🧑‍🔬 Xiaojun Meng

🏛️ Affiliations

🎓Ankang UniversityAnkang · China2024–2026 · 2 paperscurrent🏢Huawei TechnologiesShenzhen · China2025–2026 · 2 paperscurrent🔬Northwest Institute of Nuclear TechnologyXi'an · China2018–2024 · 10 papers🎓Qingdao Agricultural UniversityQingdao · China2024–2025 · 2 papers🔬Beijing Vaccum Electronic Research InstituteBeijing · China2021–2023 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution 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. Pangu Ultra: Pushing the Limits of Dense Large Language Models on Ascend NPUs (2025 · 6 citations)
   Pangu Ultra is Huawei's effort to show that a very deep dense Transformer, trained entirely on Ascend NPUs instead of GPUs, can compete with much larger sparse MoE systems.
2. Dynamic Sampling that Adapts: Self-Aware Iterative Data Persistent Optimization for Mathematical Reasoning (2026 · 4 citations)
   Data selection for training math-reasoning LLMs usually depends on fixed difficulty labels or external scorers.
3. Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity (2025 · 4 citations)
   Sparse Mixture-of-Experts LLMs are cheap per token. However, when experts are spread across accelerators, uneven routing overloads some devices, and the slowest device limits overall speed. The Pangu Team at Huawei proposes Mixture of Grouped Experts (MoGE). Experts are split into equal, non-overlapping groups…
4. MathAgent: Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data Synthesis (2026 · 3 citations)
   Synthetic data for mathematical reasoning is often built either by mutating human-curated seed problems, which limits diversity to the seeds' scope, or by prompting models from scratch, which tends toward repetitive, shallow problems (mode collapse).
5. Why Did Apple Fall: Evaluating Curiosity in Large Language Models (2026 · 1 citation)
   Curiosity-inspired intrinsic rewards are increasingly used in RL training of LLMs, but it has not been checked whether these models actually behave in curious ways, or whether the reported gains simply come from amplified statistical signals such as entropy.
6. Memory-Guided Hard Data Augmentation for Multimodal Named Entity Recognition (2026)
   The paper targets data augmentation for Multimodal Named Entity Recognition (MNER), where images help disambiguate text.

🤝 Co-authors here

12 of 27 co-authors with a page, the most papers together first.

• Jiansheng Wei ×4
• Jun Rao ×2
• Min Zhang ×2
• Wei Guo ×2
• Yanghua Xiao ×2
• Yaoyuan Wang ×2
• Yehui Tang ×2
• Zixiong Yu ×2
• Bo Xu
• Bohan Li
• Can Chen
• Dong Li

Venues

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

• Findings of the Association for Computational Linguistics ×4: Findings of the Association for Computational Linguistics 2026 ×4

🔗 Cited by

Papers of our library cite their works 22 times (of the 149,439 papers whose bibliographies we read); 7 citing papers with a page here →.

Updated 1 November 2026

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