D.9 Parameter Size and Inference Speed . . . . . . . . . . . . . . . . . . . . . . . .

A unifying theme in the design of intelligent agents is to efficiently optimize a policy based on what prior knowledge of the problem is available and what actions can be taken to learn more about it.

Breakthroughs, discoveries, and DIY tips sent six days a week. In Mary Shelley's, a mad scientist creates a monstrous creature with severed body parts. In certain film adaptations, a dismembered head is tacked onto the malformed body. Then, with the help of a lightning storm, a new life is born. From the first successful kidney transplant in 1954, modern organ transplantation has often been linked to the horrors of Frankenstein .

Offline optimization has recently emerged as an increasingly popular approach to mitigate the prohibitively expensive cost of online experimentation. The key idea is to learn a surrogate of the black-box function that underlines the target experiment using a static (offline) dataset of its previous input-output queries. Such an approach is, however, fraught with an out-of-distribution issue where the learned surrogate becomes inaccurate outside the offline data regimes. To mitigate this, existing offline optimizers have proposed numerous conditioning techniques to prevent the learned surrogate from being too erratic. Nonetheless, such conditioning strategies are often specific to particular surrogate or search models, which might not generalize to a different model choice. This motivates us to develop a model-agnostic approach instead, which incorporates a notion of model sharpness into the training loss of the surrogate as a regularizer. Our approach is supported by a new theoretical analysis demonstrating that reducing surrogate sharpness on the offline dataset provably reduces its generalized sharpness on unseen data. Our analysis extends existing theories from bounding generalized prediction loss (on unseen data) with loss sharpness to bounding the worst-case generalized surrogate sharpness with its empirical estimate on training data, providing a new perspective on sharpness regularization. Our extensive experimentation on a diverse range of optimization tasks also shows that reducing surrogate sharpness often leads to significant improvement, marking (up to) a noticeable 9.6% performance boost.

Log-based anomaly detection (LAD) is critical for ensuring the reliability of large-scale distributed systems. However, most existing LAD approaches assume centralized training, which is often impractical due to privacy constraints and the decentralized nature of system logs. While federated learning (FL) offers a promising alternative, there is a lack of dedicated testbeds tailored to the needs of LAD in federated settings. To address this, we present FedLAD, a unified platform for training and evaluating LAD models under FL constraints. FedLAD supports plug-and-play integration of diverse LAD models, benchmark datasets, and aggregation strategies, while offering runtime support for validation logging (self-monitoring), parameter tuning (self-configuration), and adaptive strategy control (self-adaptation). By enabling reproducible and scalable experimentation, FedLAD bridges the gap between FL frameworks and LAD requirements, providing a solid foundation for future research. Project code is publicly available at: https://github.com/AA-cityu/FedLAD.

Foundation models (FMs) have opened new avenues for machine learning applications due to their ability to adapt to new and unseen tasks with minimal or no further training. Time-series foundation models (TSFMs) -- FMs trained on time-series data -- have shown strong performance on classification, regression, and imputation tasks. Recent pipelines combine TSFMs with task-specific encoders, decoders, and adapters to improve performance; however, assembling such pipelines typically requires ad hoc, model-specific implementations that hinder modularity and reproducibility. We introduce FMTK, an open-source, lightweight and extensible toolkit for constructing and fine-tuning TSFM pipelines via standardized backbone and component abstractions. FMTK enables flexible composition across models and tasks, achieving correctness and performance with an average of seven lines of code. https://github.com/umassos/FMTK

We introduce AIRHILT (Aviation Integrated Reasoning, Human-in-the-Loop Testbed), a modular and lightweight simulation environment designed to evaluate multimodal pilot and air traffic control (ATC) assistance systems for aviation conflict detection. Built on the open-source Godot engine, AIRHILT synchronizes pilot and ATC radio communications, visual scene understanding from camera streams, and ADS-B surveillance data within a unified, scalable platform. The environment supports pilot- and controller-in-the-loop interactions, providing a comprehensive scenario suite covering both terminal area and en route operational conflicts, including communication errors and procedural mistakes. AIRHILT offers standardized JSON-based interfaces that enable researchers to easily integrate, swap, and evaluate automatic speech recognition (ASR), visual detection, decision-making, and text-to-speech (TTS) models. We demonstrate AIRHILT through a reference pipeline incorporating fine-tuned Whisper ASR, YOLO-based visual detection, ADS-B-based conflict logic, and GPT-OSS-20B structured reasoning, and present preliminary results from representative runway-overlap scenarios, where the assistant achieves an average time-to-first-warning of approximately 7.7 s, with average ASR and vision latencies of approximately 5.9 s and 0.4 s, respectively. The AIRHILT environment and scenario suite are openly available, supporting reproducible research on multimodal situational awareness and conflict detection in aviation; code and scenarios are available at https://github.com/ogarib3/airhilt.

We develop an adaptive strategy to design indirect experiments that optimally inform a targeted query about the ground truth mechanism in terms of sequentially narrowing the gap between an upper and lower bound on the query.

Training an AI model to predict equipment failures is an engineering achievement. But it's not until prediction meets action--the moment that model successfully flags a malfunctioning machine--that true business transformation occurs. One technical milestone lives in a proof-of-concept deck; the other meaningfully contributes to the bottom line. Craig Partridge, senior director worldwide of Digital Next Advisory at HPE, believes the true value of AI lies in inference". Inference is where AI earns its keep. It's the operational layer that puts all that training to use in real-world workflows.

Abstract--Data dimensionality reduction techniques are often utilized in the implementation of Quantum Machine Learning models to address two significant issues: the constraints of NISQ quantum devices, which are characterized by noise and a limited number of qubits, and the challenge of simulating a large number of qubits on classical devices. It also raises concerns over the scalability of these approaches, as dimensionality reduction methods are slow to adapt to large datasets. In this article, we analyze how data reduction methods affect different QML models. We conduct this experiment over several generated datasets, quantum machine algorithms, quantum data encoding methods, and data reduction methods. All these models were evaluated on the performance metrics like accuracy, precision, recall, and F1 score. Our findings have led us to conclude that the usage of data dimensionality reduction methods results in skewed performance metric values, which results in wrongly estimating the actual performance of quantum machine learning models. There are several factors, along with data dimensionality reduction methods, that worsen this problem, such as characteristics of the datasets, classical to quantum information embedding methods, percentage of feature reduction, classical components associated with quantum models, and structure of quantum machine learning models. We consistently observed the difference in the accuracy range of 14% to 48% amongst these models, using data reduction and not using it. Apart from this, our observations have shown that some data reduction methods tend to perform better for some specific data embedding methodologies and ansatz constructions. In recent decades, there has been a significant push towards research and development of Quantum Machine Learning algorithms and models. Quantum Machine Learning has also been heralded as one of the prominent use cases for Quantum Computing devices. Several studies have shown the ability of QML models to solve difficult machine-learning problems and sometimes outperform the classical approach. Mostly, these proofs are either theoretical or simulated on classical devices. This is because the current quantum computational devices lack the required number of qubits, have questionable error correction ability, and tend to have noisy qubits.