In precision-sensitive classification tasks, false positives carry severe operational consequences. For example, when a text safety classifier incorrectly flags 10% of benign user queries as unsafe, it blocks legitimate queries from being processed, degrading the experience for millions of users and potentially driving them away from the service. Similarly, in hallucination detection within Retrieval-Augmented Generation (RAG) pipelines, when factually correct responses are incorrectly flagged as hallucinated, the system triggers regeneration or self-correction mechanisms, adding unnecessary computational overhead and latency that frustrates users waiting for responses. These deployment realities demand classifiers that operate at extremely low false positive rates--often below 1%--while maintaining acceptable recall. Large language models are increasingly deployed for such precision-critical classification tasks through specialized safety guardrails like Llama Guard (Inan et al., 2023) and ShieldGemma (Zeng et al., 2024), as well as hallucination detection systems (Huang et al., 2025). Recently, reasoning-augmented approaches have emerged as a promising direction: GuardReasoner (Liu et al., 2025) incorporates chain-of-thought reasoning for safety classification, while Lynx (Ravi et al., 2024) leverages reasoning for hallucination detection in RAG

The global scarcity of GPUs necessitates more sophisticated strategies for Deep Learning jobs in shared cluster environments. Accurate estimation of how much GPU memory a job will require is fundamental to enabling advanced scheduling and GPU sharing, which helps prevent out-of-memory (OOM) errors and resource underutilization. However, existing estimation methods have limitations. Approaches relying on static analysis or historical data with machine learning often fail to accurately capture runtime dynamics. Furthermore, direct GPU analysis consumes scarce resources, and some techniques require intrusive code modifications. Thus, the key challenge lies in precisely estimating dynamic memory requirements, including memory allocator nuances, without consuming GPU resources and non-intrusive code changes. To address this challenge, we propose xMem, a novel framework that leverages CPU-only dynamic analysis to accurately estimate peak GPU memory requirements a priori. We conducted a thorough evaluation of xMem against state-of-the-art solutions using workloads from 25 different models, including architectures like Convolutional Neural Networks and Transformers. The analysis of 5209 runs, which includes ANOVA and Monte Carlo results, highlights xMem's benefits: it decreases the median relative error by 91% and significantly reduces the probability of estimation failure as safe OOM thresholds by 75%, meaning that the estimated value can often be used directly without causing OOM. Ultimately, these improvements lead to a 368% increase in memory conservation potential over current solutions.

The emergence of foundation models (FMs) has enabled the development of highly capable and autonomous agents, unlocking new application opportunities across a wide range of domains. Evaluating the architecture of agents is particularly important as the architectural decisions significantly impact the quality attributes of agents given their unique characteristics, including compound architecture, autonomous and non-deterministic behaviour, and continuous evolution. However, these traditional methods fall short in addressing the evaluation needs of agent architecture due to the unique characteristics of these agents. Therefore, in this paper, we present AgentArcEval, a novel agent architecture evaluation method designed specially to address the complexities of FM-based agent architecture and its evaluation. Moreover, we present a catalogue of agent-specific general scenarios, which serves as a guide for generating concrete scenarios to design and evaluate the agent architecture. We demonstrate the usefulness of AgentArcEval and the catalogue through a case study on the architecture evaluation of a real-world tax copilot, named Luna.

Harmonizing medication data across Electronic Health Record (EHR) systems is a persistent barrier to monitoring medications for opioid use disorder (MOUD). In heterogeneous EHR systems, key prescription attributes are scattered across differently formatted fields and freetext notes. We present a practical framework that customizes open source large language models (LLMs), including Llama, Qwen, Gemma, and MedGemma, to extract a unified set of MOUD prescription attributes (prescription date, drug name, duration, total quantity, daily quantity, and refills) from heterogeneous, site specific data and compute a standardized metric of medication coverage, \emph{MOUD days}, per patient. Our pipeline processes records directly in a fixed JSON schema, followed by lightweight normalization and cross-field consistency checks. We evaluate the system on prescription level EHR data from five clinics in a national OUD study (25{,}605 records from 1{,}257 patients), using a previously annotated benchmark of 10{,}369 records (776 patients) as the ground truth. Performance is reported as coverage (share of records with a valid, matchable output) and record-level exact-match accuracy. Larger models perform best overall: Qwen2.5-32B achieves \textbf{93.4\%} coverage with \textbf{93.0\%} exact-match accuracy across clinics, and MedGemma-27B attains \textbf{93.1\%}/\textbf{92.2\%}. A brief error review highlights three common issues and fixes: imputing missing dosage fields using within-drug norms, handling monthly/weekly injectables (e.g., Vivitrol) by setting duration from the documented schedule, and adding unit checks to prevent mass units (e.g., ``250 g'') from being misread as daily counts. By removing brittle, site-specific ETL and supporting local, privacy-preserving deployment, this approach enables consistent cross-site analyses of MOUD exposure, adherence, and retention in real-world settings.

Generative AI tools are increasingly used to create portrayals of people in occupations, raising concerns about how race and gender are represented. We conducted a large-scale audit of over 1.5 million occupational personas across 41 U.S. occupations, generated by four large language models with different AI safety commitments and countries of origin (U.S., China, France). Compared with Bureau of Labor Statistics data, we find two recurring patterns: systematic shifts, where some groups are consistently under- or overrepresented, and stereotype exaggeration, where existing demographic skews are amplified. On average, White (--31pp) and Black (--9pp) workers are underrepresented, while Hispanic (+17pp) and Asian (+12pp) workers are overrepresented. These distortions can be extreme: for example, across all four models, Housekeepers are portrayed as nearly 100\% Hispanic, while Black workers are erased from many occupations. For HCI, these findings show provider choice materially changes who is visible, motivating model-specific audits and accountable design practices.

In response to the increasingly critical demand for accurate prediction of GPU memory resources in deep learning tasks, this paper deeply analyzes the current research status and innovatively proposes a deep learning model that integrates bidirectional gated recurrent units (BiGRU) to optimize the Transformer architecture, aiming to improve the accuracy of memory demand prediction. To verify the effectiveness of the model, a carefully designed comparative experiment was conducted, selecting four representative basic machine learning models: decision tree, random forest, Adaboost, and XGBoost as benchmarks. The detailed experimental results show that the BiGRU Transformer optimization model proposed in this paper exhibits significant advantages in key evaluation indicators: in terms of mean square error (MSE) and root mean square error (RMSE), the model achieves the lowest value among all comparison models, and its predicted results have the smallest deviation from the actual values; In terms of mean absolute error (MAE) and coefficient of determination (R2) indicators, the model also performs well and the results are balanced and stable, with comprehensive predictive performance far exceeding the benchmark machine learning methods compared. In summary, the Transformer model based on bidirectional gated recurrent unit optimization successfully constructed in this study can efficiently and accurately complete GPU memory demand prediction tasks in deep learning tasks, and its prediction accuracy has been significantly improved compared to traditional machine learning methods. This research provides strong technical support and reliable theoretical basis for optimizing resource scheduling and management of deep learning tasks, and improving the utilization efficiency of computing clusters.

On-device neural network training faces critical memory constraints that limit the adaptation of pre-trained models to downstream tasks. We present MeDyate, a theoretically-grounded framework for memory-constrained dynamic subnetwork adaptation. Our approach introduces two key innovations: LaRa (Layer Ranking), an improved layer importance metric that enables principled layer pre-selection, and a dynamic channel sampling strategy that exploits the temporal stability of channel importance distributions during fine-tuning. MeDyate dynamically resamples channels between epochs according to importance-weighted probabilities, ensuring comprehensive parameter space exploration while respecting strict memory budgets. Extensive evaluation across a large panel of tasks and architectures demonstrates that MeDyate achieves state-of-the-art performance under extreme memory constraints, consistently outperforming existing static and dynamic approaches while maintaining high computational efficiency. Our method represents a significant step towards enabling efficient on-device learning by demonstrating effective fine-tuning with memory budgets as low as a few hundred kB of RAM.

Large language models have demonstrated remarkable reasoning capabilities across diverse natural language tasks. However, comparable breakthroughs in scientific discovery are more limited, because understanding complex physical phenomena demands multifaceted representations far beyond language alone. A compelling example is the design of functional materials such as MOFs-critical for a range of impactful applications like carbon capture and hydrogen storage. Navigating their vast and intricate design space in language-based representations interpretable by LLMs is challenging due to the numerous possible three-dimensional atomic arrangements and strict reticular rules of coordination geometry and topology. Despite promising early results in LLM-assisted discovery for simpler materials systems, MOF design remains heavily reliant on tacit human expertise rarely codified in textual information alone. To overcome this barrier, we introduce L2M3OF, the first multimodal LLM for MOFs. L2M3OF integrates crystal representation learning with language understanding to process structural, textual, and knowledge modalities jointly. L2M3OF employs a pre-trained crystal encoder with a lightweight projection layer to compress structural information into a token space, enabling efficient alignment with language instructions. To facilitate training and evaluation, we curate a structure-property-knowledge database of crystalline materials and benchmark L2M3OF against state-of-the-art closed-source LLMs such as GPT-5, Gemini-2.5-Pro and DeepSeek-R1. Experiments show that L2M3OF outperforms leading text-based closed-source LLMs in property prediction and knowledge generation tasks, despite using far fewer parameters. These results highlight the importance of multimodal approaches for porous material understanding and establish L2M3OF as a foundation for next-generation AI systems in materials discovery.

Reverse engineering (RE) of x86 binaries is indispensable for malware and firmware analysis, but remains slow due to stripped metadata and adversarial obfuscation. Large Language Models (LLMs) offer potential for improving RE efficiency through automated comprehension and commenting, but cloud-hosted, closed-weight models pose privacy and security risks and cannot be used in closed-network facilities. We evaluate parameter-efficient fine-tuned local LLMs for assisting with x86 RE tasks in these settings. Eight open-weight models across the CodeLlama, Qwen2.5-Coder, and CodeGemma series are fine-tuned on a custom curated dataset of 5,981 x86 assembly examples. We evaluate them quantitatively and identify the fine-tuned Qwen2.5-Coder-7B as the top performer, which we name REx86. REx86 reduces test-set cross-entropy loss by 64.2% and improves semantic cosine similarity against ground truth by 20.3\% over its base model. In a limited user case study (n=43), REx86 significantly enhanced line-level code understanding (p = 0.031) and increased the correct-solve rate from 31% to 53% (p = 0.189), though the latter did not reach statistical significance. Qualitative analysis shows more accurate, concise comments with fewer hallucinations. REx86 delivers state-of-the-art assistance in x86 RE among local, open-weight LLMs. Our findings demonstrate the value of domain-specific fine-tuning, and highlight the need for more commented disassembly data to further enhance LLM performance in RE. REx86, its dataset, and LoRA adapters are publicly available at https://github.com/dlea8/REx86 and https://zenodo.org/records/15420461.

Current Vision-Language Models (VLMs) struggle to ground anatomical regions in 3D medical images and reason about them in a step-by-step manner, a key requirement of real-world diagnostic assessment. This ability is essential for aligning model outputs with the diagnostic workflows clinicians use in practice, enabling trustworthy clinician-AI collaboration. Existing 3D datasets provide localization labels, but none support this "grounded reasoning" ability. To address this gap, we introduce 3DReasonKnee, the first 3D grounded reasoning dataset for medical images, which provides 494k high-quality quintuples derived from 7,970 3D knee MRI volumes. Each quintuple includes: (1) the 3D MRI volume, (2) a diagnostic question targeting a specific anatomical region (3) a 3D bounding box localizing the relevant anatomical structures, (4) clinician-generated diagnostic reasoning steps that explicitly detail the 3D reasoning process, and (5) structured severity assessments for the relevant anatomical region. The creation and validation of 3DReasonKnee, involving over 450 hours of expert clinician time for manually segmenting MRIs and generating reasoning chains, ensures its superior quality and clinical relevance. We establish ReasonKnee-Bench to evaluate localization and diagnostic accuracy, providing insight into VLM ability to perform grounding and severity assessment across anatomical regions and diagnostic inquiries. We benchmark five state-of-the-art VLMs, providing baseline performance for ReasonKnee-Bench. By providing this unique resource of expert-annotated 3D reasoning pathways, 3DReasonKnee serves as a repository of orthopedic surgeons' diagnostic expertise and offers a vital testbed for advancing multimodal medical AI systems towards 3D, clinically aligned, localized decision-making capabilities. The dataset can be found in: https://huggingface.co/datasets/rajpurkarlab/3DReasonKnee