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

Xinyu Yang

4 indexed papers

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

Publications per year

4
26

Top categories

NLP×4AI×3Crypto×2Software Eng.×1

Frequent co-authors

Jiejun Tan2×
Zhicheng Dou2×
Yuyang Hu2×
Yiruo Cheng2×
Xiaoxi Li2×
Ji-Rong Wen2×

Research Timeline

2026
From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors

The paper introduces ClawTrojan, a benchmark for multi-step trojan attacks against LLM agents, and proposes DASGuard, a defense mechanism that detects and sanitizes backdoor content planted across multiple workspace interactions.

From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors

This paper introduces ClawTrojan, a benchmark for multi-step trojan attacks against LLM agents, and proposes DASGuard, a dynamic defense mechanism that traces and sanitizes untrusted control content in local workspace files.

Token-Operations-Oriented Inference Optimization Techniques for Large Models

This paper proposes a four-layer technical architecture for large model inference optimization, including Multi-model Fusion, Model Optimization, Compute-Model Fusion, and Compute-Network-Model Fusion.

Loop the Loopies!

The paper introduces Loopie, two Mixture-of-Experts models that outperform vanilla Transformer baselines in looped Transformers, with extensive ablation studies and a strong reasoning pipeline.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIEmpiricalRecentJul 17, 2026

Loop the Loopies!

Zitian Gao, Yilong Chen, Yihao Xiao, Xinyu Yang +3 more

The paper introduces Loopie, two Mixture-of-Experts models that outperform vanilla Transformer baselines in looped Transformers, with extensive ablation studies and a strong reasoning pipeline.

View →
cs.SEcs.CLSurvey
Recent
Jun 18, 2026

Token-Operations-Oriented Inference Optimization Techniques for Large Models

Shiguo Lian, Kai Wang, Zhaoxiang Liu, Wen Liu +21 more

This paper proposes a four-layer technical architecture for large model inference optimization, including Multi-model Fusion, Model Optimization, Compute-Model Fusion, and Compute-Network-Model Fusion…

View →
cs.CRcs.AIcs.CLRecentMay 29, 2026

From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors

Jiejun Tan, Zhicheng Dou, Xinyu Yang, Yuyang Hu +3 more

The paper introduces ClawTrojan, a benchmark for multi-step trojan attacks against LLM agents, and proposes DASGuard, a defense mechanism that detects and sanitizes backdoor content planted across mul…

View →
cs.CRcs.AIcs.CLRecentMay 29, 2026

From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors

Jiejun Tan, Zhicheng Dou, Xinyu Yang, Yuyang Hu +3 more

This paper introduces ClawTrojan, a benchmark for multi-step trojan attacks against LLM agents, and proposes DASGuard, a dynamic defense mechanism that traces and sanitizes untrusted control content i…

View →