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

Zihan Li

6 indexed papers

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

Publications per year

6
26

Top categories

AI×5NLP×2Crypto×2Multiagent×1Image and Video Processing×1Distributed×1ML×1

Frequent co-authors

Zihan Liu2×
Wanshuang Gou1×
Jialan Zheng1×
Ziyu Li1×
Xun Yuan1×
Kasidit Anmahapong1×

Research Timeline

2026
Understanding Secret Leakage Risks in Code LLMs: A Tokenization Perspective

This paper investigates how Byte-Pair Encoding (BPE) tokenization causes Code LLMs to disproportionately memorize certain types of secrets, a phenomenon termed 'gibberish bias'.

A Survey on Split Learning for LLM Fine-Tuning: Models, Systems, and Privacy Optimizations

This survey provides a comprehensive, structured taxonomy of split learning techniques for fine-tuning Large Language Models (LLMs), covering model optimization, system efficiency, and privacy preservation.

Plan Before Search: Search Agents Need Plan

The paper introduces Plan, a structured agentic behavior that decomposes multi-hop questions into ordered sub-questions before retrieval, and proposes a self-bootstrapping paradigm to train it without relying on model distillation.

MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents

The paper introduces MemCog, a Memory-as-Cognition system that integrates memory access directly into the reasoning process, significantly improving agent performance, especially in proactive memory retrieval tasks.

A physics-informed foundation model for quantitative diffusion MRI

The paper introduces PIGMENT, a physics-informed foundation model that enables reliable quantitative mapping of brain microstructure from extremely sparse or challenging diffusion MRI scans.

Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus

The paper proposes DySCo, a dynamic trust-aware sparse consensus mechanism, to efficiently manage communication in multi-agent LLM systems by selectively connecting agents based on real-time value, thus reducing overhead while maintaining critical cross-validation.

Highlighted terms show continued research focus across papers

Papers

cs.MAcs.AIRecentJun 1, 2026

Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus

Wanshuang Gou, Zihan Liu

The paper proposes DySCo, a dynamic trust-aware sparse consensus mechanism, to efficiently manage communication in multi-agent LLM systems by selectively connecting agents based on real-time value, th…

View →
eess.IVcs.AIRecentMay 29, 2026

A physics-informed foundation model for quantitative diffusion MRI

Zihan Li, Jialan Zheng, Ziyu Li, Xun Yuan +17 more

The paper introduces PIGMENT, a physics-informed foundation model that enables reliable quantitative mapping of brain microstructure from extremely sparse or challenging diffusion MRI scans.

View →
cs.AIRecentMay 27, 2026

Plan Before Search: Search Agents Need Plan

Zhipeng Qian, Zihan Liang, Yufei Ma, Ben Chen +6 more

The paper introduces Plan, a structured agentic behavior that decomposes multi-hop questions into ordered sub-questions before retrieval, and proposes a self-bootstrapping paradigm to train it without…

View →
cs.AIcs.CLRecentMay 27, 2026

MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents

Zihan Li, Xingyu Fan, Feifei Li, Wenhui Que

The paper introduces MemCog, a Memory-as-Cognition system that integrates memory access directly into the reasoning process, significantly improving agent performance, especially in proactive memory r…

View →
cs.CRcs.CLcs.DCRecentApr 27, 2026

A Survey on Split Learning for LLM Fine-Tuning: Models, Systems, and Privacy Optimizations

Zihan Liu, Yizhen Wang, Rui Wang, Xiu Tang +1 more

This survey provides a comprehensive, structured taxonomy of split learning techniques for fine-tuning Large Language Models (LLMs), covering model optimization, system efficiency, and privacy preserv…

View →
cs.CRcs.AIRecentApr 20, 2026

Understanding Secret Leakage Risks in Code LLMs: A Tokenization Perspective

Meifang Chen, Zhe Yang, Huang Nianchen, Yizhan Huang +3 more

This paper investigates how Byte-Pair Encoding (BPE) tokenization causes Code LLMs to disproportionately memorize certain types of secrets, a phenomenon termed 'gibberish bias'.

View →