Tianyu Pang

Artificial Intelligence · 2017–2025

A researcher in the Science corpus: 17 papers; trusts 997 researchers and is trusted by 60 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 584 citations into it; #4,089 of 35,345 by trust here, #3,167 by citations
• Safety, Robustness & Interpretability — 326 citations into it; #351 of 2,251 by trust here, #316 by citations
• Computer Vision and Pattern Recognition — 315 citations into it; #6,408 of 21,575 by trust here, #4,807 by citations
• Signal Processing — 96 citations into it
• Optimization & Training — 73 citations into it
• Model Architectures — 69 citations into it
• Molecular Biology — 54 citations into it
• Generative Models — 45 citations into it

Whom Tianyu Pang trusts overall

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

1. Alex Krizhevsky
2. Kaiming He
3. Geoffrey E. Hinton
4. Ian J. Goodfellow
5. Diederik P. Kingma
6. Christian Szegedy
7. Yann LeCun
8. Yoshua Bengio
9. Ilya Sutskever
10. Nicholas Carlini

Who trusts Tianyu Pang overall

1. Yinpeng Dong
2. Cihang Xie
3. Xiao Yang
4. Sven Gowal
5. Naveed Akhtar
6. Hang Su
7. Zekai Wang
8. Anqi Mao
9. Jun Zhu
10. Sylvestre-Alvise Rebuffi

Papers from Tianyu Pang's perspective

Ordered by how strongly the researchers Tianyu Pang 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. ImageNet: A large-scale hierarchical image database
5. Attention is All you Need (Neural Information Processing Systems)
6. Gradient-based learning applied to document recognition
7. Long Short-Term Memory
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Boosting Adversarial Attacks with Momentum (2017) — 3,379 citations
• Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser (2017) — 1,036 citations
• Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks (2019) — 1,121 citations
• Improving Adversarial Robustness via Promoting Ensemble Diversity (2019) — 504 citations
• Boosting Adversarial Training with Hypersphere Embedding (2020) — 170 citations
• Adversarial Attacks and Defences Competition (2018) — 353 citations
• Bag of Tricks for Training Data Extraction from Language Models (2023) — 95 citations
• Bag of Tricks for Adversarial Training (2020) — 306 citations
• Efficient Learning of Generative Models via Finite-Difference Score Matching (2020) — 65 citations
• Understanding R1-Zero-Like Training: A Critical Perspective (2025) — 1,176 citations
• LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition (2023) — 393 citations
• Better Diffusion Models Further Improve Adversarial Training (2023) — 317 citations
• On Evaluating Adversarial Robustness of Large Vision-Language Models (2023) — 369 citations
• Benchmarking Adversarial Robustness on Image Classification (2020) — 304 citations
• Improving Black-box Adversarial Attacks with a Transfer-based Prior (2019) — 306 citations
• Geometric Universality of Adversarial Examples in Deep Learning (2018)
• Towards Robust Detection of Adversarial Examples (2017) — 236 citations