Publications

Publications: 2026, 2025

2026

Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization
Mengqi He, Xinyu Tian, Xin Shen, Shu Zou, Jinhong Ni, Zhaoyuan Yang, Weikang Li, Xuesong Li, Jing Zhang
Transactions on Machine Learning Research (TMLR), 2026
[pdf]

Simple is Better than Complex: A Representation-centric Perspective for Prompting-based Vision-Language Fusion
Yujia Yin, Jinhong Ni, Renjie Wu, Hongji Li, Tianxin Wei, Zhong Li, Yifan Chen
Transactions on Machine Learning Research (TMLR), 2026
[pdf] [code]

2025

What Makes for Text to 360-degree Panorama Generation with Stable Diffusion?
Jinhong Ni, Chang-Bin Zhang, Qiang Zhang, Jing Zhang
IEEE/CVF International Conference on Computer Vision (ICCV), 2025
[pdf] [code]

v-CLR: View-Consistent Learning for Open-World Instance Segmentation
Chang-Bin Zhang, Jinhong Ni, Yujie Zhong, Kai Han
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025 (Highlight)
[pdf] [code]

Preprint

Few Tokens Matter: Entropy Guided Attacks on Vision-Language Models
Mengqi He, Xinyu Tian, Xin Shen, Jinhong Ni, Shu Zou, Zhaoyuan Yang, Jing Zhang
arXiv preprint, 2025
[pdf]

Deep Equilibrium Multimodal Fusion
Jinhong Ni, Yalong Bai, Wei Zhang, Ting Yao, Tao Mei
arXiv preprint, 2023
[pdf] [code]