Accurate Prediction of Ligand-Protein Interaction Affinities with Fine-Tuned Small Language Modelsby Ben FauberFirst submitted to…
STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answeringby Guohao Sun, Can Qin, Huazhu…
Zero-shot domain adaptation based on dual-level mix and contrastby Yu Zhe, Jun SakumaFirst submitted to…
Segment Anything Model for automated image data annotation: empirical studies using text prompts from Grounding…
Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiTby Le Zhuo, Ruoyi Du, Han Xiao, Yangguang…
Composition Vision-Language Understanding via Segment and Depth Anything Modelby Mingxiao Huo, Pengliang Ji, Haotian Lin,…
The Overcooked Generalisation Challengeby Constantin Ruhdorfer, Matteo Bortoletto, Anna Penzkofer, Andreas BullingFirst submitted to arxiv…
Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIPby Sedigheh Eslami, Gerard de…
LaTable: Towards Large Tabular Modelsby Boris van Breugel, Jonathan Crabbé, Rob Davis, Mihaela van der…
Anomaly Detection of Tabular Data Using LLMsby Aodong Li, Yunhan Zhao, Chen Qiu, Marius Kloft,…