Yiheng Xu
Computer Vision and Pattern Recognition · 2019–2025
A researcher in the Science corpus: 4 papers; trusts 17 researchers and is trusted by 0 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 28 citations into it
- Artificial Intelligence — 22 citations into it
- Model Architectures — 7 citations into it
Whom Yiheng Xu trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Ross B. Girshick
- Jacob Devlin
- Geoffrey E. Hinton
- Alex Krizhevsky
- Shaoqing Ren
- Diederik P. Kingma
- Adam W. Harley
- Yoshua Bengio
- Xu Zhong
Who trusts Yiheng Xu overall
- Yupan Huang
- Geewook Kim
- Shuai Peng
- Minesh Mathew
- Tengchao Lv
- Chenliang Li
- Izzeddin Gur
- Pengyuan Lyu
- Yang Xu
- Lei Cui
Papers from Yiheng Xu's perspective
Ordered by how strongly the researchers Yiheng Xu trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Attention is All you Need (Neural Information Processing Systems)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- ImageNet Large Scale Visual Recognition Challenge
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- LayoutLM: Pre-training of Text and Layout for Document Image Understanding (2019) — 1,049 citations
- OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments (2024) — 919 citations
- LayoutLMv2: Multi-modal Pre-training for Visually-rich Document Understanding (2020) — 702 citations
- Qwen2.5-VL Technical Report (2025) — 5,337 citations