8 papers
When Safety Overrides Vision: Exploring Dynamics between Vision Influence and Safety Alignment in Vision-Language Models
Mehak Gupta, Tanmoy Chakraborty
Aligned vision-language models (VLMs) are designed to balance grounded visual reasoning with safe generation behavior. However, we observe a striking phenomenon: under safety-const…
Fine-Tuned Multi-Agent Framework for Detecting OCEAN in Life Narratives
Rasiq Hussain, Darshil Italiya, Joshua Oltmanns +1
Accurately assessing personality from text is challenging because traits are latent, context-dependent, and often subtly expressed across long narratives. Large language models (LL…
Multimodal Routing for Interpretable, Robust, and Auditable Clinical Prediction
Nikkie Hooman, Zhongjie Wu, Eric C. Larson +1
Electronic health record (EHR) data are inherently multimodal, and leveraging multiple modalities can improve predictive performance. However, most existing approaches rely on deep…
Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures
Evangelos Ntavelis, Sean Wu, Mohamad Shahbazi +21
We propose HeadsUp, a scalable feed-forward method for reconstructing high-quality 3D Gaussian heads from large-scale multi-camera setups. Our method employs an efficient encoder-d…
Multilingual Language Models Encode Script Over Linguistic Structure
Aastha A K Verma, Anwoy Chatterjee, Mehak Gupta +1
Multilingual language models (LMs) organize representations for typologically and orthographically diverse languages into a shared parameter space, yet the nature of this internal…
"Mirror" Language AI Models of Depression are Criterion-Contaminated
Tong Li, Rasiq Hussain, Mehak Gupta +1
Recent studies show near-perfect language-based predictions of depression scores (R2 = .70), but these "Mirror" models rely on language responses directly from depression assessmen…