ratios, systematic understanding of how synthetic data proportion affects model behavior across different scales remains limited. This paper presents a controlled empirical study examining model performance, calibration, and output characteristics when trained on varying synthetic-to-external data ratios. Using the Pythia model suite (410M-12B parameters) across five diverse tasks, we evaluate models after one to three training iterations with synthetic data proportions ranging from 0-50\%. Our key findings include: models maintain stable performance with up to 20\% synthetic data, but degradation accelerates beyond 30\%; larger models (6.9B-12B) show greater robustness to synthetic data than smaller models (410M-1.4B); calibration degradation precedes accuracy loss, providing an early warning signal; and task characteristics matter, with reasoning tasks degrading faster than retrieval tasks under synthetic data training. Importantly, we find that current best practices, such as those employed in STaR and Self-Instruct systems that maintain greater than 80\% external data, operate well within safe regimes identified by our experiments. We provide practical guidance for practitioners on synthetic data budgets based on model scale and task requirements, alongside detailed comparison with concurrent work including Shumailov et al.'s model collapse findings.

Head Start programs utilizing GoEngage face significant challenges when new or rotating staff attempt to locate appropriate Tasks (modules) on the platform homepage. These difficulties arise from domain-specific jargon (e.g., IFPA, DRDP), system-specific nomenclature (e.g., Application Pool), and the inherent limitations of lexical search in handling typos and varied word ordering. We propose a pragmatic hybrid semantic search system that synergistically combines lightweight typo-tolerant lexical retrieval, embedding-based vector similarity, and constrained large language model (LLM) re-ranking. Our approach leverages the organization's existing Task Repository and Knowledge Base infrastructure while ensuring trustworthiness through low false-positive rates, evolvability to accommodate terminological changes, and economic efficiency via intelligent caching, shortlist generation, and graceful degradation mechanisms. We provide a comprehensive framework detailing required resources, a phased implementation strategy with concrete milestones, an offline evaluation protocol utilizing curated test cases (Hit@K, Precision@K, Recall@K, MRR), and an online measurement methodology incorporating query success metrics, zero-result rates, and dwell-time proxies.