Si Chen

University of Science and Technology of China

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Multimodal Models (1)Red-Teaming & Adversarial Robustness (1)Constitutional AI & AI Ethics (1)Natural Language Processing (1)

Frequent co-authors

Liangsheng Liu (1)Jiamin Wu (1)Weiwei Feng (1)Zhixin Cheng (1)

Papers (2)

Jun 4, 2026

1w ago·also CUHK, National Key Laboratory of Deep Space Exploration, ZJU

Adversarial Attacks Already Tell the Answer: Directional Bias-Guided Test-time Defense for Vision-Language Models

Adversarial images in CLIP reveal a consistent directional bias that can be exploited to enhance model robustness, leading to surprising cases where adversarial accuracy surpasses clean accuracy.

Liangsheng Liu, Si Chen, Jiamin Wu +5

Multimodal Models Red-Teaming & Adversarial Robustness

Mar 3, 2026

Sugana Chawla +10Mar 3, 2026·also Computer Science and Engineering, Notre Dame, USTC

AI4CAREER: Responsible AI for STEM Career Development at Scale in K-16 Education

As AI increasingly shapes STEM career paths for students, this workshop identifies critical design tensions and governance principles for ensuring responsible and equitable AI-driven career development tools.

Sugana Chawla, Si Chen, J. Qian +8

Constitutional AI & AI Ethics Natural Language Processing Recommendation & Information Retrieval

Search

Si Chen

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)