Get started
Author

Naixin Zhai

Observed name: Zhai, Naixin
ORCID: 0009-0005-3709-0163
Observed ORCID: 0009-0005-3709-0163
OpenAlex ID: A5106247119
Vulnerabilities in AI-Generated Image Detection: The Challenge of Adversarial Attacks
2026 · Yunfeng Diao, Naixin Zhai, et al. · IEEE Transactions on Multimedia · 2
PDF
MemForm: Benchmarking Memory Formation Poisoning in LLM Agents
2026 · Pan, Haowen, Shao, Pengyang, et al. · arXiv (Cornell University)
PDF
AlphaPADI: Formulaic Alpha Discovery via Pool-Aware Hierarchical Discrete Diffusion
2026 · Jin, Yanzheng, Shao, Pengyang, et al. · arXiv (Cornell University)
PDF
Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning
2026 · Association for Computational Linguistics 2026, Bai, Long, et al. · Underline Science Inc.
BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning
2026 · Pengyang Shao, Naixin Zhai, et al. · International World Wide Web Conference (WWW)
Chain of Mindset: Reasoning with Adaptive Cognitive Modes
2026 · Jiang, Tianyi, An, Arctanx, et al. · arXiv (Cornell University)
PDF
BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning
2026 · Shao, Pengyang, Zhai, Naixin, et al. · arXiv (Cornell University)
PDF
Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning
2026 · Zhai, Naixin, Shao, Pengyang, et al. · arXiv (Cornell University)
PDF
Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning
2026 · Naixin Zhai, Pengyang Shao, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Works count: 9
Citation count: 2
H-index: 1
I10-index:
Year
Topic
Type