Elamur Research⌕
☰
home / authors / Yanghao Li

Yanghao Li

Yanghao Li has 2 papers in our library, in 2021–2025, most of them on Language models & pretraining, Reasoning, Vision & language; often with Bowen Zhang, Kaiming He, Piotr Dollar.

2 papers in our library · 2021–2025

OpenAlex · ORCID · h-index 28 · 62 works · 16,764 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 715 times in our library · 12 more in our library without a page yet · ⭐ Paper Stars ranking: #3335

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

🎓Tsinghua UniversityBeijing · China2017–2026 · 15 paperscurrent🎓Peking UniversityBeijing · China2014–2020 · 17 papers🏢MetaMenlo Park · United States2020–2022 · 13 papers🎓University of Chinese Academy of SciencesBeijing · China2019–2025 · 2 papers

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.

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksArtificial Intelligence · 2 worksComputer Vision and Pattern Recognition · 2 worksArts and Humanities · 1 workLanguage and Linguistics · 1 work

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

 Works by year

2020s

20251 paper20211 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Masked Autoencoders Are Scalable Vision Learners (2021 · 596 citations)
    Self-supervised pre-training by predicting removed content transformed NLP (BERT, GPT), but comparable autoencoding approaches in computer vision lagged behind.
  2. Improve Vision Language Model Chain-of-thought Reasoning (2025 · 42 citations)
    Most training data for vision language models (VLMs) pairs images with very brief answers and little explanation. The authors show that this limits chain-of-thought (CoT) ability. Fine-tuning on short ChartQA answers improved direct prediction but barely changed CoT accuracy.

All works

14 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. Multiscale Vision Transformers ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetHaoqi Fan et al.2021 · 1,374 citations
  2. Scale-Aware Trident Networks for Object Detection ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetYanghao Li et al.2019 · 1,103 citations
  3. Co-Occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetWentao Zhu et al.2016 · 923 citations
  4. Exploring Plain Vision Transformer Backbones for Object Detection ↗Lecture notes in computer science · no summary yetYanghao Li et al.2022 · 872 citations
  5. MViTv2: Improved Multiscale Vision Transformers for Classification and Detection ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetYanghao Li et al.2022 · 845 citations
  6. Masked Autoencoders Are Scalable Vision LearnersarXiv:2111.06377Kaiming He, Xinlei Chen, Saining Xie, et al.2021 · 596 citations
  7. Demystifying Neural Style Transfer ↗International Joint Conference on Artificial Intelligence · no summary yetYanghao Li et al.2017 · 526 citations
  8. Masked Autoencoders as Spatiotemporal Learners ↗neural information processing systems · no summary yetChristoph Feichtenhofer et al.2022 · 302 citations
  9. Scaling Language-Image Pre-Training via Masking ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetYanghao Li et al.2023 · 283 citations
  10. Benchmarking Detection Transfer Learning with Vision Transformers ↗arXiv (Cornell University) · no summary yetYanghao Li et al.2021 · 86 citations
  11. Reversible Vision Transformers ↗arXiv:2302.04869 · no summary yetKarttikeya Mangalam et al.2023 · 64 citations
  12. PyTorchVideo ↗ACM International Conference on Multimedia (ACM MM) · no summary yetHaoqi Fan et al.2021 · 50 citations
  13. Improve Vision Language Model Chain-of-thought ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Ruohong Zhang, Bowen Zhang, Yanghao Li, et al.2025 · 42 citations
  14. PyTorchVideo: A Deep Learning Library for Video Understanding ↗arXiv (Cornell University) · no summary yetHaoqi Fan et al.2021 · 4 citations

 Co-authors here

12 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 715 times (of the 149,439 papers whose bibliographies we read); 38 citing papers with a page here →.

Updated

↑ back to top

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