Get started
Author

Hui Xue

Observed names: Xue', Hui, Xue, Hui
ORCID: 0000-0002-2093-2839
Observed ORCID: 0000-0002-2093-2839
OpenAlex ID: A5125774891
SkillNet: Create, Evaluate, and Connect AI Skills
2026 · Liang, Yuan, Zhong, Ruobin, et al. · arXiv (Cornell University) · 81
PDF
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
2026 · Liu, Dongrui, Ren, Qihan, et al. · arXiv (Cornell University) · 78
PDF
YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models
2026 · Lin, Junyu, Liu, Meizhen, et al. · arXiv (Cornell University) · 24
PDF
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
2026 · Liu, Dongrui, Li, Yu, et al. · arXiv (Cornell University) · 14
PDF
How LoRA Remembers? A Parametric Memory Law for LLM Finetuning
2026 · Xu, Ziwen, Hong, Haiwen, et al. · arXiv (Cornell University) · 7
PDF
TC-Padé: Trajectory-Consistent Padé Approximation for Diffusion Acceleration
2026 · Cui, Benlei, He, Shaoxuan, et al. · arXiv (Cornell University) · 6
PDF
Rethinking Self-Evolving Agents: Do We Still Need Prescribed Optimization Pipelines?
2026 · Xue, Hui, Yang, Fan · arXiv (Cornell University) · 4
PDF
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
2026 · Li, Hongxing, Huang, Xiufeng, et al. · arXiv (Cornell University) · 3
PDF
simpleposter: A simple baseline for product poster generation
2026 · Cui, Benlei, Zeng, Fangao, et al. · arXiv (Cornell University) · 3
PDF
Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety
2026 · Qiu, Shikai, Xu, Xiaowen, et al. · arXiv (Cornell University) · 2
PDF
EvoHarmBench: Breaking Content Moderation with Iterative Human-Like Evasion
2026 · Ruijie Jian, Benlei Cui, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 2
PDF
Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models
2026 · Shen Pang, Benlei Cui, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 2
PDF
Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety
2026 · Ma, Ting, Huang, Xiufeng, et al. · arXiv (Cornell University) · 1
PDF
ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails
2026 · Wang, Yan, Chu, Zhixuan, et al. · arXiv (Cornell University) · 1
PDF
PGuard: A Native, Streaming, and Plug-in Guardrail for Multimodal Large Language Models
2026 · Lin, Junyu, Wu, Mengjie, et al. · arXiv (Cornell University)
PDF
TomasuLLM: Out-of-Order Speculative Execution for LLM Agents
2026 · Yu, Jiangnan, Xu, Ceyu, et al. · arXiv (Cornell University)
PDF
Fingerprinting Text-to-Image Diffusion Models via Collapsed Generation
2026 · Huang, Yuanmin, Chen, Chen, et al. · arXiv (Cornell University)
PDF
AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models
2026 · Huang, Yuanmin, Zhang, Zhenfei, et al. · arXiv (Cornell University)
PDF
Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models
2026 · Guan, Jiyang, Xie, Yong, et al. · arXiv (Cornell University)
PDF
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
2026 · Association for Computational Linguistics 2026, Cheng, Jiale, et al. · Underline Science Inc.
Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts
2026 · Association for Computational Linguistics 2026, Hong, Haiwen, et al. · Underline Science Inc.
Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
2026 · Association for Computational Linguistics 2026, Chen, Huajun, et al. · Underline Science Inc.
How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities
2026 · Association for Computational Linguistics 2026, Chen, Huajun, et al. · Underline Science Inc.
MESA: Improving MoE Safety Alignment via Decentralized Expertise
2026 · Sun, Yitong, Huang, Yao, et al. · arXiv (Cornell University)
PDF
MAIL++: Multi-Modal Bi-directional Agent Layer for Vision-Language Models
2026 · Chen, Kaixiang, Fang, Pengfei, et al. · arXiv (Cornell University)
PDF
Works count: 35
Citation count: 228
H-index: 6
I10-index: 4
Year
Topic
Type