Yanxiang Ma

4 papers · 2023–2026 · 4 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (3) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (15) 🏆 Grand Slam

Conferences

AAAI (1) ICLR (1) ICML (1) NIPS (1)

Top co-authors

Chang Xu (4) Shan You (2) Minjing Dong (2) Zixuan Huang (1) Tao Huang (1) Zijian Wang (1)

Keywords

adversarial robustness (1) chain-of-thought reasoning (1) adversarial attack (1) activation steering (1) gradient similarity (1) representation optimization (1) randomized defense (1) hidden state manipulation (1) random weight sampling (1) prior regularization (1)

Papers

Eliciting Chain-of-Thought in Base LLMs via Gradient-Based Representation Optimization AAAI 2026

Learning Mask Invariant Mutual Information for Masked Image Modeling ICLR 2025

Adversarial Robustness via Deformable Convolution with Stochasticity ICML 2025

Adversarial Robustness through Random Weight Sampling NIPS 2023