3 citations · 5 across the 14 of their papers we have counts for
11 papers · 1 filter
Fast-Slow Efficient Training for Multimodal Large Language Models via Visual Token Pruning
Dingkun Zhang, Shuhan Qi, Yulin Wu +3
Multimodal Large Language Models (MLLMs) suffer from severe training inefficiency issue, which is associated with their massive model sizes and visual token numbers. Existing effor…
V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval
Dongyang Chen, Chaoyang Wang, Dezhao Su +6
Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improves candidate reranking. However,…
FMVP: Masked Flow Matching for Adversarial Video Purification
Duoxun Tang, Xueyi Zhang, Chak Hin Wang +6
Video recognition models remain vulnerable to adversarial attacks, while existing diffusion-based purification methods suffer from inefficient sampling and curved trajectories. Dir…
Attention-Guided Patch-Wise Sparse Adversarial Attacks on Vision-Language-Action Models
Naifu Zhang, Wei Tao, Xi Xiao +5
In recent years, Vision-Language-Action (VLA) models in embodied intelligence have developed rapidly. However, existing adversarial attack methods require costly end-to-end trainin…
FeatureFool: Zero-Query Fooling of Video Models via Feature Map
Duoxun Tang, Xi Xiao, Guangwu Hu +6
The vulnerability of deep neural networks (DNNs) has been preliminarily verified. Existing black-box adversarial attacks usually require multi-round interaction with the model and…
MA-CBP: A Criminal Behavior Prediction Framework Based on Multi-Agent Asynchronous Collaboration
Cheng Liu, Daou Zhang, Tingxu Liu +7
With the acceleration of urbanization, criminal behavior in public scenes poses an increasingly serious threat to social security. Traditional anomaly detection methods based on fe…
SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design
Wenxin Tang, Jingyu Xiao, Wenxuan Jiang +8
Manual slide creation is labor-intensive and requires expert prior knowledge. Existing natural language-based LLM generation methods struggle to capture the visual and structural n…
Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach
Linhao Huang, Xue Jiang, Zhiqiang Wang +5
Video-based multimodal large language models (V-MLLMs) have shown vulnerability to adversarial examples in video-text multimodal tasks. However, the transferability of adversarial…
LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything Model
Yuxin Cao, Jinghao Li, Xi Xiao +5
Previous work has shown that well-crafted adversarial perturbations can threaten the security of video recognition systems. Attackers can invade such models with a low query budget…
LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer
Yuxin Cao, Ziyu Zhao, Xi Xiao +3
Video recognition systems are vulnerable to adversarial examples. Recent studies show that style transfer-based and patch-based unrestricted perturbations can effectively improve a…
StyleFool: Fooling Video Classification Systems via Style Transfer
Yuxin Cao, Xi Xiao, Ruoxi Sun +3
Video classification systems are vulnerable to adversarial attacks, which can create severe security problems in video verification. Current black-box attacks need a large number o…