Author

Yichuan Mo

Observed name: Mo, Yichuan

Institution: Peking University

Observed institutions: Shanghai Jiao Tong University, Peking University

ORCID: 0000-0002-2663-2052

Observed ORCID: 0000-0002-2663-2052

OpenAlex ID: A5038918955

Jailbreak and Guard Aligned Language Models With Only Few In-Context Demonstrations

2026 · Zeming Wei, Yifei Wang, et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 51

PDF

When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture

2022 · Yichuan Mo, Dongxian Wu, et al. · neural information processing systems · 39

PDF

Multi-Task Learning Improves Synthetic Speech Detection

2022 · Yichuan Mo, Shilin Wang · IEEE International Conference on Acoustics Speech and Signal Processing · 21

Fight Back Against Jailbreaking via Prompt Adversarial Tuning

2024 · Yichuan Mo, Yuji Wang, et al. · neural information processing systems · 10

PDF

DICE: Domain-attack Invariant Causal Learning for Improved Data Privacy Protection and Adversarial Robustness

2022 · Qibing Ren, Yiting Chen, et al. · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · 10

On the Adversarial Transferability of Generalized “Skip Connections”

2026 · Yisen Wang, Yichuan Mo, et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2

PDF

TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors

2024 · Mo, Yichuan, Huang, Hui, et al. · arXiv (Cornell University) · 2

PDF

PID: Prompt-Independent Data Protection Against Latent Diffusion Models

2024 · Li, Ang, Mo, Yichuan, et al. · arXiv (Cornell University) · 2

PDF

Improving Generative Adversarial Networks Via Adversarial Learning in Latent Space

2022 · Yang Li, Yichuan Mo, et al. · neural information processing systems · 1

Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care

2026 · Yang, Aiyuan, Piao, Canbin, et al. · arXiv (Cornell University)

PDF

TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models

2026 · Mo, Yichuan, Jiang, Yukun, et al. · arXiv (Cornell University)

PDF

Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making

2026 · M3 Team, Dou, Chengfeng, et al. · arXiv (Cornell University)

PDF

TrustLDM: Benchmarking Trustworthiness in Language Diffusion Model

2026 · Mo, Yichuan, Jiang, Yukun, et al. · Figshare

Rethink Backdoor Robustness in Vision Transformers

2026 · Yichuan Mo, Dongxian Wu, et al. · Lecture notes in computer science

TrustDLM: Benchmarking Trustworthiness in Diffusion Language Models

2026 · Yichuan Mo, Yukun Jiang, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

PDF

Decoding Diffusion Language Models with Foreseeing Movement

2026 · Yichuan Mo, Quan Chen, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

PDF

Generalist++: A Meta-learning Framework for Mitigating Trade-off in Adversarial Training

2025 · Wang, Yisen, Mo, Yichuan, et al. · arXiv (Cornell University)

PDF

Works count: 18

Citation count: 138

H-index: 5

I10-index: 5