activity
20242026
collaborators

13 papers

cs.AI2026

PTQ4SNN: Membrane-Aware Post-Training Quantization for Spiking Neural Networks

Hui Xie, Tong Shi, Haotong Qin +3

Spiking neural networks (SNNs) enable sparse and event-driven computation, but their low-bit deployment remains incomplete because recurrent membrane states are commonly retained i…

cs.LG2026

An Empirical Study of openPangu Quantization on Ascend NPUs

Tong Shi, Jiacheng Wang, Hui Xie +4

openPangu models are attractive targets for private and domestic large-language-model deployment, yet their robustness under aggressive post-training quantization on Ascend NPUs ha…

cs.CR2026

SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents

Zonghao Ying, Yangguang Shao, Jianle Gan +8

Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face…

cs.CV2026

Reading Between the Pixels: An Inscriptive Jailbreak Attack on Text-to-Image Models

Zonghao Ying, Haowen Dai, Lianyu Hu +5

Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse. We identify and formalize the inscriptive jailbreak,…

cs.CR2026

Evolving Deception: When Agents Evolve, Deception Wins

Zonghao Ying, Haowen Dai, Tianyuan Zhang +6

Self-evolving agents offer a promising path toward scalable autonomy. However, in this work, we show that in competitive environments, self-evolution can instead give rise to a ser…

cs.CV2026

SPARK: Jailbreaking T2V Models by Synergistically Prompting Auditory and Recontextualized Knowledge

Zonghao Ying, Moyang Chen, Nizhang Li +6

Jailbreak attacks can circumvent model safety guardrails and reveal critical blind spots. Prior attacks on text-to-video (T2V) models typically add adversarial perturbations to obv…