Elamur Research⌕
☰
home / authors / Zesen Cheng

Zesen Cheng

Zesen Cheng has 2 papers in our library, in 2024–2025, most of them on Language models & pretraining, Speech & spoken language; often with Chang Gao, Deli Zhao, Guanzheng Chen.

2 papers in our library · 2024–2025

OpenAlex · ORCID · h-index 11 · 33 works · 457 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 454 times in our library · ⭐ Paper Stars ranking: #4303

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

🏢Alibaba GroupSan Mateo · United States2026 · 1 papercurrent🎓Peking UniversityBeijing · China2023–2025 · 24 papers🏢Alibaba GroupHangzhou · China2024–2025 · 5 papers🏢Alibaba GroupGeorge Town · Cayman Islands2024–2025 · 4 papers🏢Alibaba DAMO AcademyHangzhou · China2024–2025 · 3 papers🔬State Key Laboratory of Oncology in South ChinaGuangzhou2020–2025 · 3 papers🏥Sun Yat-sen University Cancer CenterGuangzhou · China2020–2025 · 3 papers🎓South China University of TechnologyGuangzhou · China2020–2021 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 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 · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksComputer Vision and Pattern Recognition · 2 worksLanguage and Linguistics · 2 works

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

 Works by year

2020s

20251 paper20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Qwen3-VL Technical Report (2025 · 370 citations)
    Qwen3-VL is the Qwen Team's newest open family of vision–language models. Its goal is to handle text, images and video in one model, with long contexts and strong reasoning, while keeping the language skills of the underlying LLM. The family is built on Qwen3 and comes in four dense sizes and two mixture-of-experts…
  2. VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs (2024 · 118 citations)
    Video-LLMs lag behind image-focused multimodal models because they fuse information across frames poorly and usually ignore the soundtrack. VideoLLaMA 2, from DAMO Academy (Alibaba Group), tackles both weaknesses while keeping the modular two-branch layout of the original VideoLLaMA.

 Co-authors here

12 of 16 co-authors with a page, the most papers together first.

 Cited by

Papers of our library cite their works 454 times (of the 149,439 papers whose bibliographies we read); 136 citing papers with a page here →.

Updated

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