Author

Zhuoyi Lin

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Sep 2026

Selective Channel Restoration for Backdoored Vision-Language Models

Vision-language models (VLMs) exhibit strong multimodal capabilities but remain vulnerable to backdoors implanted through poisoned fine-tuning data. Existing defenses often require extensive parameter updates during fine-tuning or incur per-query overhead during inference. To address these limitations, we propose Pertu...

Shu-Ming Liu, Zhi-Fang Zhang, Su-Qin Yuan et al. · arXiv.org · 0 citations

#machine learning Jul 2026

On the effectiveness of reward functions in reinforcement learning for confidence calibration of large language models

This paper proposes the concept of non-hackable confidence reward schemes and defines a spectrum of such reward schemes for RL confidence calibration training in LLMs, and demonstrates that selective confidence reward hacking can occur in practical datasets with reward schemes that are not designed to be non-hackable.

C. Tan, Zhuoyi Lin, M. Motani et al. · arXiv.org · 0 citations