Large language models (LLMs) excel in text generation; however, these creative elements require heavy computation and are accompanied by a steep cost. Especially for targeted applications such as sales and marketing outreach, these costs are far from feasible. This paper introduces the concept of "Trained Miniatures" - Small Language Models(SLMs) fine-tuned for specific, high-value applications, generating similar domain-specific responses for a fraction of the cost.

Understanding the nuanced performance of machine learning models is essential for responsible deployment, especially in high-stakes domains like healthcare and finance. This paper introduces a novel framework, Conformalized Exceptional Model Mining, which combines the rigor of Conformal Prediction with the explanatory power of Exceptional Model Mining (EMM). The proposed framework identifies cohesive subgroups within data where model performance deviates exceptionally, highlighting regions of both high confidence and high uncertainty. We develop a new model class, mSMoPE (multiplex Soft Model Performance Evaluation), which quantifies uncertainty through conformal prediction's rigorous coverage guarantees. By defining a new quality measure, Relative Average Uncertainty Loss (RAUL), our framework isolates subgroups with exceptional performance patterns in multi-class classification and regression tasks. Experimental results across diverse datasets demonstrate the framework's effectiveness in uncovering interpretable subgroups that provide critical insights into model behavior. This work lays the groundwork for enhancing model interpretability and reliability, advancing the state-of-the-art in explainable AI and uncertainty quantification.

The rapid proliferation of large language models (LLMs) has intensified the requirement for reliable safety evaluation to uncover model vulnerabilities. To this end, numerous LLM safety evaluation benchmarks are proposed. However, existing benchmarks generally rely on labor-intensive manual curation, which causes excessive time and resource consumption. They also exhibit significant redundancy and limited difficulty. To alleviate these problems, we introduce SafetyFlow, the first agent-flow system designed to automate the construction of LLM safety benchmarks. SafetyFlow can automatically build a comprehensive safety benchmark in only four days without any human intervention by orchestrating seven specialized agents, significantly reducing time and resource cost. Equipped with versatile tools, the agents of SafetyFlow ensure process and cost controllability while integrating human expertise into the automatic pipeline. The final constructed dataset, SafetyFlowBench, contains 23,446 queries with low redundancy and strong discriminative power. Our contribution includes the first fully automated benchmarking pipeline and a comprehensive safety benchmark. We evaluate the safety of 49 advanced LLMs on our dataset and conduct extensive experiments to validate our efficacy and efficiency.

Evaluating automatically generated radiology reports remains a fundamental challenge due to the lack of clinically grounded, interpretable, and fine-grained metrics. Existing methods either produce coarse overall scores or rely on opaque black-box models, limiting their usefulness in real-world clinical workflows. We introduce RadReason, a novel evaluation framework for radiology reports that not only outputs fine-grained sub-scores across six clinically defined error types, but also produces human-readable justifications that explain the rationale behind each score. Our method builds on Group Relative Policy Optimization and incorporates two key innovations: (1) Sub-score Dynamic Weighting, which adaptively prioritizes clinically challenging error types based on live F1 statistics; and (2) Majority-Guided Advantage Scaling, which adjusts policy gradient updates based on prompt difficulty derived from sub-score agreement. Together, these components enable more stable optimization and better alignment with expert clinical judgment. Experiments on the ReXVal benchmark show that RadReason surpasses all prior offline metrics and achieves parity with GPT-4-based evaluations, while remaining explainable, cost-efficient, and suitable for clinical deployment. Code will be released upon publication.

Mental health disorders are a global crisis. While various datasets exist for detecting such disorders, there remains a critical gap in identifying individuals actively seeking help. This paper introduces a novel dataset, M-Help, specifically designed to detect help-seeking behavior on social media. The dataset goes beyond traditional labels by identifying not only help-seeking activity but also specific mental health disorders and their underlying causes, such as relationship challenges or financial stressors. AI models trained on M-Help can address three key tasks: identifying help-seekers, diagnosing mental health conditions, and uncovering the root causes of issues.

The development of Large Speech-Language Models (LSLMs) has been slowed by fragmented architectures and a lack of transparency, hindering the systematic comparison and reproducibility of research. Unlike in the vision-language domain, the LSLM field suffers from the common practice of releasing model weights without their corresponding training data and configurations. To address these critical gaps, we introduce LLaSO, the first fully open, end-to-end framework for large-scale speech-language modeling. LLaSO provides the community with three essential resources: (1) LLaSO-Align, a 12M-instance speech-text alignment corpus; (2) LLaSO-Instruct, a 13.5M-instance multi-task instruction-tuning dataset; and (3) LLaSO-Eval, a reproducible benchmark for standardized evaluation. To validate our framework, we build and release LLaSO-Base, a 3.8B-parameter reference model trained exclusively on our public data. It achieves a normalized score of 0.72, establishing a strong, reproducible baseline that surpasses comparable models. Our analysis reveals that while broader training coverage enhances performance, significant generalization gaps persist on unseen tasks, particularly in pure audio scenarios. By releasing the complete stack of data, benchmarks, and models, LLaSO establishes a foundational open standard to unify research efforts and accelerate community-driven progress in LSLMs. We release the code, dataset, pretrained models, and results in https://github.com/EIT-NLP/LLaSO.

Large Artificial Intelligence (AI) training workloads spanning several tens of thousands of GPUs present unique power management challenges. These arise due to the high variability in power consumption during the training. Given the synchronous nature of these jobs, during every iteration there is a computation-heavy phase, where each GPU works on the local data, and a communication-heavy phase where all the GPUs synchronize on the data. Because compute-heavy phases require much more power than communication phases, large power swings occur. The amplitude of these power swings is ever increasing with the increase in the size of training jobs. An even bigger challenge arises from the frequency spectrum of these power swings which, if harmonized with critical frequencies of utilities, can cause physical damage to the power grid infrastructure. Therefore, to continue scaling AI training workloads safely, we need to stabilize the power of such workloads. This paper introduces the challenge with production data and explores innovative solutions across the stack: software, GPU hardware, and datacenter infrastructure. We present the pros and cons of each of these approaches and finally present a multi-pronged approach to solving the challenge. The proposed solutions are rigorously tested using a combination of real hardware and Microsoft's in-house cloud power simulator, providing critical insights into the efficacy of these interventions under real-world conditions.

We introduce CUS-QA, a benchmark for open-ended regional question answering that encompasses both textual and visual modalities. We also provide strong baselines using state-of-the-art large language models (LLMs). Our dataset consists of manually curated questions and answers grounded in Wikipedia, created by native speakers from Czechia, Slovakia, and Ukraine, with accompanying English translations. It includes both purely textual questions and those requiring visual understanding. We evaluate state-of-the-art LLMs through prompting and complement this with human judgments of answer correctness. Using these human evaluations, we analyze the reliability of existing automatic evaluation metrics. Our baseline results show that even the best open-weight LLMs achieve only around 50% accuracy on textual questions and below 30% on visual questions. LLM-based evaluation metrics show strong correlation with human judgment, while traditional string-overlap metrics perform surprisingly well due to the prevalence of named entities in answers.

Control Flow Graphs (CFGs) are critical for analyzing program execution and characterizing malware behavior. With the growing adoption of Graph Neural Networks (GNNs), CFG-based representations have proven highly effective for malware detection. This study proposes a novel framework that dynamically constructs CFGs and embeds node features using a hybrid approach combining rule-based encoding and autoencoder-based embedding. A GNN-based classifier is then constructed to detect malicious behavior from the resulting graph representations. To improve model interpretability, we apply state-of-the-art explainability techniques, including GNNExplainer, PGExplainer, and CaptumExplainer, the latter is utilized three attribution methods: Integrated Gradients, Guided Backpropagation, and Saliency. In addition, we introduce a novel aggregation method, called RankFusion, that integrates the outputs of the top-performing explainers to enhance the explanation quality. We also evaluate explanations using two subgraph extraction strategies, including the proposed Greedy Edge-wise Composition (GEC) method for improved structural coherence. A comprehensive evaluation using accuracy, fidelity, and consistency metrics demonstrates the effectiveness of the proposed framework in terms of accurate identification of malware samples and generating reliable and interpretable explanations.

We propose an efficient hybrid least squares/gradient descent method to accelerate DeepONet training. Since the output of DeepONet can be viewed as linear with respect to the last layer parameters of the branch network, these parameters can be optimized using a least squares (LS) solve, and the remaining hidden layer parameters are updated by means of gradient descent form. However, building the LS system for all possible combinations of branch and trunk inputs yields a prohibitively large linear problem that is infeasible to solve directly. To address this issue, our method decomposes the large LS system into two smaller, more manageable subproblems $\unicode{x2014}$ one for the branch network and one for the trunk network $\unicode{x2014}$ and solves them separately. This method is generalized to a broader type of $L^2$ loss with a regularization term for the last layer parameters, including the case of unsupervised learning with physics-informed loss.