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

Yi Yu

6 indexed papers

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

Publications per year

6
26

Top categories

Crypto×2NLP×1ML×1Prog. Lang.×1Signal Processing×1AI×1Robotics×1

Frequent co-authors

Lin-Fa Lee2×
Yi-Yu Chang2×
Chia-Mu Yu2×
Kuo-Hui Yeh2×
Zhiyu Li1×
Zeyu Zhang1×

Research Timeline

2026
WebMCP Tool Surface Poisoning: Runtime Manipulation Attacks on LLM Agents

This paper identifies a new threat in WebMCP, called Mid-Session Tool Injection (MSTI), and proposes mitigation directions.

WebMCP Tool Surface Poisoning: Runtime Manipulation Attacks on LLM Agents

The paper identifies Mid-Session Tool Injection (MSTI) as a novel threat in the WebMCP protocol, demonstrating that attackers can manipulate the visible or perceived set of tools available to AI agents during an active session.

Self-Evolving Cognitive Framework via Causal World Modeling for Embodied Scientific Intelligence

The paper proposes a self-evolving cognitive framework for embodied scientific intelligence that constructs and refines internal causal representations through interaction with the environment.

Generalizable and Computational Efficient Channel Extrapolation for 6G: A Configurable AI-Driven Framework Built from a Modular Perspective

This paper proposes a three-stage AI-driven framework for generalizable and computationally efficient channel extrapolation in 6G mobile networks.

Structure-Aware Equivalence for Evaluating Autoformalized Statements

Introduces Structure-Aware Equivalence (SAE) for evaluating autoformalized mathematical statements.

MemT-1.0: Towards Memory-Native Evolution

This paper introduces MemT-1.0, a new architecture of memory foundation models that internalize memory as part of model computation.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.LGEmpiricalRecentOct 19, 2026

MemT-1.0: Towards Memory-Native Evolution

Zhiyu Li, Zeyu Zhang, Linyun Liu, Yiwei Bu +70 more

This paper introduces MemT-1.0, a new architecture of memory foundation models that internalize memory as part of model computation.

View →
cs.PLEmpiricalRecent
Oct 18, 2026

Structure-Aware Equivalence for Evaluating Autoformalized Statements

Yi Yu, Yu-Hsuan Wu, Guang Lin, Yuhui Zhang +1 more

Introduces Structure-Aware Equivalence (SAE) for evaluating autoformalized mathematical statements.

View →
eess.SPEmpiricalRecentAug 5, 2026

Generalizable and Computational Efficient Channel Extrapolation for 6G: A Configurable AI-Driven Framework Built from a Modular Perspective

Yuan Gao, Xinyi Wu, Jiang Jun, Yi Yu +4 more

This paper proposes a three-stage AI-driven framework for generalizable and computationally efficient channel extrapolation in 6G mobile networks.

View →
cs.AIcs.ROTheoreticalRecentJun 21, 2026

Self-Evolving Cognitive Framework via Causal World Modeling for Embodied Scientific Intelligence

Yi Yu, Tetsunari Inamura

The paper proposes a self-evolving cognitive framework for embodied scientific intelligence that constructs and refines internal causal representations through interaction with the environment.

View →
cs.CREmpiricalRecentJun 4, 2026

WebMCP Tool Surface Poisoning: Runtime Manipulation Attacks on LLM Agents

Lin-Fa Lee, Yi-Yu Chang, Chia-Mu Yu, Kuo-Hui Yeh

This paper identifies a new threat in WebMCP, called Mid-Session Tool Injection (MSTI), and proposes mitigation directions.

View →
cs.CRRecentJun 4, 2026

WebMCP Tool Surface Poisoning: Runtime Manipulation Attacks on LLM Agents

Lin-Fa Lee, Yi-Yu Chang, Chia-Mu Yu, Kuo-Hui Yeh

The paper identifies Mid-Session Tool Injection (MSTI) as a novel threat in the WebMCP protocol, demonstrating that attackers can manipulate the visible or perceived set of tools available to AI agent…

View →