Shenglai Zeng

~Shenglai_Zeng2

5

论文总数

2.5

年均投稿

5.6

平均评分

接收情况2/5

会议分布

ICLR

4

NeurIPS

1

发表论文 (5 篇)

20251 篇

Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy

NeurIPS 2025Poster

20244 篇

Exploring Memorization in Fine-tuned Language Models

ICLR 2024withdrawn

On the Generalization of Training-based ChatGPT Detection Methods

ICLR 2024Rejected

Confidence-driven Sampling for Backdoor Attacks

ICLR 2024Rejected

Sharpness-Aware Data Poisoning Attack

ICLR 2024Spotlight

合作者 (20)

Jiliang Tang4 篇

Pengfei He4 篇

Yingqian Cui3 篇

Charu C. Aggarwal2 篇