12 citations · 15 across the 9 of their papers we have counts for
9 papers
Beyond Similarity: Trustworthy Memory Search for Personal AI Agents
Jiawen Zhang, Kejia Chen, Jiachen Ma +7
Personal AI agents increasingly rely on long-term memory to provide persistent personalization across sessions. However, existing memory pipelines are largely driven by semantic si…
REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak
Jiachen Ma, Jiawen Zhang, Xiangtian Li +3
While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that circumvent conventional surface-…
Understanding and Preserving Safety in Fine-Tuned LLMs
Jiawen Zhang, Yangfan Hu, Kejia Chen +7
Fine-tuning is an essential and pervasive functionality for applying large language models (LLMs) to downstream tasks. However, it has the potential to substantially degrade safety…
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45 Law
Shanghai AI Lab, :, Yicheng Bao +115
We introduce SafeWork-R1, a cutting-edge multimodal reasoning model that demonstrates the coevolution of capabilities and safety. It is developed by our proposed SafeLadder framewo…
SafeCoT: Improving VLM Safety with Minimal Reasoning
Jiachen Ma, Zhanhui Zhou, Chao Yang +1
Ensuring safe and appropriate responses from vision-language models (VLMs) remains a critical challenge, particularly in high-risk or ambiguous scenarios. We introduce SafeCoT, a l…
A Comparative Study on Reasoning Patterns of OpenAI's o1 Model
Siwei Wu, Zhongyuan Peng, Xinrun Du +14
Enabling Large Language Models (LLMs) to handle a wider range of complex tasks (e.g., coding, math) has drawn great attention from many researchers. As LLMs continue to evolve, mer…
Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models
Jiachen Ma, Yijiang Li, Zhiqing Xiao +4
Text-to-image (T2I) models can be maliciously used to generate harmful content such as sexually explicit, unfaithful, and misleading or Not-Safe-for-Work (NSFW) images. Previous at…
CAME: Contrastive Automated Model Evaluation
Ru Peng, Qiuyang Duan, Haobo Wang +5
The Automated Model Evaluation (AutoEval) framework entertains the possibility of evaluating a trained machine learning model without resorting to a labeled testing set. Despite th…
Towards Understanding the Generative Capability of Adversarially Robust Classifiers
Yao Zhu, Jiacheng Ma, Jiacheng Sun +3
Recently, some works found an interesting phenomenon that adversarially robust classifiers can generate good images comparable to generative models. We investigate this phenomenon…