LLM-powered agents often use prompt compression to reduce inference costs, but this introduces a new security risk. Compression modules, which are optimized for efficiency rather than safety, can be manipulated by adversarial inputs, causing semantic drift and altering LLM behavior. This work identifies prompt compression as a novel attack surface and presents CompressionAttack, the first framework to exploit it. CompressionAttack includes two strategies: HardCom, which uses discrete adversarial edits for hard compression, and SoftCom, which performs latent-space perturbations for soft compression. Experiments on multiple LLMs show up to an average ASR of 83% and 87% in two tasks, while remaining highly stealthy and transferable. Case studies in three practical scenarios confirm real-world impact, and current defenses prove ineffective, highlighting the need for stronger protections.

Clustering on NISQ hardware is constrained by data loading and limited qubits. We present \textbf{qc-kmeans}, a hybrid compressive $k$-means that summarizes a dataset with a constant-size Fourier-feature sketch and selects centroids by solving small per-group QUBOs with shallow QAOA circuits. The QFF sketch estimator is unbiased with mean-squared error $O(\varepsilon^2)$ for $B,S=Θ(\varepsilon^{-2})$, and the peak-qubit requirement $q_{\text{peak}}=\max\{D,\lceil \log_2 B\rceil + 1\}$ does not scale with the number of samples. A refinement step with elitist retention ensures non-increasing surrogate cost. In Qiskit Aer simulations (depth $p{=}1$), the method ran with $\le 9$ qubits on low-dimensional synthetic benchmarks and achieved competitive sum-of-squared errors relative to quantum baselines; runtimes are not directly comparable. On nine real datasets (up to $4.3\times 10^5$ points), the pipeline maintained constant peak-qubit usage in simulation. Under IBM noise models, accuracy was similar to the idealized setting. Overall, qc-kmeans offers a NISQ-oriented formulation with shallow, bounded-width circuits and competitive clustering quality in simulation.

Identifying the determinants of academic success in basic education represents a central challenge for educational research and policymaking, particularly in a country with Brazil's vast dimensions and socioeconomic heterogeneity (Issah et al. 2023). A systemic approach is crucial, as student performance is influenced by a complex interplay of factors spanning individual, academic, socioeconomic, and institutional domains (Barrag an Moreno and Guzm an Rinc on 2025). The System of Assessment of Basic Education (SAEB), conducted by the National Institute for Educational Studies and Research An ısio Teixeira (INEP) (INEP 2025), provides a rich, multi-level dataset uniquely suited for such an analysis (Bonamino et al. 2010). The public availability of its anonymized microdata enables the research community to investigate the intricate relationships between student proficiency and a wide array of contextual factors, from socioeconomic backgrounds to school infrastructure and teacher profiles. Consequently, the SAEB microdata is an essential resource for data-driven research aimed at informing and evaluating educational policies in the country (Lundberg and Lee 2017b; Mazoni and Oliveira 2023). While traditional statistical methods are common, the Educational Data Mining (EDM) paradigm offers powerful tools for uncovering complex, non-linear patterns from such data (Romero and Ventura 2010). Furthermore, we demonstrate that by interpreting the model's classification results with XAI techniques, our method provides data-driven insights for educators and policymakers (Idrizi 2024). The primary objective of this research is thus to develop and evaluate a multi-level machine learning model to identify the key systemic factors associated with the academic performance of 9th-grade and high school students, using the SAEB microdata. Building upon this perspective, the study shifts its analytical focus from purely individual student interventions toward addressing the systemic determinants that shape educational outcomes in Brazilian basic education.

Despite a potential plateau in ML advancement, the societal impact of large language models lies not in approaching superintelligence but in generating text surfaces indistinguishable from human writing. While Critical AI Studies provides essential material and socio-technical critique, it risks overlooking how LLMs phenomenologically reshape meaning-making. This paper proposes a semiotics of "surface integrity" as attending to the immediate plane where LLMs inscribe themselves into human communication. I distinguish three knowledge interests in ML research (epistemology, epistēmē, and epistemics) and argue for integrating surface-level stylistic analysis alongside depth-oriented critique. Through two case studies examining stylistic markers of synthetic text, I argue how attending to style as a semiotic phenomenon reveals LLMs as cultural machines that transform the conditions of meaning emergence and circulation in contemporary discourse, independent of questions about machine consciousness.

We explore the use of expert-guided bandit learning, which we refer to as online mixture-of-experts (OMoE). In this setting, given a context, a candidate committee of experts must determine how to aggregate their outputs to achieve optimal results in terms of aggregate accuracy. We propose two algorithms to address this problem. The first algorithm combines aggregate voting with UCB-driven successive elimination, efficiently pruning suboptimal exploration actions. The second algorithm employs an online weighted-majority-voting mechanism, leveraging the respective voting power of each expert proportional to their predictive power. We derive theoretical guarantees for the regret properties in the bandit setting under ideal circumstances, and empirical results are provided accordingly. As a modern study on applications, these methods are applied to the online fine-tuning of a set of expert large language models (LLMs), where after each response, the generative LLM dynamically reweighs its set of experts and/or selects the optimal committee of experts to generate the most accurate response. Our results introduce new methodologies and no-regret guarantees for combining multiple experts to improve on the performance of the an aggregate model overall.

As generative AI continues to evolve, Vision Language Models (VLMs) have emerged as promising tools in various healthcare applications. One area that remains relatively underexplored is their use in human activity recognition (HAR) for remote health monitoring. VLMs offer notable strengths, including greater flexibility and the ability to overcome some of the constraints of traditional deep learning models. However, a key challenge in applying VLMs to HAR lies in the difficulty of evaluating their dynamic and often non-deterministic outputs. To address this gap, we introduce a descriptive caption data set and propose comprehensive evaluation methods to evaluate VLMs in HAR. Through comparative experiments with state-of-the-art deep learning models, our findings demonstrate that VLMs achieve comparable performance and, in some cases, even surpass conventional approaches in terms of accuracy. This work contributes a strong benchmark and opens new possibilities for the integration of VLMs into intelligent healthcare systems. Code and dataset are available at: https://github.com/gouga10/

Large Language Models (LLMs) often struggle with generating truly innovative ideas, typically defaulting to high-probability, familiar concepts within their training data's "gravity wells." While advanced search-based methods like Tree of Thoughts (ToT) attempt to mitigate this, they are fundamentally limited by their reliance on unprincipled, inconsistent self-evaluation heuristics to guide exploration. To address this gap, we introduce \textbf{Magellan}, a novel framework that reframes creative generation as a principled, guided exploration of an LLM's latent conceptual space. At its core, Magellan employs Monte Carlo Tree Search (MCTS) governed by a hierarchical guidance system. For long-range direction, a "semantic compass" vector, formulated via orthogonal projection, steers the search towards relevant novelty. For local, step-by-step decisions, a landscape-aware value function replaces flawed self-evaluation with an explicit reward structure that balances intrinsic coherence, extrinsic novelty, and narrative progress. Extensive experiments demonstrate that Magellan significantly outperforms strong baselines, including ReAct and ToT, in generating scientific ideas with superior plausibility and innovation. Our work shows that for creative discovery, a principled, guided search is more effective than unconstrained agency, paving the way for LLMs to become more capable partners in innovation.

LLMs often fail to handle temporal knowledge conflicts--contradictions arising when facts evolve over time within their training data. Existing studies evaluate this phenomenon through benchmarks built on structured knowledge bases like Wikidata, but they focus on widely-covered, easily-memorized popular entities and lack the dynamic structure needed to fairly evaluate LLMs with different knowledge cut-off dates. We introduce evolveQA, a benchmark specifically designed to evaluate LLMs on temporally evolving knowledge, constructed from 3 real-world, time-stamped corpora: AWS updates, Azure changes, and WHO disease outbreak reports. Our framework identifies naturally occurring knowledge evolution and generates questions with gold answers tailored to different LLM knowledge cut-off dates. Through extensive evaluation of 12 open and closed-source LLMs across 3 knowledge probing formats, we demonstrate significant performance drops of up to 31% on evolveQA compared to static knowledge questions.

There is growing interest in using machine learning (ML) to support clinical diagnosis, but most approaches rely on static, fully observed datasets and fail to reflect the sequential, resource-aware reasoning clinicians use in practice. Diagnosis remains complex and error prone, especially in high-pressure or resource-limited settings, underscoring the need for frameworks that help clinicians make timely and cost-effective decisions. We propose ACTMED (Adaptive Clinical Test selection via Model-based Experimental Design), a diagnostic framework that integrates Bayesian Experimental Design (BED) with large language models (LLMs) to better emulate real-world diagnostic reasoning. At each step, ACTMED selects the test expected to yield the greatest reduction in diagnostic uncertainty for a given patient. LLMs act as flexible simulators, generating plausible patient state distributions and supporting belief updates without requiring structured, task-specific training data. Clinicians can remain in the loop; reviewing test suggestions, interpreting intermediate outputs, and applying clinical judgment throughout. We evaluate ACTMED on real-world datasets and show it can optimize test selection to improve diagnostic accuracy, interpretability, and resource use. This represents a step toward transparent, adaptive, and clinician-aligned diagnostic systems that generalize across settings with reduced reliance on domain-specific data.

AI inference scaling is often tuned through 1D heuristics (a fixed reasoning pass) or 2D bivariate trade-offs (e.g., accuracy vs. compute), which fail to consider cost and latency constraints. We introduce a 3D optimization framework that jointly calibrates accuracy, cost, and latency within a unified decision space, enabling constraints-aware inference scaling. Using Monte Carlo simulations across three representative scenarios and nine simulated large language models, we evaluate four optimization methods to address the 3D multi-objective optimization (MOO) problem. Framing inference scaling in MOO shapes a feasible space that 1D and 2D optimizations fail to capture, enabling environment-adaptive selection of the inference scaling~$k$. Results show that knee-point optimization based on Pareto frontiers achieves the best balance, while accuracy-maximization remains favorable when accuracy is prioritized. Our results further show that smaller models, when combined with optimal inference scaling, can match or exceed the performance of larger models at a fraction of the cost. The framework establishes a theoretical foundation for deployment-aware inference scaling across diverse operational conditions.