Profiles2025-2026
Biyu Zhou
Institute of Information Engineering, Chinese Academy of Sciences
7Papers
0Last author
6Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers7
- Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMsAuthor 2 of 5AAAI 2026
- FABLE: Fine-grained Fact Anchoring for Unstructured Model EditingAuthor 2 of 5ACL Findings 2026
- More Thinking, Less Talking: Internalizing Deliberative Safety into LLM ParametersAuthor 3 of 5ACL 2026
- Profiling the Irrational Agent: Cognitive Modeling of LLM Behaviors in Sequential JailbreaksAuthor 2 of 5ICML 2026
- Resolving the Security-Auditability Dilemma with Auditable Latent Chain-of-Thought AlignmentAuthor 4 of 5ACL 2026
- Chain of Attack: Hide Your Intention through Multi-Turn InterrogationAuthor 2 of 5ACL Findings 2025 · 3 citations
- LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model EditingAuthor 2 of 5EMNLP 2025
