ZS
Zhengyang Shan
cs.AIcs.CRcs.CLcs.CVcs.HCcs.LGAdversarial examplesAdversarial robustnessBlack-box attackscs.GR
On Valency
published · living versionsW_hwk8skzp·v1 · currentpublished
Modeling Discourse Profiles in Climate Misinformation Discourse
with Ge Gao, Bryan A. Plummer, Margrit Betke, Derry Wijaya
1 version
Preprints & journals
15 papers in the corpus · 2020–2026Modeling Discourse Profiles in Climate Misinformation Discourse2610.24489v1 · Ge Gao, Zhengyang Shan, Bryan A. Plummer et al.2026 · 0 citationsarXivon Valency
UNBIND: UNlearning By INference-time Directional Steering for Code LLMs2609.35913v1 · Zhengyang Shan, Jiayun Xin, Yanjun Lin et al.2026 · 0 citationsarXiv
AI Writers Have a Consistent Stylometric Footprint, but AI Editors Do Not2608.27855v2 · Zhengyang Shan, Yukyung Lee, Sophie Hao2026 · 0 citationsarXiv
PersonaEval: Persona-Based User Simulation for Evaluating Interactive Applications2608.15838v1 · Yifan Simon Liu, Qianfeng Wen, Yilan Fan et al.2026 · 0 citationsarXiv
MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations2608.15844v1 · Sky Ng, Brihi Joshi, Ishan Gupta et al.2026 · 0 citationsarXiv
OBLIVION: Workflow-Level Operational Skill Unlearning for Deployed Agents2608.08264v1 · Zhengyang Shan, Xu Qian, Jiayun Xin et al.2026 · 0 citationsarXiv
ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents2605.17324v1 · Udari Madhushani Sehwag, Zhengyang Shan, Heming Liu et al.2026 · 0 citationsarXiv
Delving into the adversarial robustness of semantic segmentation with decision-based black-box attacks.42102549 · Chen, Zhaoyu, Shan, Zhengyang, Chang, Jingwen et al.2026 · 0 citationsNeural networks : the official journal of the International Neural Network Society. 2026;202:109020
Utility-Aware Data Pricing: Token-Level Quality and Empirical Training Gain for LLMs2604.22893v2 · Minghui Xu, Qi Luo, Kun Li et al.2026 · 0 citationsarXiv
SAGE: Signal-Amplified Guided Embeddings for LLM-based Vulnerability Detection2604.19031v1 · Zhengyang Shan, Xu Qian, Jiayun Xin et al.2026 · 0 citationsarXiv
Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw2603.10387v1 · Zhengyang Shan, Jiayun Xin, Yue Zhang et al.2026 · 0 citationsarXiv
DebiasPI: Inference-time Debiasing by Prompt Iteration of a Text-to-Image Generative Model2501.18642v1 · Sarah Bonna, Yu-Cheng Huang, Ekaterina Novozhilova et al.2025 · 3 citationsarXiv
Delving into Decision-based Black-box Attacks on Semantic Segmentation2402.01220v1 · Zhaoyu Chen, Zhengyang Shan, Jingwen Chang et al.2024 · 0 citationsarXiv
ResDiff: Combining CNN and Diffusion Model for Image Super-Resolution2303.08714v3 · Shuyao Shang, Zhengyang Shan, Guangxing Liu et al.2023 · 141 citationsarXiv
Nonuniqueness for a fully nonlinear, degenerate elliptic boundary value problem in conformal geometry2004.01514v1 · Zhengyang Shan2020 · 1 citationarXiv
Career total: 19 works. 15 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.