52 citations · 60 across the 15 of their papers we have counts for
6 papers · 2 filters
FusionAudit: Pathway-Conditioned Robustness Auditing for Native Multimodal Models
Jiaming Zhang, Zherui Li, Siqi Guo +3
As vision-language models (VLMs) transition from frozen-encoder pipelines to native multimodal architectures, the visual channel increasingly serves as both a perceptual input and…
Forbid Your Attention: Fooling Multimodal Large Language Models by Selectively Removing Intrinsic Focus in Spectral Domain
Daizong Liu, Junhao Dong, Zhiyuan Ma +6
Multimodal large language models (MLLMs) have extended the capability of large language models (LLMs) to process more contextual multimodal information, showing remarkable progress…
EvTrajGS: Accurate and Efficient 3D Gaussian Splatting from Unposed Event Streams
Zixuan Chen, Jiakai Zhang, Junhao Dong +4
Event cameras, with high temporal resolution, high dynamic range, and asynchronous sensing characteristics, have shown great potential for dense 3D reconstruction. Traditional reco…
Unifying Adversarially Robust Model Experts in Vision-Language Models
Nguyen Duc Thai, Junhao Dong, Sua Qi Rong +2
Vision-language models (VLMs), such as CLIP, are vulnerable to adversarial attacks, posing a serious problem for real-life applications and deployment. Adversarial fine-tuning emer…
CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic
Shen Lin, Junhao Dong, Rongjie Chen +3
Vision-language models (VLMs) have shown remarkable ability in aligning visual and textual representations, enabling a wide range of multimodal applications. However, their large-s…
Hierarchically Robust Zero-shot Vision-language Models
Junhao Dong, Yifei Zhang, Hao Zhu +2
Vision-Language Models (VLMs) can perform zero-shot classification but are susceptible to adversarial attacks. While robust fine-tuning improves their robustness, existing approach…