Zechun Liu

Computer Vision and Pattern Recognition · 2018–2024

A researcher in the Science corpus: 12 papers; trusts 846 researchers and is trusted by 21 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 336 citations into it; #5,930 of 21,575 by trust here, #3,538 by citations
• Artificial Intelligence — 333 citations into it; #8,014 of 35,345 by trust here, #4,316 by citations
• Efficiency & Compression — 125 citations into it
• Model Architectures — 55 citations into it
• Representation & Self-Supervised Learning — 55 citations into it
• Evaluation & Benchmarks — 45 citations into it
• Optimization & Training — 42 citations into it
• Natural Language Processing — 31 citations into it

Whom Zechun Liu trusts overall

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

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

Who trusts Zechun Liu overall

1. Zhiqiang Shen
2. Kwang-Ting Cheng
3. Jing Liu
4. Gaurav Menghani
5. Eric P. Xing
6. Ji Lin
7. Haotong Qin
8. Marios Savvides
9. Wenqi Shao
10. Jianfei Cai

Papers from Zechun Liu's perspective

Ordered by how strongly the researchers Zechun Liu 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

• Single Path One-Shot Neural Architecture Search with Uniform Sampling (2019) — 1,036 citations
• MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning (2023) — 726 citations
• S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (2021) — 24 citations
• Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm (2018) — 648 citations
• MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning (2019) — 640 citations
• Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation (2021) — 167 citations
• Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study (2021) — 83 citations
• SpinQuant: LLM quantization with learned rotations (2024) — 438 citations
• LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding (2024) — 321 citations
• LLM-QAT: Data-Free Quantization Aware Training for Large Language Models (2023) — 398 citations
• ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions (2020) — 434 citations
• Un-mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning (2020) — 122 citations