Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Xiao Yan

Xiao Yan

7 indexed papers

Recent (6 mo)
7
With code
0
Influential cites
0
Benchmarked
0

Publications per year

7
26

Top categories

AI×6NLP×4ML×4Crypto×4Vision×2Software Eng.×1Logic×1

Frequent co-authors

Dongrui Liu2×
Yu Li2×
Zhonghao Yang2×
Peng Wang2×
Guanxu Chen2×
Yuejin Xie2×

Research Timeline

2026
Toward Polymorphic Backdoor against Semantic Communication via Intensity-Based Poisoning

The paper proposes SemBugger, a polymorphic backdoor attack that uses intensity-based poisoning to achieve diverse malicious outcomes in Semantic Communication (SC) systems, alongside a provable defense mechanism.

Zero-Knowledge Model Checking

The paper presents a novel technology that uses zero-knowledge proofs to formally verify a software system's correctness against a public specification without revealing the system's internal details.

Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning

The paper introduces Q-ALIGN DT, a novel framework that improves conditioned sequence models by enforcing alignment between the input return-to-go (RTG) signal and the output policy's expected Q-value, leading to superior policy controllability and performance.

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.

BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution

BenchEvolver introduces a solution-centric evolutionary framework to automatically transform saturated coding benchmarks into significantly harder, high-quality, and diverse evaluation suites.

MiCU: End-to-End Smart Home Command Understanding with Large Language Model

The paper introduces MiCU, a domain-specific LLM that significantly improves smart home command understanding, especially for ambiguous commands, by synthesizing training data and optimizing the model for efficiency.

Highlighted terms show continued research focus across papers

Papers

cs.SEcs.AIcs.CLRecentMay 31, 2026

BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution

Yangzhen Wu, Aaron J. Li, Wenjie Ma, Li Cao +9 more

BenchEvolver introduces a solution-centric evolutionary framework to automatically transform saturated coding benchmarks into significantly harder, high-quality, and diverse evaluation suites.

View →
cs.CLcs.AIRecentMay 31, 2026

MiCU: End-to-End Smart Home Command Understanding with Large Language Model

Haowei Han, Kexin Hu, Weiwei Cai, Debiao Zhang +5 more

The paper introduces MiCU, a domain-specific LLM that significantly improves smart home command understanding, especially for ambiguous commands, by synthesizing training data and optimizing the model…

View →
cs.AIcs.CLcs.CRRecentMay 28, 2026

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

Dongrui Liu, Yu Li, Zhonghao Yang, Peng Wang +46 more

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.

View →
cs.AIcs.CLcs.CRRecentMay 28, 2026

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

Dongrui Liu, Yu Li, Zhonghao Yang, Peng Wang +46 more

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.

View →
cs.LGcs.AIRecentMay 27, 2026

Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning

Yuxiao Yang, Weitong Zhang

The paper introduces Q-ALIGN DT, a novel framework that improves conditioned sequence models by enforcing alignment between the input return-to-go (RTG) signal and the output policy's expected Q-value…

View →
cs.CRcs.LORecentMay 1, 2026

Zero-Knowledge Model Checking

Pascal Berrang, Mirco Giacobbe, Jacob Swales, Xiao Yang

The paper presents a novel technology that uses zero-knowledge proofs to formally verify a software system's correctness against a public specification without revealing the system's internal details.

View →
cs.CRcs.AIRecentApr 25, 2026

Toward Polymorphic Backdoor against Semantic Communication via Intensity-Based Poisoning

Xiao Yang, Yuni Lai, Gaolei Li, Jun Wu +3 more

The paper proposes SemBugger, a polymorphic backdoor attack that uses intensity-based poisoning to achieve diverse malicious outcomes in Semantic Communication (SC) systems, alongside a provable defen…

View →