Semantic-Rearrangement-Based Multi-Level Alignment for Domain Generalized Segmentationby Guanlong Jiao, Chenyangguang Zhang, Haonan Yin, Yu Mo,…
Listen Then See: Video Alignment with Speaker Attentionby Aviral Agrawal, Carlos Mateo Samudio Lezcano, Iqui…
Ethical-Lens: Curbing Malicious Usages of Open-Source Text-to-Image Modelsby Yuzhu Cai, Sheng Yin, Yuxi Wei, Chenxin…
When are Foundation Models Effective? Understanding the Suitability for Pixel-Level Classification Using Multispectral Imageryby Yiqun…
OTCXR: Rethinking Self-supervised Alignment using Optimal Transport for Chest X-ray Analysisby Vandan Gorade, Azad Singh,…
FedPFT: Federated Proxy Fine-Tuning of Foundation Modelsby Zhaopeng Peng, Xiaoliang Fan, Yufan Chen, Zheng Wang,…
Prompt Optimizer of Text-to-Image Diffusion Models for Abstract Concept Understandingby Zezhong Fan, Xiaohan Li, Chenhao…
Exploring the Transferability of Visual Prompting for Multimodal Large Language Modelsby Yichi Zhang, Yinpeng Dong,…
Stepwise Alignment for Constrained Language Model Policy Optimizationby Akifumi Wachi, Thien Q. Tran, Rei Sato,…
Self-Supervised Visual Preference Alignmentby Ke Zhu, Zheng Ge, Liang Zhao, Xiangyu ZhangFirst submitted to arxiv…