3 papers
cs.CV2026
Customized Visual Storytelling with Unified Multimodal LLMs
Wei-Hua Li, Cheng Sun, Chu-Song Chen
Multimodal story customization aims to generate coherent story flows conditioned on textual descriptions, reference identity images, and shot types. While recent progress in story…
cs.CV2025
MotiF: Making Text Count in Image Animation with Motion Focal Loss
Shijie Wang, Samaneh Azadi, Rohit Girdhar +3
Text-Image-to-Video (TI2V) generation aims to generate a video from an image following a text description, which is also referred to as text-guided image animation. Most existing m…
cs.CV2025
Pre-trained Vision-Language Models Learn Discoverable Visual Concepts
Yuan Zang, Tian Yun, Hao Tan +2
Do vision-language models (VLMs) pre-trained to caption an image of a "durian" learn visual concepts such as "brown" (color) and "spiky" (texture) at the same time? We aim to answe…