6 papers
UpSafeC: Upcycling for Controllable Safety in Large Language Models
Yuhao Sun, Zhuoer Xu, Shiwen Cui +4
Large Language Models (LLMs) have achieved remarkable progress across a wide range of tasks, but remain vulnerable to safety risks such as harmful content generation and jailbreak…
IGD: Instructional Graphic Design with Multimodal Layer Generation
Yadong Qu, Shancheng Fang, Yuxin Wang +4
Graphic design visually conveys information and data by creating and combining text, images and graphics. Two-stage methods that rely primarily on layout generation lack creativity…
SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability
Jiankang Wang, Zhihan Zhang, Zhihang Liu +4
Multimodal large language models (MLLMs) have made remarkable progress in either temporal or spatial localization. However, they struggle to perform spatio-temporal video grounding…
MaskDiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generation
Tianhao Qi, Jianlong Yuan, Wanquan Feng +6
Sora has unveiled the immense potential of the Diffusion Transformer (DiT) architecture in single-scene video generation. However, the more challenging task of multi-scene video ge…
Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing
Yadong Qu, Yuxin Wang, Bangbang Zhou +3
Existing scene text recognition (STR) methods struggle to recognize challenging texts, especially for artistic and severely distorted characters. The limitation lies in the insuffi…
DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection
Yuhao Sun, Lingyun Yu, Hongtao Xie +2
With the rapid development of face recognition (FR) systems, the privacy of face images on social media is facing severe challenges due to the abuse of unauthorized FR systems. Som…