13 papers
SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision
Zhaoxu Li, Chenqi Kong, Yi Yu +6
Large Vision-Language Models (LVLMs) recently achieve significant breakthroughs in understanding complex visual-textual contexts. However, hallucination issues still limit their re…
ChronoLock: Protecting Videos from Unauthorized Text-to-Video Personalization
Jiaming He, Jiashu Zhang, Guanyu Hou +4
Text-to-video (T2V) diffusion models have made it increasingly easy to synthesize realistic and temporally coherent videos, while recent personalization techniques allow such model…
Feature-Space Smoothing: Certified Robustness of Deep Representations
Song Xia, Meiwen Ding, Chenqi Kong +2
Modern deep learning models exhibit strong capabilities across diverse applications, yet remain vulnerable to malicious inputs that induce erroneous predictions via feature-space d…
Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization
Hui Lu, Yi Yu, Yiming Yang +6
Targeted adversarial attacks on closed-source multimodal large language models (MLLMs) have been increasingly explored under black-box transfer, yet prior methods are predominantly…
When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models
Hui Lu, Yi Yu, Yiming Yang +5
Vision-Language-Action (VLA) models are vulnerable to adversarial attacks, yet universal and transferable attacks remain underexplored, as most existing patches overfit to a single…
MambaTAD: When State-Space Models Meet Long-Range Temporal Action Detection
Hui Lu, Yi Yu, Shijian Lu +4
Temporal Action Detection (TAD) aims to identify and localize actions by determining their starting and ending frames within untrimmed videos. Recent Structured State-Space Models…