arXiv:2512.16891v1 Announce Type: cross Abstract: Video Large Language Models (VLLMs) unlock world-knowledge-aware video understanding through pretraining on internet-scale data and have already shown promise on tasks such as movie analysis and video question answering. However, deploying VLLMs for downstream tasks such as video recommendation remains challenging, since real systems require multi-video inputs, lightweight backbones, low-latency […]
C-DGPA: Class-Centric Dual-Alignment Generative Prompt Adaptation
arXiv:2512.16164v1 Announce Type: cross Abstract: Unsupervised Domain Adaptation transfers knowledge from a labeled source domain to an unlabeled target domain. Directly deploying Vision-Language Models (VLMs) with prompt tuning in downstream UDA tasks faces the signifi cant challenge of mitigating domain discrepancies. Existing prompt-tuning strategies primarily align marginal distribu tion, but neglect conditional distribution discrepancies, lead […]
MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual Questions
arXiv:2507.21503v3 Announce Type: replace Abstract: Recently Multimodal Large Language Models (MLLMs) have achieved considerable advancements in vision-language tasks, yet produce potentially harmful or untrustworthy content. Despite substantial work investigating the trustworthiness of language models, MMLMs’ capability to act honestly, especially when faced with visually unanswerable questions, remains largely underexplored. This work presents the first systematic […]
Uncovering Alzheimer’s Disease Progression via SDE-based Spatio-Temporal Graph Deep Learning on Longitudinal Brain Networks
arXiv:2509.21735v2 Announce Type: replace-cross Abstract: Identifying objective neuroimaging biomarkers to forecast Alzheimer’s disease (AD) progression is crucial for timely intervention. However, this task remains challenging due to the complex dysfunctions in the spatio-temporal characteristics of underlying brain networks, which are often overlooked by existing methods. To address these limitations, we develop an interpretable spatio-temporal graph […]
WildFit: Autonomous In-situ Model Adaptation for Resource-Constrained IoT Systems
arXiv:2409.07796v4 Announce Type: replace-cross Abstract: Resource-constrained IoT devices increasingly rely on deep learning models, however, these models experience significant accuracy drops due to domain shifts when encountering variations in lighting, weather, and seasonal conditions. While cloud-based retraining can address this issue, many IoT deployments operate with limited connectivity and energy constraints, making traditional fine-tuning approaches […]
Decoding Fake Narratives in Spreading Hateful Stories: A Dual-Head RoBERTa Model with Multi-Task Learning
arXiv:2512.16147v1 Announce Type: cross Abstract: Social media platforms, while enabling global connectivity, have become hubs for the rapid spread of harmful content, including hate speech and fake narratives citedavidson2017automated, shu2017fake. The Faux-Hate shared task focuses on detecting a specific phenomenon: the generation of hate speech driven by fake narratives, termed Faux-Hate. Participants are challenged to […]
Evaluating Large Language Models in Crisis Detection: A Real-World Benchmark from Psychological Support Hotlines
arXiv:2506.01329v2 Announce Type: replace-cross Abstract: Psychological support hotlines serve as critical lifelines for crisis intervention but encounter significant challenges due to rising demand and limited resources. Large language models (LLMs) offer potential support in crisis assessments, yet their effectiveness in emotionally sensitive, real-world clinical settings remains underexplored. We introduce PsyCrisisBench, a comprehensive benchmark of 540 […]
Speech-FT: Merging Pre-trained And Fine-Tuned Speech Representation Models For Cross-Task Generalization
arXiv:2502.12672v3 Announce Type: replace-cross Abstract: Fine-tuning speech representation models can enhance performance on specific tasks but often compromises their cross-task generalization ability. This degradation is often caused by excessive changes in the representations, making it difficult to retain information learned during pre-training. Existing approaches, such as regularizing weight changes during fine-tuning, may fail to maintain […]
Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies
arXiv:2505.21236v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) systems have countless applications, from energy-grid management to protein design. However, such real-world scenarios are often extremely difficult, combinatorial in nature, and require complex coordination between multiple agents. This level of complexity can cause even state-of-the-art RL systems, trained until convergence, to hit a performance ceiling which […]
Mathematical Insights into Protein Architecture: Persistent Homology and Machine Learning Applied to the Flagellar Motor
arXiv:2504.16941v5 Announce Type: replace Abstract: We present a machine learning approach that leverages persistent homology to classify bacterial flagellar motors into two functional states: rotated and stalled. By embedding protein structural data into a topological framework, we extract multiscale features from filtered simplicial complexes constructed over atomic coordinates. These topological invariants, specifically persistence diagrams and […]