arXiv:2508.16198v3 Announce Type: replace
Abstract: Multimodal Large Language Models (MLLMs) have increasingly supported omni-modal processing across text, vision, and speech. However, existing evaluation frameworks for such models suffer from critica…
arXiv:2604.25387v1 Announce Type: cross
Abstract: Direction-of-arrival (DOA) estimation is an important task in microphone array processing and many downstream applications. The steered response power with phase transform (SRP-PHAT) method has been wi…
arXiv:2604.25053v1 Announce Type: new
Abstract: While large language models (LLMs) are increasingly being explored for mental health applications, recent studies reveal that they can exhibit stigma toward individuals with psychological conditions. Exi…
arXiv:2604.25720v1 Announce Type: cross
Abstract: Despite strong performance of deep learning models in retinal disease detection, most systems produce static predictions without clinical reasoning or interactive explanation. Recent advances in multim…
arXiv:2604.24831v1 Announce Type: cross
Abstract: Deep Learning methods are becoming prominent in automated software bug detection; however, they lack the global understanding of the given code. Consequently, their performance tends to degrade, especi…
arXiv:2604.20191v2 Announce Type: replace-cross
Abstract: Interpretable driver attention prediction is crucial for human-like autonomous driving. However, existing datasets provide only scene-level global gaze rather than fine-grained object-level ann…
arXiv:2604.25096v1 Announce Type: new
Abstract: There is growing concern that AI chatbots might fuel delusional beliefs in users. Some have suggested that humans and chatbots mutually reinforce false beliefs over time, but quantitative evidence is lac…
arXiv:2604.24833v1 Announce Type: cross
Abstract: Despite transformative advances in generative motion synthesis, real-time interactive motion control remains dominated by traditional techniques. In this work, we identify two key challenges in bridgin…
arXiv:2602.15547v2 Announce Type: replace
Abstract: Text embedding models are widely used for semantic similarity tasks, including information retrieval, clustering, and classification. General-purpose models are typically trained with single- or mult…
arXiv:2604.24811v1 Announce Type: new
Abstract: Graph neural Ordinary Differential Equations (ODE) combine neural ODE with the message passing mechanism of Graph Neural Networks (GNN), providing a continuous-time modeling method for graph representati…