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

Yan Xie

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

NLP×2ML×1AI×1Stats Theory×1Crypto×1

Frequent co-authors

Tao Feng2×
Tianyang Luo2×
Jingjun Xu2×
Zhigang Hua2×
Shuang Yang2×
Ge Liu2×

Research Timeline

2026
Sequential Change Detection for Multiple Data Streams with Differential Privacy

The paper proposes DP-SUM-CUSUM, a differentially private method for detecting synchronized distributional changes across multiple data streams, explicitly characterizing the privacy-efficiency trade-off.

Masked Diffusion Modeling for Anomaly Detection

The paper proposes MaskDiff-AD, a forward-only masked diffusion model trained on nominal data to achieve state-of-the-art anomaly detection across various categorical, mixed-type, and text datasets.

ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents

ExpGraph is a model-agnostic framework that uses a self-evolving experience graph to enable LLM agents to reuse past successful strategies and failure lessons, significantly improving performance across diverse tasks.

ExpWeaver: LLM Agents Learn from Experience via Latent RAG

ExpWeaver introduces a novel framework for LLM agents to learn from past experiences using latent retrieval-augmented generation, achieving state-of-the-art performance while significantly improving token efficiency.

Highlighted terms show continued research focus across papers

Papers

cs.CLRecentMay 31, 2026

ExpWeaver: LLM Agents Learn from Experience via Latent RAG

Tao Feng, Tianyang Luo, Jingjun Xu, Zhigang Hua +4 more

ExpWeaver introduces a novel framework for LLM agents to learn from past experiences using latent retrieval-augmented generation, achieving state-of-the-art performance while significantly improving t…

View →
cs.CLRecentMay 29, 2026

ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents

Tao Feng, Chongrui Ye, Tianyang Luo, Jingjun Xu +7 more

ExpGraph is a model-agnostic framework that uses a self-evolving experience graph to enable LLM agents to reuse past successful strategies and failure lessons, significantly improving performance acro…

View →
cs.LGcs.AIRecentMay 28, 2026

Masked Diffusion Modeling for Anomaly Detection

Lixing Zhang, Yuchen Liang, Liyan Xie

The paper proposes MaskDiff-AD, a forward-only masked diffusion model trained on nominal data to achieve state-of-the-art anomaly detection across various categorical, mixed-type, and text datasets.

View →
math.STcs.CRRecentApr 14, 2026

Sequential Change Detection for Multiple Data Streams with Differential Privacy

Lixing Zhang, Liyan Xie, Ruizhi Zhang

The paper proposes DP-SUM-CUSUM, a differentially private method for detecting synchronized distributional changes across multiple data streams, explicitly characterizing the privacy-efficiency trade-…

View →