Author

Yunhao Liang

Observed name: Liang, Yunhao

Institutions: Chinese Academy of Sciences, University of Chinese Academy of Sciences

Observed institutions: Chinese Academy of Sciences, University of Chinese Academy of Sciences

OpenAlex ID: A5125067626

Correct Tests Are Not Enough: Measuring and Training Oracle Conversion in Specification-Based Test Generation

2026 · Liang, Yunhao, Gan, Chengguang, et al. · arXiv (Cornell University)

How Output Format Confounds Data Quality and Capability in Instruction Tuning

2026 · Gan, Chengguang, Wei, Hanjun, et al. · arXiv (Cornell University)

Joint Training Is Not Enough: Conditioned Cross-Granularity Training for Multimodal Document Understanding

2026 · Gan, Chengguang, Liang, Yunhao, et al. · arXiv (Cornell University)

Auditing and Decomposing Feedback-Driven Evolution in LLM Test Generation under the Oracle Problem

2026 · Liang, Yunhao, Gan, Chengguang, et al. · arXiv (Cornell University)

Security Tests as Executable Specifications for LLM Code Generation: Benefits, Trade-offs, and Coverage Limits

2026 · Liang, Yunhao, Gan, Chengguang, et al. · arXiv (Cornell University)

Do Code Language Models Follow Tests? Paired Interventions on Program Behavior

2026 · Liang, Yunhao, Gan, Chengguang, et al. · arXiv (Cornell University)

A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism

2026 · Gan, Chengguang, Cai, Zhixi, et al. · arXiv (Cornell University)

MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation

2026 · Gan, Chengguang, Wei, Hanjun, et al. · arXiv (Cornell University)

A Multilingual Dataset and Empirical Validation for the Mutual Reinforcement Effect in Information Extraction

2026 · Association for Computational Linguistics 2026, Gan, Chengguang, et al. · Underline Science Inc.

Scaling Test-Driven Code Generation from Functions to Classes: An Empirical Study

2026 · Liang, Yunhao, Ying, Ruixuan, et al. · arXiv (Cornell University)

GuideWeb: A Benchmark for Automatic In-App Guide Generation on Real-World Web UIs

2026 · Gan, Chengguang, Tsujii, Yoshihiro, et al. · arXiv (Cornell University)

Visual Merit or Linguistic Crutch? A Close Look at DeepSeek-OCR

2026 · Liang, Yunhao, Ying, Ruixuan, et al. · arXiv (Cornell University)

Works count: 12

Citation count:

H-index:

I10-index: