3 citations · 4 across the 13 of their papers we have counts for
16 papers
LLM Detoxification via Transition-Aware Reward-Guided Representation Sampling
Aishan Liu, Yisong Xiao, Xianglong Liu +7
Large Language Models (LLMs) can generate toxic content, motivating effective test-time detoxification. Existing representation steering methods often rely on static or coarse inte…
Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding
Yisong Xiao, Aishan Liu, Yongxin Huang +6
Large Vision-Language Models (LVLMs) have achieved remarkable performance across a wide range of tasks; however, they often inherit social biases from their training data, resultin…
SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems
Haowen Dai, Zonghao Ying, Wenfeng Li +10
Multi-agent systems improve capability through task decomposition and role specialization, but these same mechanisms introduce an important safety blind spot: a harmful objective c…
Technical Report on the CVPR 2026@AdvML Workshop Challenge
Tianyuan Zhang, Zonglei Jing, Jiangfan Liu +47
Vision-language agents (VLAs) are increasingly used to interpret complex driving scenes and support safety-critical reasoning. This report presents the CVPR 2026@AdvML Workshop Cha…
Improving Safety Alignment via Balanced Direct Preference Optimization
Shiji Zhao, Mengyang Wang, Shukun Xiong +7
With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. Reinforcement Learning from…
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…
Reasoning-Oriented Programming: Chaining Semantic Gadgets to Jailbreak Large Vision Language Models
Quanchen Zou, Moyang Chen, Zonghao Ying +6
Large Vision-Language Models (LVLMs) undergo safety alignment to suppress harmful content. However, current defenses predominantly target explicit malicious patterns in the input r…
Uncovering Strategic Egoism Behaviors in Large Language Models
Yaoyuan Zhang, Aishan Liu, Zonghao Ying +4
Large language models (LLMs) face growing trustworthiness concerns (\eg, deception), which hinder their safe deployment in high-stakes decision-making scenarios. In this paper, we…
Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing
Yisong Xiao, Aishan Liu, Siyuan Liang +3
Large Language Models (LLMs) have demonstrated impressive performance across various tasks, yet they remain vulnerable to generating toxic content, necessitating detoxification str…
PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking
Quanchen Zou, Zonghao Ying, Moyang Chen +7
The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation…
Fairness Mediator: Neutralize Stereotype Associations to Mitigate Bias in Large Language Models
Yisong Xiao, Aishan Liu, Siyuan Liang +2
LLMs have demonstrated remarkable performance across diverse applications, yet they inadvertently absorb spurious correlations from training data, leading to stereotype association…
Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
Zonghao Ying, Deyue Zhang, Zonglei Jing +7
Multi-turn jailbreak attacks simulate real-world human interactions by engaging large language models (LLMs) in iterative dialogues, exposing critical safety vulnerabilities. Howev…
BDefects4NN: A Backdoor Defect Database for Controlled Localization Studies in Neural Networks
Yisong Xiao, Aishan Liu, Xinwei Zhang +6
Pre-trained large deep learning models are now serving as the dominant component for downstream middleware users and have revolutionized the learning paradigm, replacing the tradit…
LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusions
Tianyuan Zhang, Lu Wang, Hainan Li +5
Lane detection (LD) is an essential component of autonomous driving systems, providing fundamental functionalities like adaptive cruise control and automated lane centering. Existi…
GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing
Yisong Xiao, Aishan Liu, QianJia Cheng +6
Large Vision-Language Models (LVLMs) have been widely adopted in various applications; however, they exhibit significant gender biases. Existing benchmarks primarily evaluate gende…
Pre-trained Trojan Attacks for Visual Recognition
Aishan Liu, Xinwei Zhang, Yisong Xiao +6
Pre-trained vision models (PVMs) have become a dominant component due to their exceptional performance when fine-tuned for downstream tasks. However, the presence of backdoors with…