Related papers: SAGE: Sensor-Augmented Grounding Engine for LLM-Po…
Large Audio Language Models (LALMs) have been widely applied in real-time scenarios, such as in-car assistants and online meeting comprehension. In practice, audio inputs are often corrupted by device and environmental noise, leading to…
Large Language Models (LLM) are increasingly integrated into everyday interactions, serving not only as information assistants but also as emotional companions. Even in the absence of explicit toxicity, repeated emotional reinforcement or…
Recent studies observe that reinforcement learning with verifiable rewards (RLVR) reliably improves pass@1 on reasoning tasks, yet often fails to yield comparable gains in pass@k, raising the question of whether RLVR genuinely enables large…
This paper investigates the performance of various speech SSL models on dialectal Arabic (DA) and Arabic-English code-switched (CS) speech. To address data scarcity, a modified audio-splicing approach is introduced to generate artificial CS…
Personalization has become an essential capability in modern AI systems, enabling customized interactions that align with individual user preferences, contexts, and goals. Recent research has increasingly concentrated on Retrieval-Augmented…
Human Activity Recognition (HAR) using Inertial Measurement Unit (IMU) sensors is a cornerstone of mobile health, smart environments, and human-computer interaction. However, current deep learning-based HAR models often struggle with heavy…
The exponential growth of scientific knowledge has created significant barriers to cross-disciplinary knowledge discovery, synthesis and research collaboration. In response to this challenge, we present BioSage, a novel compound AI…
Large Language Models (LLMs) are increasingly explored as high-level reasoning engines for cyber-physical systems, yet their application to real-time UAV swarm management remains challenging due to heterogeneous interfaces, limited…
Recent advancements in large language models (LLMs) have significantly advanced the automation of software development tasks, including code synthesis, program repair, and test generation. More recently, researchers and industry…
Many human interactions, such as political debates, are carried out in group settings, where there are arbitrarily many participants, each with different views and agendas. To explore such complex social settings, we present SAUCE: a…
Motion sensor time-series are central to Human Activity Recognition (HAR), yet conventional approaches are constrained to fixed activity sets and typically require costly parameter retraining to adapt to new behaviors. While Large Language…
Generative Large Language Models (LLMs) hold significant promise in healthcare, demonstrating capabilities such as passing medical licensing exams and providing clinical knowledge. However, their current use as information retrieval tools…
Large Language Models (LLMs) have been increasingly adopted for health-related tasks, yet their performance in depression detection remains limited when relying solely on text input. While Retrieval-Augmented Generation (RAG) typically…
Simulating student learning behaviors in open-ended problem-solving environments holds potential for education research, from training adaptive tutoring systems to stress-testing pedagogical interventions. However, collecting authentic data…
Despite recent advancements in Large Language Models (LLMs), complex Software Engineering (SE) tasks require more collaborative and specialized approaches. This concept paper systematically reviews the emerging paradigm of LLM-based…
Improving Sparse Autoencoders (SAEs) requires benchmarks that can precisely validate architectural innovations. However, current SAE benchmarks on LLMs are often too noisy to differentiate architectural improvements, and current synthetic…
Accessibility remains a critical concern in today's society, as many technologies are not developed to support the full range of user needs. Existing multi-agent systems (MAS) often cannot provide comprehensive assistance for users in need…
The current paper presents the development and validation of SelfScore, a novel benchmark designed to assess the performance of automated Large Language Model (LLM) agents on help desk and professional consultation tasks. Given the…
Large Language Models (LLMs) have become foundational tools in artificial intelligence, supporting a wide range of applications beyond traditional natural language processing, including urban systems and tourist recommendations. However,…
Advances in mobile and wearable technologies have enabled the potential to passively monitor a person's mental, behavioral, and affective health. These approaches typically rely on longitudinal collection of self-reported outcomes, e.g.,…