---
title: "Jifeng Dai · Tsinghua University — author profile and papers"
description: "Jifeng Dai, Tsinghua University: 2 papers on Elamur Research (2019–2024), h-index 49 — affiliations, topics, co-authors and who cites them…"
canonical: "https://research.elamur.ai/free/en/authors/jifeng-dai/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/jifeng-dai/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Jifeng Dai

# Jifeng Dai

Jifeng Dai has 2 papers in our library, in 2019–2024, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/), [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/); often with [Lewei Lu](https://md.research.elamur.ai/free/en/authors/lewei-lu/), [Xizhou Zhu](https://md.research.elamur.ai/free/en/authors/xizhou-zhu/), [Yue Cao](https://md.research.elamur.ai/free/en/authors/yue-cao/).

2 papers in our library · 2019–2024

[OpenAlex](https://openalex.org/A5026944066) · [ORCID](https://orcid.org/0000-0002-6785-0785) · [**h-index 49**](https://openalex.org/authors/A5026944066) · [145 works](https://openalex.org/works?filter=author.id:A5026944066) · [34,970 citations](https://openalex.org/works?filter=author.id:A5026944066&sort=cited_by_count:desc) OpenAlex, 2026-10-14

[📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/jifeng-dai/#papers) · [🔗 Cited 1,583 times in our library](https://md.research.elamur.ai/free/en/authors/jifeng-dai/cited-by/) · [17 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #2286](https://md.research.elamur.ai/free/en/paper-stars/page/23/#star-2286)

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Jifeng+Dai) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Jifeng+Dai) · [dblp](https://dblp.org/search?q=Jifeng+Dai) · [ACL Anthology](https://aclanthology.org/search/?q=Jifeng+Dai)

## Affiliations

[🎓**Tsinghua University** Beijing · China 2010–2026 · 57 papers*current*](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) · [🔬**Shanghai Artificial Intelligence Laboratory** Shanghai · China 2022–2025 · 29 papers](https://md.research.elamur.ai/free/en/labs/shanghai-artificial-intelligence-laboratory/) · [🏢**Sensetime** Beijing · China 2020–2022 · 17 papers](https://md.research.elamur.ai/free/en/companies/sensetime/) · [🏢**Microsoft Research Asia** Beijing · China 2016–2019 · 11 papers](https://md.research.elamur.ai/free/en/companies/microsoft-research-asia/) · [🏢**Microsoft** Redmond · United States 2015–2019 · 10 papers](https://md.research.elamur.ai/free/en/companies/microsoft/) · [🎓**Kunming University of Science and Technology** Kunming · China 2022–2024 · 4 papers](https://ror.org/00xyeez13) · [🎓**Beijing University of Civil Engineering and Architecture** Beijing · China 2010–2016 · 4 papers](https://ror.org/02yj0p855) · [🎓**Shanghai Jiao Tong University** Shanghai · China 2020–2022 · 3 papers](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) · [🔬**Beijing National Research Center for Information Science and Technology** Beijing · China 2024–2025 · 2 papers](https://md.research.elamur.ai/free/en/labs/beijing-national-research-center-for-information-science-and-technology/) · [🎓**Chinese University of Hong Kong** Hong Kong · China 2020–2021 · 2 papers](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong/)

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 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 5 The field of science this work belongs to (OpenAlex fields).[Computer Science · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Arts and Humanities · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Artificial Intelligence · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Computer Vision and Pattern Recognition · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Language and Linguistics · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/)

🧭 Topics 3 Research subjects and languages the work is about.[Language models & pretraining · 2 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Reasoning · 1 work](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Vision & language · 1 work](https://md.research.elamur.ai/free/en/topics/multimodal/)

## Works by year

### 2020s

[**2024** 1 paper](https://md.research.elamur.ai/free/en/authors/jifeng-dai/year/2024/)

### 2010s

[**2019** 1 paper](https://md.research.elamur.ai/free/en/authors/jifeng-dai/year/2019/)

## Papers

The most cited first (OpenAlex and our library).

1. **[VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://md.research.elamur.ai/free/en/papers/su-2019-vl-bert-pre-training-generic/)** *(2019 · 1,066 citations)* Vision-and-language tasks such as visual question answering and visual commonsense reasoning have usually been handled by task-specific models.
2. **[Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization](https://md.research.elamur.ai/free/en/papers/wang-2024-enhancing-reasoning-ability-multimodal-large/)** *(2024 · 44 citations)* Open-source multimodal LLMs trained only with pre-training and supervised fine-tuning often score lower when they reason step by step than when they answer directly.

## All works

19 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. **[R-FCN: Object Detection via Region-based Fully Convolutional Networks ↗](https://arxiv.org/abs/1605.06409) arXiv (Cornell University) · no summary yet**Jifeng Dai et al.*2016 · 3,248 citations*
2. **[Deformable ConvNets V2: More Deformable, Better Results ↗](https://doi.org/10.1109/cvpr.2019.00953) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Xizhou Zhu et al.*2019 · 2,786 citations*
3. **[Instance-Aware Semantic Segmentation via Multi-task Network Cascades ↗](https://doi.org/10.1109/cvpr.2016.343) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Jifeng Dai, Kaiming He, Jian Sun*2016 · 1,287 citations*
4. **[BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation ↗](https://doi.org/10.1109/iccv.2015.191) IEEE International Conference on Computer Vision (ICCV) · no summary yet**Jifeng Dai, Kaiming He, Jian Sun*2015 · 1,130 citations*
5. **[Fully Convolutional Instance-Aware Semantic Segmentation ↗](https://doi.org/10.1109/cvpr.2017.472) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Yi Li et al.*2017 · 1,097 citations*
6. **[ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation ↗](https://doi.org/10.1109/cvpr.2016.344) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Di Lin et al.*2016 · 1,096 citations*
7. [**VL-BERT: Pre-training of Generic Visual-Linguistic Representations arXiv:1908.08530**Weijie Su, Xizhou Zhu, Yue Cao, et al.*2019 · 1,066 citations*](https://md.research.elamur.ai/free/en/papers/su-2019-vl-bert-pre-training-generic/)
8. **[InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions ↗](https://doi.org/10.1109/cvpr52729.2023.01385) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Wenhai Wang et al.*2023 · 1,040 citations*
9. **[Planning-oriented Autonomous Driving ↗](https://doi.org/10.1109/cvpr52729.2023.01712) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Yihan Hu et al.*2023 · 965 citations*
10. **[Deep Feature Flow for Video Recognition ↗](https://doi.org/10.1109/cvpr.2017.441) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Xizhou Zhu et al.*2017 · 679 citations*
11. **[An Empirical Study of Spatial Attention Mechanisms in Deep Networks ↗](https://doi.org/10.1109/iccv.2019.00679) IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yet**Xizhou Zhu et al.*2019 · 604 citations*
12. **[Exploring Cross-Image Pixel Contrast for Semantic Segmentation ↗](https://doi.org/10.1109/iccv48922.2021.00721) IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yet**Wenguan Wang et al.*2021 · 570 citations*
13. **[Convolutional feature masking for joint object and stuff segmentation ↗](https://doi.org/10.1109/cvpr.2015.7299025) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Jifeng Dai, Kaiming He, Jian Sun*2015 · 441 citations*
14. **[Instance-Sensitive Fully Convolutional Networks ↗](https://doi.org/10.1007/978-3-319-46466-4_32) Lecture notes in computer science · no summary yet**Jifeng Dai et al.*2016 · 434 citations*
15. **[Fast Convergence of DETR with Spatially Modulated Co-Attention ↗](https://doi.org/10.1109/iccv48922.2021.00360) IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yet**Peng Gao et al.*2021 · 360 citations*
16. **[BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision ↗](https://doi.org/10.1109/cvpr52729.2023.01710) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Chenyu Yang et al.*2023 · 339 citations*
17. **[Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions ↗](https://doi.org/10.1109/cvpr52729.2023.02083) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Yurui Zhu et al.*2023 · 171 citations*
18. **[Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory ↗](https://arxiv.org/abs/2305.17144) arXiv:2305.17144 · no summary yet**Xizhou Zhu et al.*2023 · 96 citations*
19. [**Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization arXiv:2411.10442**Weiyun Wang, Zhe Chen, Wenhai Wang, et al.*2024 · 44 citations*](https://md.research.elamur.ai/free/en/papers/wang-2024-enhancing-reasoning-ability-multimodal-large/)

## Co-authors here

12 of 13 co-authors with a page, the most papers together first.

- [Lewei Lu](https://md.research.elamur.ai/free/en/authors/lewei-lu/) ×2
- [Xizhou Zhu](https://md.research.elamur.ai/free/en/authors/xizhou-zhu/) ×2
- [Yue Cao](https://md.research.elamur.ai/free/en/authors/yue-cao/) ×2
- [Bin Li](https://md.research.elamur.ai/free/en/authors/bin-li/)
- [Furu Wei](https://md.research.elamur.ai/free/en/authors/furu-wei/)
- [Jinguo Zhu](https://md.research.elamur.ai/free/en/authors/jinguo-zhu/)
- [Weijie Su](https://md.research.elamur.ai/free/en/authors/weijie-su/)
- [Weiyun Wang](https://md.research.elamur.ai/free/en/authors/weiyun-wang/)
- [Wenhai Wang](https://md.research.elamur.ai/free/en/authors/wenhai-wang/)
- [Yangzhou Liu](https://md.research.elamur.ai/free/en/authors/yangzhou-liu/)
- [Yu Qiao](https://md.research.elamur.ai/free/en/authors/yu-qiao/)
- [Zhangwei Gao](https://md.research.elamur.ai/free/en/authors/zhangwei-gao/)

## Venues

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

- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings ×10
- IEEE/CVF International Conference on Computer Vision (ICCV) ×3
- [Science China Information Sciences](https://md.research.elamur.ai/free/en/venues/science-china-information-sciences/)
- IEEE International Conference on Computer Vision (ICCV)
- Lecture notes in computer science

## Cited by

Papers of our library cite their works 1,583 times (of the 149,439 papers whose bibliographies we read); [193 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/jifeng-dai/cited-by/).

Updated 30 October 2026