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

Yiming Liu

4 indexed papers

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

Publications per year

4
26

Top categories

AI×4Crypto×1

Frequent co-authors

Mahtab Bigverdi1×
Lindsey Li1×
Weikai Huang1×
Jaemin Cho1×
Jieyu Zhang1×
Tuhin Kundu1×

Research Timeline

2026
Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw

The paper introduces DeepTrap, an automated framework that evaluates security vulnerabilities in agentic language models by manipulating their internal execution contexts, demonstrating that task completion does not guarantee safety.

Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent

The paper introduces Compass, an expert-guided LLM agent framework that successfully extracts and integrates thousands of previously inaccessible marine lead records from vast corpora of scientific papers, creating a major new global database.

CAPF: Guiding Search-Agent Rollouts with Credit-Attenuated Privileged Feedback

The paper proposes Credit-Attenuated Privileged Feedback (CAPF), a training-time mechanism that uses verifier-side information to guide LLM search agents, significantly improving their performance on complex QA tasks.

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

This paper introduces Imaginative Perception Tokens (IPT) to improve spatial reasoning in vision language models.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentJun 2, 2026

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

Mahtab Bigverdi, Lindsey Li, Weikai Huang, Yiming Liu +7 more

This paper introduces Imaginative Perception Tokens (IPT) to improve spatial reasoning in vision language models.

View →
cs.AIRecentJun 1, 2026

CAPF: Guiding Search-Agent Rollouts with Credit-Attenuated Privileged Feedback

Bin Chen, Xinye Liao, Yiming Liu, Xin Liao +1 more

The paper proposes Credit-Attenuated Privileged Feedback (CAPF), a training-time mechanism that uses verifier-side information to guide LLM search agents, significantly improving their performance on…

View →
cs.AIRecentMay 28, 2026

Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent

Yiming Liu, Bin Lu, Meng Jin, Ziyuan Sang +5 more

The paper introduces Compass, an expert-guided LLM agent framework that successfully extracts and integrates thousands of previously inaccessible marine lead records from vast corpora of scientific pa…

View →
cs.CRcs.AIRecentMay 11, 2026

Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw

Hongwei Yao, Yiming Liu, Yiling He, Bingrun Yang

The paper introduces DeepTrap, an automated framework that evaluates security vulnerabilities in agentic language models by manipulating their internal execution contexts, demonstrating that task comp…

View →