3 citations · 7 across the 13 of their papers we have counts for
18 papers
SafeEvo: Deciphering the Safety Alignment Mechanism and Evolution in Language Models
Miao Yu, Hao Huang, Lu Yuan +3
Safety interpretability advances the study of Large Language Model (LLM) alignment from behavioral constraints driven by data or algorithms towards a deeper understanding of intern…
RESCUE: Repairing Language Model Errors to Sparse Circuits via Reinforcement Learning
Chuanpu Liu, Miao Yu, Yikai Cai +5
Large language models (LLMs) exhibit strong general capabilities that mechanistic interpretability has attributed to sparse computational circuits. However, existing circuit studie…
A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook
Kaiwen Luo, Zhenhong Zhou, Leyan Wang +32
Advances in Large Language Models (LLMs) have paved the way for Multimodal Large Language Models (MLLMs). Among these, Large Audio Language Models (LALMs) are essential for realizi…
ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety
Kun Wang, Cheng Qian, Miao Yu +6
Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnera…
SafeSeek: Universal Attribution of Safety Circuits in Language Models
Miao Yu, Siyuan Fu, Moayad Aloqaily +6
Mechanistic interpretability reveals that safety-critical behaviors (e.g., alignment, jailbreak, backdoor) in Large Language Models (LLMs) are grounded in specialized functional co…
EmoRAG: Evaluating RAG Robustness to Symbolic Perturbations
Xinyun Zhou, Xinfeng Li, Yinan Peng +9
Retrieval-Augmented Generation (RAG) systems are increasingly central to robust AI, enhancing large language model (LLM) faithfulness by incorporating external knowledge. However,…
SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models
Huahui Yi, Kun Wang, Qiankun Li +7
Multimodal Large Reasoning Models (MLRMs) demonstrate impressive cross-modal reasoning but often amplify safety risks under adversarial or unsafe prompts, a phenomenon we call the…
Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models
Liang Lin, Miao Yu, Moayad Aloqaily +5
Backdoor attacks are a significant threat to large language models (LLMs), often embedded via public checkpoints, yet existing defenses rely on impractical assumptions about trigge…
OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment
Liang Lin, Zhihao Xu, Junhao Dong +10
Large language model (LLM) alignment faces a critical dilemma when addressing multiple human preferences: improvements in one dimension frequently come at the expense of others, cr…
Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
Miao Yu, Zhenhong Zhou, Moayad Aloqaily +5
Fine-tuned Large Language Models (LLMs) are vulnerable to backdoor attacks through data poisoning, yet the internal mechanisms governing these attacks remain a black box. Previous…
Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment through Latent Acoustic Pattern Triggers
Liang Lin, Miao Yu, Kaiwen Luo +9
As Audio Large Language Models (ALLMs) emerge as powerful tools for speech processing, their safety implications demand urgent attention. While considerable research has explored t…
G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
Guibin Zhang, Muxin Fu, Guancheng Wan +3
Large language model (LLM)-powered multi-agent systems (MAS) have demonstrated cognitive and execution capabilities that far exceed those of single LLM agents, yet their capacity f…
UniErase: Towards Balanced and Precise Unlearning in Language Models
Miao Yu, Liang Lin, Guibin Zhang +7
Large language models (LLMs) require iterative updates to address the outdated information problem, where LLM unlearning offers an approach for selective removal. However, mainstre…
A Survey on Trustworthy LLM Agents: Threats and Countermeasures
Miao Yu, Fanci Meng, Xinyun Zhou +9
With the rapid evolution of Large Language Models (LLMs), LLM-based agents and Multi-agent Systems (MAS) have significantly expanded the capabilities of LLM ecosystems. This evolut…
LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models
Miao Yu, Junfeng Fang, Yingjie Zhou +4
While safety-aligned large language models (LLMs) are increasingly used as the cornerstone for powerful systems such as multi-agent frameworks to solve complex real-world problems,…
Mind Scramble: Unveiling Large Language Model Psychology Via Typoglycemia
Miao Yu, Junyuan Mao, Guibin Zhang +7
Research into the external behaviors and internal mechanisms of large language models (LLMs) has shown promise in addressing complex tasks in the physical world. Studies suggest th…
NetSafe: Exploring the Topological Safety of Multi-agent Networks
Miao Yu, Shilong Wang, Guibin Zhang +6
Large language models (LLMs) have empowered nodes within multi-agent networks with intelligence, showing growing applications in both academia and industry. However, how to prevent…
G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks
Guibin Zhang, Yanwei Yue, Xiangguo Sun +6
Recent advancements in large language model (LLM)-based agents have demonstrated that collective intelligence can significantly surpass the capabilities of individual agents, prima…