PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignmentby Zhendong Liu, Yuanbi Nie, Yingshui Tan,…
ColorEdit: Training-free Image-Guided Color editing with diffusion modelby Xingxi Yin, Zhi Li, Jingfeng Zhang, Chenglin…
Increasing the Accessibility of Causal Domain Knowledge via Causal Information Extraction Methods: A Case Study…
Accelerating Knowledge Graph and Ontology Engineering with Large Language Modelsby Cogan Shimizu, Pascal HitzlerFirst submitted…
Multimodal Object Detection using Depth and Image Data for Manufacturing Partsby Nazanin Mahjourian, Vinh NguyenFirst…
DROJ: A Prompt-Driven Attack against Large Language Modelsby Leyang Hu, Boran WangFirst submitted to arxiv…
MIRe: Enhancing Multimodal Queries Representation via Fusion-Free Modality Interaction for Multimodal Retrievalby Yeong-Joon Ju, Ho-Joong…
Direct Preference Optimization Using Sparse Feature-Level Constraintsby Qingyu Yin, Chak Tou Leong, Hongbo Zhang, Minjun…
Fast Disentangled Slim Tensor Learning for Multi-view Clusteringby Deng Xu, Chao Zhang, Zechao Li, Chunlin…
Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMsby Megh Thakkar, Yash…