Hongxu Yin

Computer Vision and Pattern Recognition · 2017–2024

A researcher in the Science corpus: 14 papers; trusts 1,152 researchers and is trusted by 12 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 487 citations into it; #8,866 of 21,575 by trust here, #3,848 by citations
• Artificial Intelligence — 442 citations into it; #14,212 of 35,345 by trust here, #7,010 by citations
• Efficiency & Compression — 164 citations into it; #623 of 1,264 by trust here, #360 by citations
• Model Architectures — 104 citations into it
• Multimodal Learning — 72 citations into it
• Optimization & Training — 55 citations into it
• Evaluation & Benchmarks — 54 citations into it
• Generative Models — 47 citations into it

Whom Hongxu Yin trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Alex Krizhevsky
2. Kaiming He
3. Geoffrey E. Hinton
4. Karen Simonyan
5. Yoshua Bengio
6. Ilya Sutskever
7. Diederik P. Kingma
8. Ross B. Girshick
9. Yann LeCun
10. Alex Graves

Who trusts Hongxu Yin overall

1. Xiaoliang Dai
2. Qiankun Gao
3. Xin Dong
4. Shiwei Liu
5. Lin Wang
6. B. Ermiş
7. Ameya Prabhu
8. Arjun Ashok
9. Yuang Liu
10. James Smith

Papers from Hongxu Yin's perspective

Ordered by how strongly the researchers Hongxu Yin trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. ImageNet: A large-scale hierarchical image database
6. Long Short-Term Memory
7. Gradient-based learning applied to document recognition
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. ImageNet Large Scale Visual Recognition Challenge
10. Going deeper with convolutions

Their papers

• Dreaming to Distill: Data-Free Knowledge Transfer via DeepInversion (2019) — 706 citations
• ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation (2018) — 294 citations
• A-ViT: Adaptive Tokens for Efficient Vision Transformer (2021) — 538 citations
• VILA: On Pre-training for Visual Language Models (2023) — 896 citations
• NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm (2017) — 258 citations
• Fully Dynamic Inference With Deep Neural Networks (2020) — 55 citations
• SpatialRGPT: Grounded Spatial Reasoning in Vision Language Model (2024) — 364 citations
• See through Gradients: Image Batch Recovery via GradInversion (2021) — 618 citations
• LongVILA: Scaling Long-Context Visual Language Models for Long Videos (2024) — 306 citations
• DoRA: Weight-Decomposed Low-Rank Adaptation (2024) — 957 citations
• Deep Neural Networks are Surprisingly Reversible: A Baseline for Zero-Shot Inversion (2021) — 11 citations
• Data-free Knowledge Distillation for Object Detection (2021) — 88 citations
• Incremental Learning Using a Grow-and-Prune Paradigm With Efficient Neural Networks (2019) — 36 citations
• Hardware-Guided Symbiotic Training for Compact, Accurate, yet Execution-Efficient LSTM (2019) — 10 citations