Elamur Research⌕
☰
home / authors / Xuanfan Ni

Xuanfan Ni

Xuanfan Ni has 3 papers in our library, in 2025–2026, most of them on Efficient models & compression, Multilingual & cross-lingual NLP, Reasoning; often with Chenyang Lyu, Bo Zeng, Longyue Wang.

3 papers in our library · 2025–2026

OpenAlex · ORCID · Wikidata · h-index 1 · 23 works · 9 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 12 times in our library · ⭐ Paper Stars ranking: #9601

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

🎓Nanjing University of Aeronautics and AstronauticsNanjing · China2023–2026 · 11 paperscurrent🏢Alibaba GroupHangzhou · China2025–2026 · 8 paperscurrent🎓Fudan UniversityShanghai · China2025 · 2 papers🏛️Ministry of Industry and Information TechnologyBeijing · China2023–2024 · 2 papers

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

 Fields, topics and concepts

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

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 3 worksComputer Science · 3 worksArtificial Intelligence · 3 worksComputer Vision and Pattern Recognition · 3 worksLanguage and Linguistics · 3 works

🧭 Topics 3Research subjects and languages the work is about.Multilingual & cross-lingual NLP · 1 workEfficient models & compression · 2 worksReasoning · 1 work

 Works by year

2020s

20261 paper20252 papers

 Papers

The most cited first (OpenAlex and our library).

  1. Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models (2025 · 8 citations)
    Small models are often taught to reason by fine-tuning them on long chain-of-thought (CoT) traces from large reasoning models such as DeepSeek-R1.
  2. Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language (2025 · 5 citations)
    Most benchmarks for LLM instruction following are English-only or plain machine translations, so they handle constraints that don't transfer across languages poorly.
  3. ReFreeKV: Towards Threshold-Free KV Cache Compression (2026)
    KV cache pruning methods such as H2O, SnapKV and CAKE can cut LLM inference memory with little loss, but only when the cache budget is tuned to each dataset or domain.

 Co-authors here

12 of 20 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 12 times (of the 149,439 papers whose bibliographies we read); 7 citing papers with a page here →.

Updated

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