Evaluating Large Language Models' (LLMs) anthropomorphic capabilities has

These observations suggest that monocular 3D object detection heavily relies on object depth quality; nevertheless, conventional methods yield unsatisfactory results due to the extraction of less-discriminative features for object depth inference.

Privacy has nowadays become a major concern in large-scale data processing. Releasing seemingly harmless statistics of a dataset could unexpectedly leak sensitive information of individuals (see e.g.

The central task of interpretability research is to explain the functions that AI systems learn from data. Investigating these functions requires experimentation with trained models, using tools that incorporate varying degrees of human input. Hand-tooled approaches that rely on close manual inspection [Zeiler and Fergus, 2014, Zhou et al., 2014, Mahendran and V edaldi, 2015, Olah et al., 2017, 2020, Elhage et al., 2021] or search for predefined phenomena [Wang et al., 2022, Nanda

Data-driven methods for electrocardiogram (ECG) interpretation are rapidly progressing. Large datasets have enabled advances in artificial intelligence (AI) based ECG analysis, yet limitations in annotation quality, size, and scope remain major challenges. Here we present CODE-II, a large-scale real-world dataset of 2,735,269 12-lead ECGs from 2,093,807 adult patients collected by the Telehealth Network of Minas Gerais (TNMG), Brazil. Each exam was annotated using standardized diagnostic criteria and reviewed by cardiologists. A defining feature of CODE-II is a set of 66 clinically meaningful diagnostic classes, developed with cardiologist input and routinely used in telehealth practice. We additionally provide an open available subset: CODE-II-open, a public subset of 15,000 patients, and the CODE-II-test, a non-overlapping set of 8,475 exams reviewed by multiple cardiologists for blinded evaluation. A neural network pre-trained on CODE-II achieved superior transfer performance on external benchmarks (PTB-XL and CPSC 2018) and outperformed alternatives trained on larger datasets.

This technical report investigates the performance of pre-trained audio models on COVID-19 detection tasks using established benchmark datasets. We fine-tuned Audio-MAE and three PANN architectures (CNN6, CNN10, CNN14) on the Coswara and COUGHVID datasets, evaluating both intra-dataset and cross-dataset generalization. We implemented a strict demographic stratification by age and gender to prevent models from exploiting spurious correlations between demographic characteristics and COVID-19 status. Intra-dataset results showed moderate performance, with Audio-MAE achieving the strongest result on Coswara (0.82 AUC, 0.76 F1-score), while all models demonstrated limited performance on Coughvid (AUC 0.58-0.63). Cross-dataset evaluation revealed severe generalization failure across all models (AUC 0.43-0.68), with Audio-MAE showing strong performance degradation (F1-score 0.00-0.08). Our experiments demonstrate that demographic balancing, while reducing apparent model performance, provides more realistic assessment of COVID-19 detection capabilities by eliminating demographic leakage - a confounding factor that inflate performance metrics. Additionally, the limited dataset sizes after balancing (1,219-2,160 samples) proved insufficient for deep learning models that typically require substantially larger training sets. These findings highlight fundamental challenges in developing generalizable audio-based COVID-19 detection systems and underscore the importance of rigorous demographic controls for clinically robust model evaluation.

In this study, we evaluate open-source models for security incident classification, comparing them with proprietary models. We utilize a dataset of anonymized real incidents, categorized according to the NIST SP 800-61r3 taxonomy and processed using five prompt-engineering techniques (PHP, SHP, HTP, PRP, and ZSL). The results indicate that, although proprietary models still exhibit higher accuracy, locally deployed open-source models provide advantages in privacy, cost-effectiveness, and data sovereignty. According to CERT.br, Brazil reported over 516k security incidents in 2024 and more than 181k in the first half of 2025, underscoring a persistent upward trend that challenges SOCs and CSIRTs to manage high alert volumes efficiently [1]. To alleviate this overload, AI-driven solutions, particularly prompt-engineering techniques such as Progressive Hint Prompting (PHP), have demonstrated over 90% accuracy with models like GPT -4o and Gemini 2 [2].

Spontaneous speech presents several challenges for speech synthesis, particularly in capturing the natural flow of conversation, including turn-taking, pauses, and disfluencies. Although speech synthesis systems have made significant progress in generating natural and intelligible speech, primarily through architectures that implicitly model prosodic features such as pitch, intensity, and duration, the construction of datasets with explicit prosodic segmentation and their impact on spontaneous speech synthesis remains largely unexplored. This paper evaluates the effects of manual and automatic prosodic segmentation annotations in Brazilian Portuguese on the quality of speech synthesized by a non-autoregressive model, FastSpeech 2. Experimental results show that training with prosodic segmentation produced slightly more intelligible and acoustically natural speech. While automatic segmentation tends to create more regular segments, manual prosodic segmentation introduces greater variability, which contributes to more natural prosody. Analysis of neutral declarative utterances showed that both training approaches reproduced the expected nuclear accent pattern, but the prosodic model aligned more closely with natural pre-nuclear contours. To support reproducibility and future research, all datasets, source codes, and trained models are publicly available under the CC BY-NC-ND 4.0 license.

Today's large language models (LLMs) are capable of supporting multilingual scenarios, allowing users to interact with LLMs in their native languages. When LLMs respond to subjective questions posed by users, they are expected to align with the views of specific demographic groups or historical periods, shaped by the language in which the user interacts with the model. Existing studies mainly focus on researching the opinions represented by LLMs among demographic groups in the United States or a few countries, lacking worldwide country samples and studies on human opinions in different historical periods, as well as lacking discussion on using language to steer LLMs. Moreover, they also overlook the potential influence of prompt language on the alignment of LLMs' opinions. In this study, our goal is to fill these gaps. To this end, we create an evaluation framework based on the World Values Survey (WVS) to systematically assess the alignment of LLMs with human opinions across different countries, languages, and historical periods around the world. We find that LLMs appropriately or over-align the opinions with only a few countries while under-aligning the opinions with most countries. Furthermore, changing the language of the prompt to match the language used in the questionnaire can effectively steer LLMs to align with the opinions of the corresponding country more effectively than existing steering methods. At the same time, LLMs are more aligned with the opinions of the contemporary population. To our knowledge, our study is the first comprehensive investigation of the topic of opinion alignment in LLMs across global, language, and temporal dimensions. Our code and data are publicly available at https://github.com/ku-nlp/global-opinion-alignment and https://github.com/nlply/global-opinion-alignment.