collaborators

5 papers

cs.AI2025

RETAIL: Towards Real-world Travel Planning for Large Language Models

Bin Deng, Yizhe Feng, Zeming Liu +5

Although large language models have enhanced automated travel planning abilities, current systems remain misaligned with real-world scenarios. First, they assume users provide expl…

cs.CL2025

ToolSpectrum : Towards Personalized Tool Utilization for Large Language Models

Zihao Cheng, Hongru Wang, Zeming Liu +4

While integrating external tools into large language models (LLMs) enhances their ability to access real-time information and domain-specific services, existing approaches focus na…

cs.CV2025

Generalizable AI-Generated Image Detection Based on Fractal Self-Similarity in the Spectrum

Shengpeng Xiao, Yuanfang Guo, Heqi Peng +5

With the rapid development of image synthesis techniques, AI-generated images have become increasingly realistic, which heightens the potential risk associated with their misuse an…

cs.CV2025

Deepfake Detection via Knowledge Injection

Tonghui Li, Yuanfang Guo, Zeming Liu +2

Deepfake detection technologies become vital because current generative AI models can generate realistic deepfakes, which may be utilized in malicious purposes. Existing deepfake d…

cs.CV2024

AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation

Heqi Peng, Yunhong Wang, Ruijie Yang +3

Adversarial example detection, which can be conveniently applied in many scenarios, is important in the area of adversarial defense. Unfortunately, existing detection methods suffe…