collaborators

6 papers

cs.CV2026

TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs

Kejia Zhang, Keda Tao, Zhiming Luo +3

Multimodal large language models (MLLMs) are prone to hallucinations, generating plausible but visually ungrounded outputs, partly because direct preference optimization (DPO) over…

cs.CV2026

A Survey of Token Compression for Efficient Multimodal Large Language Models

Kele Shao, Keda Tao, Kejia Zhang +7

Multimodal large language models (MLLMs) have made remarkable strides, largely driven by their ability to process increasingly long and complex contexts, such as high-resolution im…

cs.CV2025

MANI-Pure: Magnitude-Adaptive Noise Injection for Adversarial Purification

Xiaoyi Huang, Junwei Wu, Kejia Zhang +2

Adversarial purification with diffusion models has emerged as a promising defense strategy, but existing methods typically rely on uniform noise injection, which indiscriminately p…

cs.CV2025

Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment

Kejia Zhang, Juanjuan Weng, Shaozi Li +1

Despite the remarkable progress of deep neural networks (DNNs) in various visual tasks, their vulnerability to adversarial examples raises significant security concerns. Recent adv…

cs.CV2025

Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs

Kejia Zhang, Keda Tao, Jiasheng Tang +1

Large vision-language models (LVMs) extend large language models (LLMs) with visual perception capabilities, enabling them to process and interpret visual information. A major chal…

cs.CV2025

Mitigating Low-Frequency Bias: Feature Recalibration and Frequency Attention Regularization for Adversarial Robustness

Kejia Zhang, Juanjuan Weng, Yuanzheng Cai +2

Ensuring the robustness of deep neural networks against adversarial attacks remains a fundamental challenge in computer vision. While adversarial training (AT) has emerged as a pro…