EVLM: Self-reflective Multimodal Reasoning and KTO Alignment for Cross-Dimensional Visual Editing

Communications in computer and information science 2026

View at publisher

Authors: Umar Khalid, Kashif Munir, Hasan Iqbal, Azib Farooq, Jing Hua, Nazanin Rahnavard, Chen Chen, Victor Zhu, Zhengping Ji

DOI: 10.1007/978-3-032-16893-1_8

Cited by: 0

References: 52

Fields of Study & Subjects

Multimodal Machine Learning Applications Generative Adversarial Networks and Image Synthesis Advanced Neural Network Applications

References 52