Da-Cheng Juan

Artificial Intelligence · 2017–2025

A researcher in the Science corpus: 23 papers; trusts 960 researchers and is trusted by 26 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 492 citations into it; #9,073 of 35,345 by trust here, #4,190 by citations
• Computer Vision and Pattern Recognition — 341 citations into it; #6,376 of 21,575 by trust here, #3,525 by citations
• Natural Language Processing — 226 citations into it
• Model Architectures — 128 citations into it; #984 of 2,278 by trust here, #595 by citations
• Evaluation & Benchmarks — 86 citations into it
• Optimization & Training — 65 citations into it
• Representation & Self-Supervised Learning — 52 citations into it
• Efficiency & Compression — 51 citations into it; #682 of 1,264 by trust here, #722 by citations

Whom Da-Cheng Juan trusts overall

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

1. Yoshua Bengio
2. Alex Krizhevsky
3. Geoffrey E. Hinton
4. Kaiming He
5. Diederik P. Kingma
6. Ilya Sutskever
7. Yann LeCun
8. Christian Szegedy
9. Alex Graves
10. Jimmy Ba

Who trusts Da-Cheng Juan overall

1. Dimitrios Stamoulis
2. Soravit Changpinyo
3. Young Geun Kim
4. Yi Tay
5. Ruizhou Ding
6. Xiangxiang Chu
7. Mostafa Dehghani
8. Piyush Sharma
9. Zarana Parekh
10. Ting-Wu Chin

Papers from Da-Cheng Juan's perspective

Ordered by how strongly the researchers Da-Cheng Juan 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. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
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. Learning Multiple Layers of Features from Tiny Images

Their papers

• Synthesizer: Rethinking Self-Attention for Transformer Models (2020) — 407 citations
• Sparse Sinkhorn Attention (2020) — 399 citations
• COCO-GAN: Generation by Parts via Conditional Coordinating (2019) — 149 citations
• DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures (2018) — 197 citations
• Attributed Text Generation via Post-hoc Research and Revision (2022) — 27 citations
• Graph-RISE: Graph-Regularized Image Semantic Embedding (2019) — 43 citations
• OmniNet: Omnidirectional Representations from Transformers (2021) — 33 citations
• Ultra Fine-Grained Image Semantic Embedding (2020) — 23 citations
• Low-Dimensional Hyperbolic Knowledge Graph Embeddings (2020) — 475 citations
• RARR: Researching and Revising What Language Models Say, Using Language Models (2022) — 339 citations
• Task Transfer by Preference-Based Cost Learning (2018) — 56 citations
• On the Robustness of Self-Attentive Models (2019) — 110 citations
• HyperGrid: Efficient Multi-Task Transformers with Grid-wise Decomposable Hyper Projections (2020) — 9 citations
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations
• HyperGrid Transformers: Towards A Single Model for Multiple Tasks (2021) — 44 citations
• Synthesizer: Rethinking Self-Attention in Transformer Models (2020) — 76 citations
• Remix: Rebalanced Mixup (2020) — 304 citations
• Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization (2020) — 50 citations
• InstaNAS: Instance-aware Neural Architecture Search (2018) — 54 citations
• PPP-Net: Platform-aware Progressive Search for Pareto-optimal Neural Architectures (2018) — 58 citations