4 papers
OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents
Zheng Wu, Yi Hua, Zhaoyuan Huang +8
The evolution of Multimodal Large Language Models (MLLMs) has shifted the focus from text generation to active behavioral execution, particularly via OS agents navigating complex G…
SAKED: Mitigating Hallucination in Large Vision-Language Models via Stability-Aware Knowledge Enhanced Decoding
Zhaoxu Li, Chenqi Kong, Peijun Bao +5
Hallucinations in Large Vision-Language Models (LVLMs) pose significant security and reliability risks in real-world applications. Inspired by the observation that humans are more…
Propose and Rectify: A Forensics-Driven MLLM Framework for Image Manipulation Localization
Keyang Zhang, Chenqi Kong, Hui Liu +3
The increasing sophistication of image manipulation techniques demands robust forensic solutions that can both reliably detect alterations and precisely localize tampered regions.…
Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance
Hui Liu, Wenya Wang, Kecheng Chen +6
In zero-shot image recognition tasks, humans demonstrate remarkable flexibility in classifying unseen categories by composing known simpler concepts. However, existing vision-langu…