Dan Su

Artificial Intelligence · with Yu · 2018–2023

A researcher in the Science corpus: 23 papers; trusts 855 researchers and is trusted by 23 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 705 citations into it; #10,379 of 35,345 by trust here, #3,423 by citations
• Natural Language Processing — 402 citations into it
• Computer Vision and Pattern Recognition — 325 citations into it; #17,489 of 21,575 by trust here, #4,245 by citations
• Signal Processing — 196 citations into it; #2,370 of 7,572 by trust here, #853 by citations
• Speech & Audio — 171 citations into it; #1,013 of 1,076 by trust here, #445 by citations
• Generative Models — 132 citations into it; #1,515 of 1,956 by trust here, #1,262 by citations
• Evaluation & Benchmarks — 104 citations into it
• Model Architectures — 80 citations into it

Whom Dan Su trusts overall

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

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

Who trusts Dan Su overall

1. Rongjie Huang
2. Barret Zoph
3. Cong Han
4. Xu Tan
5. Ziwei Ji
6. Orion Weller
7. Deng-Ping Fan
8. Nayeon Lee
9. Yuma Koizumi
10. Dongchao Yang

Papers from Dan Su's perspective

Ordered by how strongly the researchers Dan Su 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. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
9. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
10. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)

Their papers

• Survey of Hallucination in Natural Language Generation (2022) — 5,175 citations
• GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10, 000 Hours of Transcribed Audio (2021) — 607 citations
• Speech Super-Resolution Using Parallel WaveNet (2018) — 21 citations
• Bilateral Denoising Diffusion Models (2021) — 47 citations
• Improving Attention Based Sequence-to-Sequence Models for End-to-End English Conversational Speech Recognition (2018) — 59 citations
• Multi-modal fusion network with multi-scale multi-path and cross-modal interactions for RGB-D salient object detection (2019) — 336 citations
• Improving Attention-Based End-to-End ASR Systems with Sequence-Based Loss Functions (2018) — 10 citations
• Speech-XLNet: Unsupervised Acoustic Model Pretraining For Self-Attention Networks (2019) — 54 citations
• DurIAN: Duration Informed Attention Network For Multimodal Synthesis (2019) — 119 citations
• DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs (2022) — 82 citations
• A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity (2023) — 1,776 citations
• Read before Generate! Faithful Long Form Question Answering with Machine Reading (2022) — 77 citations
• FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis (2022) — 237 citations
• Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training (2022) — 85 citations
• Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters (2021) — 47 citations
• Glow-WaveGAN: Learning Speech Representations from GAN-based Variational Auto-Encoder For High Fidelity Flow-based Speech Synthesis (2021) — 29 citations
• SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts (2021) — 81 citations
• VARA-TTS: Non-Autoregressive Text-to-Speech Synthesis based on Very Deep VAE with Residual Attention (2021) — 24 citations
• Speechmoe2: Mixture-of-Experts Model with Improved Routing (2021) — 41 citations
• Code-Switched Speech Synthesis Using Bilingual Phonetic Posteriorgram with Only Monolingual Corpora (2020) — 22 citations