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

Yichen Li

7 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

7
26

Top categories

AI×6ML×3NLP×2Info Retrieval×2Crypto×2Neural Computing×1Networking×1

Frequent co-authors

Yaxuan Kong2×
Qingren Yao2×
Yuqi Nie2×
Yilei Shao2×
Stefan Zohren2×
Anna Vettoruzzo2×

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'.

Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs

The paper proposes an Augmented Model maniPulation (AugMP) strategy, utilizing graph representation learning, to effectively and stealthily manipulate federated fine-tuning of LLMs, significantly degrading global model performance while evading standard defenses.

TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning

The paper introduces TimeSage-MT, a comprehensive multi-turn benchmark designed to rigorously test an LLM agent's ability to perform complex, evolving time series analysis, revealing critical gaps in current agentic reasoning.

Test-Time Training for Zero-Resource Dense Retrieval Reranking

The paper proposes DART, a test-time adaptation method that enhances zero-resource dense retrieval reranking by adaptively tuning a bilinear scoring matrix using pseudo-positive and pseudo-negative examples, achieving significant performance gains with minimal latency.

TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning

The paper introduces TimeSage-MT, a comprehensive multi-turn benchmark designed to rigorously test an LLM agent's ability to perform complex, evolving time series analysis, revealing critical gaps in current agentic reasoning.

Test-Time Training for Zero-Resource Dense Retrieval Reranking

The paper proposes DART, a test-time adaptation method that enhances zero-resource dense retrieval reranking by adaptively tuning a bilinear scoring matrix using pseudo-positive and pseudo-negative examples, achieving significant performance gains with minimal latency.

Algorithm Modelization: Transforming Optimization Algorithms into Evolvable Intelligence

This paper introduces Algorithm Modelization, a paradigm that turns iterative algorithms into trainable models.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.NEEmpiricalRecentOct 16, 2026

Algorithm Modelization: Transforming Optimization Algorithms into Evolvable Intelligence

Jian Yao, Zhiyao Zhang, Yichen Li, Xingyu Wu +1 more

This paper introduces Algorithm Modelization, a paradigm that turns iterative algorithms into trainable models.

View →
cs.CLcs.AIRecentMay 31, 2026

TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning

Yaxuan Kong, Qingren Yao, Yuqi Nie, Yichen Li +6 more

The paper introduces TimeSage-MT, a comprehensive multi-turn benchmark designed to rigorously test an LLM agent's ability to perform complex, evolving time series analysis, revealing critical gaps in…

View →
cs.IRcs.AIcs.LGRecentMay 31, 2026

Test-Time Training for Zero-Resource Dense Retrieval Reranking

Shiyan Liu, Yichen Li

The paper proposes DART, a test-time adaptation method that enhances zero-resource dense retrieval reranking by adaptively tuning a bilinear scoring matrix using pseudo-positive and pseudo-negative ex…

View →
cs.CLcs.AIRecentMay 31, 2026

TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning

Yaxuan Kong, Qingren Yao, Yuqi Nie, Yichen Li +6 more

The paper introduces TimeSage-MT, a comprehensive multi-turn benchmark designed to rigorously test an LLM agent's ability to perform complex, evolving time series analysis, revealing critical gaps in…

View →
cs.IRcs.AIcs.LGRecentMay 31, 2026

Test-Time Training for Zero-Resource Dense Retrieval Reranking

Shiyan Liu, Yichen Li

The paper proposes DART, a test-time adaptation method that enhances zero-resource dense retrieval reranking by adaptively tuning a bilinear scoring matrix using pseudo-positive and pseudo-negative ex…

View →
cs.LGcs.CRcs.NIMay 8, 2026

Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs

Hanlin Cai, Kai Li, Houtianfu Wang, Haofan Dong +3 more

The paper proposes an Augmented Model maniPulation (AugMP) strategy, utilizing graph representation learning, to effectively and stealthily manipulate federated fine-tuning of LLMs, significantly degr…

View →
cs.CRcs.AIApr 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 →