Algorithmic bias in medical imaging can perpetuate health disparities, yet its causes remain poorly understood in segmentation tasks. While fairness has been extensively studied in classification, segmentation remains underexplored despite its clinical importance. In breast cancer segmentation, models exhibit significant performance disparities against younger patients, commonly attributed to physiological differences in breast density. We audit the MAMA-MIA dataset, establishing a quantitative baseline of age-related bias in its automated labels, and reveal a critical Biased Ruler effect where systematically flawed labels for validation misrepresent a model's actual bias. However, whether this bias originates from lower-quality annotations (label bias) or from fundamentally more challenging image characteristics remains unclear. Through controlled experiments, we systematically refute hypotheses that the bias stems from label quality sensitivity or quantitative case difficulty imbalance. Balancing training data by difficulty fails to mitigate the disparity, revealing that younger patient cases are intrinsically harder to learn. We provide direct evidence that systemic bias is learned and amplified when training on biased, machine-generated labels, a critical finding for automated annotation pipelines. This work introduces a systematic framework for diagnosing algorithmic bias in medical segmentation and demonstrates that achieving fairness requires addressing qualitative distributional differences rather than merely balancing case counts.

Abstract--We present MH-1M, one of the most comprehensive and up-to-date datasets for advanced Android malware research. The dataset comprises 1,340,515 applications, encompassing a wide range of features and extensive metadata. T o ensure accurate malware classification, we employ the VirusT otal API, integrating multiple detection engines for comprehensive and reliable assessment. Our GitHub, Figshare, and Harvard Dataverse repositories provide open access to the processed dataset and its extensive supplementary metadata, totaling more than 400 GB of data and including the outputs of the feature extraction pipeline as well as the corresponding VirusT otal reports. Our findings underscore the MH-1M dataset's invaluable role in understanding the evolving landscape of malware. The pervasive spread of Android malware poses a significant challenge for cybersecurity research. This challenge stems mainly from the open-source nature and affordability of Android platforms, which grant users access to a large market of free applications. At the same time, malware continually evolves, adapting its tactics to execute more sophisticated and frequent attacks. Such attacks often result in data destruction, information theft, and several other cybercrimes [1], [2], [3]. Machine learning (ML) algorithms have been widely used to uncover malware and have demonstrated remarkable effectiveness in detection systems, leveraging their discriminative capabilities to identify new variants of malicious applications [4], [5], [6]. To mitigate these risks, researchers have developed a variety of methods for detecting Android malware, establishing machine learning as a central focus of contemporary mobile security research [7], [8], [9]. However, the effectiveness of ML models is highly dependent on the quality of the datasets used for training. Many existing datasets suffer from limitations such as outdated data, inadequate representation, and a limited number of samples and features, making them unsuitable for modern malware detection [10], [2], [11], [12]. These issues raise concerns about the reliability of reported performance metrics and can potentially lead to misleading conclusions [2]. A growing body of research in Android malware detection strongly supports the notion that increasing the number of discriminative features can significantly improve classification performance [13], [14], [15]. We present in Table I an overview of widely used Android malware datasets from recent years.

Artificial intelligence systems based on large language models (LLMs) can now generate coherent text, music, and images, yet they operate without a persistent state: each inference reconstructs context from scratch. This paper introduces the Narrative Continuity Test (NCT) -- a conceptual framework for evaluating identity persistence and diachronic coherence in AI systems. Unlike capability benchmarks that assess task performance, the NCT examines whether an LLM remains the same interlocutor across time and interaction gaps. The framework defines five necessary axes -- Situated Memory, Goal Persistence, Autonomous Self-Correction, Stylistic & Semantic Stability, and Persona/Role Continuity -- and explains why current architectures systematically fail to support them. Case analyses (Character.\,AI, Grok, Replit, Air Canada) show predictable continuity failures under stateless inference. The NCT reframes AI evaluation from performance to persistence, outlining conceptual requirements for future benchmarks and architectural designs that could sustain long-term identity and goal coherence in generative models.

The rapid development of Vision-language models (VLMs) enables open-ended perception and reasoning. Recent works have started to investigate how to adapt general-purpose VLMs into personalized assistants. Even commercial models such as ChatGPT now support model personalization by incorporating user-specific information. However, existing methods either learn a set of concept tokens or train a VLM to utilize user-specific information. However, both pipelines struggle to generate accurate answers as personalized assistants. We introduce Jarvis, an innovative framework for a personalized AI assistant through personal KV-Cache retrieval, which stores user-specific information in the KV-Caches of both textual and visual tokens. The textual tokens are created by summarizing user information into metadata, while the visual tokens are produced by extracting distinct image patches from the user's images. When answering a question, Jarvis first retrieves related KV-Caches from personal storage and uses them to ensure accuracy in responses. We also introduce a fine-grained benchmark built with the same distinct image patch mining pipeline, emphasizing accurate question answering based on fine-grained user-specific information. Jarvis is capable of providing more accurate responses, particularly when they depend on specific local details. Jarvis achieves state-of-the-art results in both visual question answering and text-only tasks across multiple datasets, indicating a practical path toward personalized AI assistants. The code and dataset will be released.

This paper introduces a new shape-matching methodology, combinative matching, to combine interlocking parts for geometric shape assembly. Previous methods for geometric assembly typically rely on aligning parts by finding identical surfaces between the parts as in conventional shape matching and registration. Specifically, we explicitly model two distinct properties of interlocking shapes: 'identical surface shape' and'opposite volume occupancy. ' Our method thus learns to establish correspondences across regions where their surface shapes appear identical but their volumes occupy the inverted space to each other . T o facilitate this process, we also learn to align regions in rotation by estimating their shape orientations via equivariant neural networks. The proposed approach significantly reduces local ambiguities in matching and allows a robust combination of parts in assembly. Experimental results on geometric assembly benchmarks demonstrate the efficacy of our method, consistently outperforming the state of the art.

Background: Medical coding structures healthcare data for research, quality monitoring, and policy. This study assesses the potential of large language models (LLMs) to assign ICPC-2 codes using the output of a domain-specific search engine. Methods: A dataset of 437 Brazilian Portuguese clinical expressions, each annotated with ICPC-2 codes, was used. A semantic search engine (OpenAI's text-embedding-3-large) retrieved candidates from 73,563 labeled concepts. Thirty-three LLMs were prompted with each query and retrieved results to select the best-matching ICPC-2 code. Performance was evaluated using F1-score, along with token usage, cost, response time, and format adherence. Results: Twenty-eight models achieved F1-score > 0.8; ten exceeded 0.85. Top performers included gpt-4.5-preview, o3, and gemini-2.5-pro. Retriever optimization can improve performance by up to 4 points. Most models returned valid codes in the expected format, with reduced hallucinations. Smaller models (<3B) struggled with formatting and input length. Conclusions: LLMs show strong potential for automating ICPC-2 coding, even without fine-tuning. This work offers a benchmark and highlights challenges, but findings are limited by dataset scope and setup. Broader, multilingual, end-to-end evaluations are needed for clinical validation.

The rapid advancement of generative AI has provided users with a wide range of well-trained models to address diverse prompts. When selecting a model for a given prompt, users should weigh not only its performance but also its service cost. However, existing model-selection methods typically emphasize performance while overlooking cost differences. In this paper, we introduce PromptWise, an online learning framework that assigns prompts to generative models in a cost-aware manner. PromptWise estimates prompt-model compatibility to select the least expensive model expected to deliver satisfactory outputs. Unlike standard contextual bandits that make a one-shot decision per prompt, PromptWise employs a cost-aware bandit structure that allows sequential model assignments per prompt to reduce total service cost. Through numerical experiments on tasks such as code generation and translation, we demonstrate that PromptWise can achieve performance comparable to baseline selection methods while incurring substantially lower costs. The code is available at: github.com/yannxiaoyanhu/PromptWise.

What is the shortest path between two data points lying in a high-dimensional space? While the answer is trivial in Euclidean geometry, it becomes significantly more complex when the data lies on a curved manifold -- requiring a Riemannian metric to describe the space's local curvature. Estimating such a metric, however, remains a major challenge in high dimensions. In this work, we propose a method for deriving Riemannian metrics directly from pretrained Energy-Based Models (EBMs) -- a class of generative models that assign low energy to high-density regions. These metrics define spatially varying distances, enabling the computation of geodesics -- shortest paths that follow the data manifold's intrinsic geometry. We introduce two novel metrics derived from EBMs and show that they produce geodesics that remain closer to the data manifold and exhibit lower curvature distortion, as measured by alignment with ground-truth trajectories. We evaluate our approach on increasingly complex datasets: synthetic datasets with known data density, rotated character images with interpretable geometry, and high-resolution natural images embedded in a pretrained VAE latent space. Our results show that EBM-derived metrics consistently outperform established baselines, especially in high-dimensional settings. Our work is the first to derive Riemannian metrics from EBMs, enabling data-aware geodesics and unlocking scalable, geometry-driven learning for generative modeling and simulation.

We introduce GreekBarBench, a benchmark that evaluates LLMs on legal questions across five different legal areas from the Greek Bar exams, requiring citations to statutory articles and case facts. To tackle the challenges of free-text evaluation, we propose a three-dimensional scoring system combined with an LLM-as-a-judge approach. We also develop a meta-evaluation benchmark to assess the correlation between LLM-judges and human expert evaluations, revealing that simple, span-based rubrics improve their alignment. Our systematic evaluation of 13 proprietary and open-weight LLMs shows that even though the best models outperform average expert scores, they fall short of the 95th percentile of experts.

This paper is the first investigation of the connection between emotion, embodiment, and everyday language in a large sample of natural language data. We created corpora of body part mentions (BPMs) in online English text (blog posts and tweets). This includes a subset featuring human annotations for the emotions of the person whose body part is mentioned in the text. We show that BPMs are common in personal narratives and tweets (~5% to 10% of posts include BPMs) and that their usage patterns vary markedly by time and %geographic location. Using word-emotion association lexicons and our annotated data, we show that text containing BPMs tends to be more emotionally charged, even when the BPM is not explicitly used to describe a physical reaction to the emotion in the text. Finally, we discover a strong and statistically significant correlation between body-related language and a variety of poorer health outcomes. In sum, we argue that investigating the role of body-part related words in language can open up valuable avenues of future research at the intersection of NLP, the affective sciences, and the study of human wellbeing.