🧑‍🔬 Ngai Wong

🏛️ Affiliations

🎓University of Hong KongPok Fu Lam · China2000–2026 · 403 papersEmploymentcurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 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. Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models (2025 · 47 citations)
   Distilling large language models usually means training a student to match the teacher's next-token distribution with a Kullback-Leibler loss.
2. Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies (2024 · 46 citations)
   Standard scaling laws for LLMs predict loss from parameter count and training data but treat vocabulary size as fixed.
3. TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review (2025 · 16 citations)
   Peer review is under strain from growing submission volumes. LLM-based review assistants tend to miss details buried in long papers, give shallow critiques, or, as with multi-agent systems like MARG, consume very large numbers of tokens. TreeReview addresses this by treating reviewing as question answering organised…
4. Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation (2026 · 13 citations)
   Small LLMs are usually distilled by fine-tuning them on outputs from the most powerful available teacher. Prior work shows this can backfire: very strong teachers may produce answers that are too complex or too far from what the student can absorb. Earlier remedies (Mix, CAR) still make every candidate teacher answer…
5. Revisiting Model Interpolation for Efficient Reasoning (2026 · 6 citations)
   The paper looks at efficient reasoning: how to keep the accuracy of long chain-of-thought models while producing fewer tokens.
6. Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models (2026 · 5 citations)
   Compressing small language models (under 8B parameters) to about 2 bits per weight usually ruins their accuracy.

All works

7 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them.

1. Scalable production of ultraflat and ultraflexible diamond membrane ↗Nature · no summary yetJixiang Jing et al.2024 · 71 citations
2. Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language ModelsInternational Conference on Computational Linguistics (COLING)Taiqiang Wu, Chaofan Tao, Jiahao Wang, et al.2025 · 47 citations
3. Scaling Laws with Vocabulary: Larger Models Deserve Larger VocabulariesarXiv:2407.13623Chaofan Tao, Qian Liu, Longxu Dou, et al.2024 · 46 citations
4. TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer ReviewConference on Empirical Methods in Natural Language Processing (EMNLP)Yuan Chang, Ziyue Li, Hengyuan Zhang, et al.2025 · 16 citations
5. Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher DistillationAnnual Meeting of the Association for Computational Linguistics (ACL)Hengyuan Zhang, Shiping Yang, Xiao Liang, et al.2026 · 13 citations
6. Revisiting Model Interpolation for Efficient ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Taiqiang Wu, Runming Yang, Tao Liu, et al.2026 · 6 citations
7. Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language ModelsFindings of the Association for Computational LinguisticsHe Xiao, Qingyao Yang, Dirui Xie, et al.2026 · 5 citations

🤝 Co-authors here

12 of 21 co-authors with a page, the most papers together first.

• Chaofan Tao ×3
• Runming Yang ×3
• Hayden Kwok-Hay So ×2
• Hengyuan Zhang ×2
• Jiahao Wang ×2
• Taiqiang Wu ×2
• Chenming Shang
• Jing Xiong
• Longxu Dou
• Min Lin
• Niklas Muennighoff
• Ping Luo

Venues

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

• Annual Meeting of the Association for Computational Linguistics (ACL) ×2: ACL 2026 ×2
• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026
• International Conference on Computational Linguistics (COLING): COLING 2025
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025
• Nature

🔗 Cited by

Papers of our library cite their works 134 times (of the 149,439 papers whose bibliographies we read); 36 citing papers with a page here →.

Updated 30 October 2026

↑ back to top

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