3 papers
cs.CL2026
AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool Use
Yuanjie Lyu, Chengyu Wang, Haonan Zheng +4
Modern industrial applications increasingly demand language models that act as agents, capable of multi-step reasoning and tool use in real-world settings. These tasks are typicall…
cs.CV2024
Sample-agnostic Adversarial Perturbation for Vision-Language Pre-training Models
Haonan Zheng, Wen Jiang, Xinyang Deng +1
Recent studies on AI security have highlighted the vulnerability of Vision-Language Pre-training (VLP) models to subtle yet intentionally designed perturbations in images and texts…
cs.CV2024
A Unified Understanding of Adversarial Vulnerability Regarding Unimodal Models and Vision-Language Pre-training Models
Haonan Zheng, Xinyang Deng, Wen Jiang +1
With Vision-Language Pre-training (VLP) models demonstrating powerful multimodal interaction capabilities, the application scenarios of neural networks are no longer confined to un…