Scholar

Josef Dai

Google Scholar ID: eRmX5AsAAAAJ

Zhejiang University

Alignment

Google Scholar↗

Citations & Impact

All-time

Citations

3,007

H-index

12

i10-index

14

Publications

20

Co-authors

5

list available

Contact

No contact links provided.

Publications

6 items

Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models

2025

Cited

0

SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Safe Reinforcement Learning

2025

Cited

0

Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback

2024

Cited

0

PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference

2024

Cited

50

Language Models Resist Alignment: Evidence From Data Compression

2024

Cited

2

Reward Generalization in RLHF: A Topological Perspective

2024

Cited

4

Resume (English only)

Co-authors

5 total

Jiaming Ji (吉嘉铭)

Peking University

Peking University

Peking University Ph.D Student

Tianyi Alex Qiu

Peking University

Peking University