2 citations · 2 across the 4 of their papers we have counts for
5 papers
Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization
Mengqi He, Xinyu Tian, Xin Shen +6
Recent studies show that gradient-based universal image jailbreaks on vision-language models (VLMs) exhibit little or no cross-model transferability, casting doubt on the feasibili…
High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models
Mengqi He, Xinyu Tian, Xin Shen +4
Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertainty, is highly correlated with VLM…
What Makes for Text to 360-degree Panorama Generation with Stable Diffusion?
Jinhong Ni, Chang-Bin Zhang, Qiang Zhang +1
Recent prosperity of text-to-image diffusion models, e.g. Stable Diffusion, has stimulated research to adapt them to 360-degree panorama generation. Prior work has demonstrated the…
v-CLR: View-Consistent Learning for Open-World Instance Segmentation
Chang-Bin Zhang, Jinhong Ni, Yujie Zhong +1
In this paper, we address the challenging problem of open-world instance segmentation. Existing works have shown that vanilla visual networks are biased toward learning appearance…
Deep Equilibrium Multimodal Fusion
Jinhong Ni, Yalong Bai, Wei Zhang +2
Multimodal fusion integrates the complementary information present in multiple modalities and has gained much attention recently. Most existing fusion approaches either learn a fix…