Scholar

Yuntai Bao

Google Scholar ID: phKr8uQAAAAJ

Zhejiang University

Mechanistic interpretabilityAI safety

Google Scholar↗

Citations & Impact

All-time

Citations

23

H-index

1

i10-index

1

Publications

3

Co-authors

0

Contact

No contact links provided.

Publications

5 items

Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions

2026

Cited

0

PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts

2026

Cited

0

Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions

2026

Cited

0

Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks

2025

Cited

0

Scalable Multi-Stage Influence Function for Large Language Models via Eigenvalue-Corrected Kronecker-Factored Parameterization

2025

Cited

0

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)