Elamur Research⌕
☰
home / authors / Junhong Wu

Junhong Wu

Junhong Wu has 3 papers in our library, in 2023–2025, most of them on Language models & pretraining, Speech & spoken language; often with Jiajun Zhang, Jianghao Chen, Yangyifan Xu.

3 papers in our library · 2023–2025

OpenAlex · ORCID · h-index 16 · 48 works · 891 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 49 times in our library · ⭐ Paper Stars ranking: #7680

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

🎓University of Chinese Academy of SciencesBeijing · China2023–2026 · 11 paperscurrent🏛️Chinese Academy of SciencesBeijing · China2023–2026 · 9 paperscurrent🔬Institute of AutomationBeijing · China2023–2026 · 9 paperscurrent🔬State Key Laboratory of Clean Energy UtilizationHangzhou2013–2018 · 11 papers🎓Zhejiang UniversityHangzhou · China2013–2018 · 11 papers🎓National Taiwan Ocean UniversityKeelung · Taiwan2022–2025 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 16 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 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 3 worksComputer Science · 3 worksArtificial Intelligence · 3 worksLanguage and Linguistics · 3 worksComputer Vision and Pattern Recognition · 1 work

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 3 worksSpeech & spoken language · 1 work

 Works by year

2020s

20252 papers20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing (2023 · 32 citations)
    Text-trained large language models struggle to take speech as input. Cascaded systems that feed ASR output into an LLM keep the two components separate, and end-to-end speech LLMs depend on speech instruction data, which is rare. The authors first show that training an adapter only to reproduce transcripts makes the…
  2. LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMs (2025 · 12 citations)
    Extending LLMs to long inputs usually relies on continual pre-training with long documents. However, there has been no reliable way to judge whether a long sample actually contains meaningful long-range connections or is just loosely joined text. The authors first show that this matters. Llama2-7B trained on 32K…
  3. Hit the Sweet Spot! Span-Level Ensemble for Large Language Models (2025 · 11 citations)
    Combining several large language models can exploit their complementary strengths, but current ensembling works at two awkward granularities.

 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 49 times (of the 149,439 papers whose bibliographies we read); 15 citing papers with a page here →.

Updated

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