Yihao Zhang

Orcid: 0009-0002-0284-1367

Affiliations:
  • Peking University, Beijing, China


According to our database1, Yihao Zhang authored at least 20 papers between 2023 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Symbolic-Neural Soft-Logic Reasoning: Towards Robust and Verifiable Thinking Chains via Cooperative Evolution.
CoRR, May, 2026

The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems.
CoRR, April, 2026

ClawWorm: Self-Propagating Attacks Across LLM Agent Ecosystems.
CoRR, March, 2026

RACA: Representation-Aware Coverage Criteria for LLM Safety Testing.
CoRR, February, 2026

On Mutation Testing of In-Context Learning Systems.
J. Syst. Archit., 2026

2025
Automata-Based Steering of Large Language Models for Diverse Structured Generation.
CoRR, November, 2025

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models.
CoRR, June, 2025

Mitigating Fine-tuning Risks in LLMs via Safety-Aware Probing Optimization.
CoRR, May, 2025

Robust and Efficient Watermarking of Large Language Models Using Error Correction Codes.
Proc. Priv. Enhancing Technol., 2025

Component Composition in MedTiny: Multi-Level Constructs and Operational Semantics.
Proceedings of the 37th International Conference on Software Engineering and Knowledge Engineering, 2025

MedTiny Code Generation for Enhancing RegLang Smart Contract Reliability.
Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing, 2025

Automata-Based Steering of Large Language Models for Diverse Structured Generation.
Proceedings of the Formal Methods and Software Engineering, 2025

2024
Weighted automata extraction and explanation of recurrent neural networks for natural language tasks.
J. Log. Algebraic Methods Program., January, 2024

Automata Extraction from Transformers.
CoRR, 2024

Towards General Conceptual Model Editing via Adversarial Representation Engineering.
CoRR, 2024

MILE: A Mutation Testing Framework of In-Context Learning Systems.
Proceedings of the Dependable Software Engineering. Theories, Tools, and Applications, 2024

Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

2023
Using Z3 for Formal Modeling and Verification of FNN Global Robustness.
CoRR, 2023

Using Z3 for Formal Modeling and Verification of FNN Global Robustness (S).
Proceedings of the 35th International Conference on Software Engineering and Knowledge Engineering, 2023

MedTiny: Enhanced Mediator Modeling Language for Scalable Parallel Algorithms.
Proceedings of the 23rd IEEE International Conference on Software Quality, 2023


  Loading...