An Ran Chen

Affiliation:

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Eval Frameworks & Benchmarks (2)Code Generation & Program Synthesis (2)Architecture Design (Transformers, SSMs, MoE) (1)Natural Language Processing (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Sepideh Hodaeian (1)Sepideh Hodaeian (1)Zhenhao Li (1)An-Ran Chen (1)Xinyu Shi (1)Xinyu Shi (1)Zhou Yang (1)He Yang Yuan (1)

Papers (3)

Sep 21, 2026

Affiliation:3w ago

TAILOR: Template-Preserving Augmentation for Long-Tailed Log Parsing

TAILOR, a log parsing framework that improves template inference for rare log groups through template-preserving augmentation, is proposed and experimental results show that TAILOR improves parsing accuracy on rare log groups by 19% over the strongest baseline while maintaining competitive performance on complete datasets.

Sepideh Hodaeian, Sepideh Hodaeian, Zhenhao Li +2

Architecture Design (Transformers, SSMs, MoE)Eval Frameworks & Benchmarks

Jul 22, 2026

Jul 22, 2026·also Affiliation:

Bridging Behavior and Implementation: Automated Java Glue Code Generation for Behavior-Driven Development

AutoGlue achieves a 58.7% improvement in API F1 scores, demonstrating that LLMs can seamlessly translate natural-language requirements into executable code.

Xinyu Shi, Xinyu Shi, Zhou Yang +1

Code Generation & Program Synthesis Natural Language Processing

Apr 22, 2026

He Yang Yuan +3Apr 22, 2026·also Affiliation:

Towards Secure Logging: Characterizing and Benchmarking Logging Code Security Issues with LLMs

LLMs are surprisingly bad at fixing real-world logging security vulnerabilities, despite being moderately effective at detecting them.

He Yang Yuan, Xin Wang, Kundi Yao +1

Code Generation & Program Synthesis Eval Frameworks & Benchmarks Red-Teaming & Adversarial Robustness