Elamur Research⌕
☰
home / authors / Daixuan Cheng

Daixuan Cheng

Daixuan Cheng has 2 papers in our library, in 2024–2025, most of them on Language models & pretraining, Reasoning; often with Furu Wei, Shaohan Huang, Bo Dai.

2 papers in our library · 2024–2025

OpenAlex · ORCID · h-index 5 · 16 works · 110 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 126 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #7538

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Renmin University of ChinaBeijing · China2026 · 1 papercurrent🎓Beijing University of Posts and TelecommunicationsBeijing · China2021–2025 · 6 papers🔬State Key Laboratory of Networking and Switching TechnologyBeijing · China2021–2025 · 6 papers🏢MicrosoftRedmond · United States2022–2024 · 5 papers🏛️Beijing Institute for General Artificial IntelligenceBeijing · China2023–2025 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 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 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 works

🧭 Topics 2Research subjects and languages the work is about.Reasoning · 1 workLanguage models & pretraining · 1 work

 Works by year

2020s

20251 paper20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Reasoning with Exploration: An Entropy Perspective (2025 · 63 citations)
    RL training of LLMs with verifiable rewards tends to over-exploit. Models settle into narrow strategies, and reasoning gains level off. The authors ask whether token-level entropy, a classic exploration signal in RL, can identify exploratory reasoning. They analyse Qwen2.5-Base-7B on math problems and find that…
  2. Instruction Pre-Training: Language Models are Supervised Multitask Learners (2024 · 59 citations)
    Modern language models are usually pre-trained on raw text with next-token prediction, while supervised multitask learning is saved for post-training.

All works

3 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. Reasoning with Exploration: An Entropy PerspectivearXiv:2506.14758Daixuan Cheng, Shaohan Huang, Xuekai Zhu, et al.2025 · 63 citations
  2. Instruction Pre-Training: Language Models are Supervised Multitask LearnersConference on Empirical Methods in Natural Language Processing (EMNLP)Daixuan Cheng, Yuxian Gu, Shaohan Huang, et al.2024 · 59 citations
  3. Adapting Large Language Models to Domains via Reading Comprehension ↗arXiv:2309.09530 · no summary yetDaixuan Cheng, Shaohan Huang, Furu Wei2023 · 33 citations

 Co-authors here

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

Venues

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

 Cited by

Papers of our library cite their works 126 times (of the 149,439 papers whose bibliographies we read); 40 citing papers with a page here →.

Updated

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