From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 28 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.

📚 Shelves 7Arts and Humanities · 2 works Computer Science · 2 works Artificial Intelligence · 2 works Language and Linguistics · 2 works Computer Science Applications · 1 work Information Systems · 1 work Computer Vision and Pattern Recognition · 1 work

🧭 Topics 1Code & programming languages · 1 work

Works by year

2020s

20241 paper 20231 paper

Papers

The most cited first (OpenAlex and our library).

TACO: Topics in Algorithmic COde generation dataset (2023 · 73 citations)
Benchmarks such as HumanEval and MBPP are close to saturation. They mostly test short, basic functions. Competition-style sets like APPS and CodeContests suffer from duplicates, weak test suites that let wrong code pass, and little detail on which algorithmic abilities a problem demands. TACO, from BAAI and…
Aquila2 Technical Report (2024 · 1 citation)
Most LLMs are pretrained on a fixed dataset over a long run, so it is hard to change the data mix or add new sources partway through. BAAI's Aquila2 is a family of Chinese–English bilingual models at 7B, 34B and an experimental 70B size. They were trained with HeuriMentor (HM), a framework with three parts:

Co-authors here

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

Cited by

Papers of our library cite their works 68 times (of the 149,439 papers whose bibliographies we read); 26 citing papers with a page here →.

Updated 2 November 2026

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

🧑‍🔬 Guang Liu

🏛️ Affiliations

🧭 Fields, topics and concepts

📅 Works by year

2020s

📄 Papers

🤝 Co-authors here

🔗 Cited by

Guang Liu

Affiliations

Fields, topics and concepts

Works by year

Papers

Co-authors here

Cited by