🧑‍🔬 Yihao Liu

🏛️ Affiliations

🎓Vanderbilt UniversityNashville · United States2025–2026 · 10 paperscurrent🎓South China Business College Guangdong University of Foreign StudiesGuangzhou · China2026 · 1 papercurrent🏛️Chinese Academy of SciencesBeijing · China2019–2025 · 23 papers🔬Shenzhen Institutes of Advanced TechnologyShenzhen · China2019–2025 · 21 papers🎓University of Chinese Academy of SciencesBeijing · China2014–2025 · 21 papersEducation 2014–2018 · Bachelor of EngineeringEducation 2018–2023 · Doctor of Philosophy🎓Johns Hopkins UniversityBaltimore · United States2021–2025 · 14 papers🔬Shanghai Artificial Intelligence LaboratoryShanghai · China2023–2025 · 11 papersEmployment since 2023 · Researcher🎓China University of Geosciences (Beijing)Beijing · China2021–2023 · 4 papers🔬State Key Laboratory of Geological Processes and Mineral ResourcesWuhan2021–2023 · 4 papers🎓Nanyang Technological UniversitySingapore · Singapore2021–2024 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 29 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills (2026 · 12 citations)
   LLM agents increasingly depend on skill files, which are reusable documents describing procedures for a domain.
2. TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Models (2025 · 8 citations)
   Large language models often misread tables when tuned with parameter-efficient methods such as LoRA. Flattening a grid into a token sequence hides which cells share a row or column, and nested headers become hard to interpret. TableLoRA is a PEFT-compatible module that addresses these problems with two components:

All works

5 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. RankSRGAN: Generative Adversarial Networks With Ranker for Image Super-Resolution ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetWenlong Zhang et al.2019 · 406 citations
2. FD-GAN: Generative Adversarial Networks with Fusion-Discriminator for Single Image Dehazing ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetDong Yu et al.2020 · 294 citations
3. Learn to Match: Automatic Matching Network Design for Visual Tracking ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetZhipeng Zhang et al.2021 · 262 citations
4. Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent SkillsarXiv:2603.25158Jingwei Ni, Yihao Liu, Xinpeng Liu, et al.2026 · 12 citations
5. TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Xinyi He, Yihao Liu, Mengyu Zhou, et al.2025 · 8 citations

🤝 Co-authors here

8 co-authors with a page, the most papers together first.

• Mengyu Zhou ×2
• Dongmei Zhang
• Haoyu Dong
• Jingwei Ni
• Shi Han
• Xiaoxi Jiang
• Xinyi He
• Yutao Sun

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• IEEE/CVF International Conference on Computer Vision (ICCV) ×2
• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2025
• Proceedings of the AAAI Conference on Artificial Intelligence

🔗 Cited by

Papers of our library cite their works 24 times (of the 149,439 papers whose bibliographies we read); 4 citing papers with a page here →.

Updated 3 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/yihao-liu/