Songfang Huang

Artificial Intelligence · 2007–2023

A researcher in the Science corpus: 15 papers; trusts 362 researchers and is trusted by 9 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 350 citations into it; #12,855 of 35,345 by trust here, #5,749 by citations
• Computer Vision and Pattern Recognition — 267 citations into it
• Natural Language Processing — 170 citations into it
• Multimodal Learning — 121 citations into it
• Large Language Models — 70 citations into it
• Evaluation & Benchmarks — 53 citations into it
• Representation & Self-Supervised Learning — 39 citations into it
• Model Architectures — 37 citations into it

Whom Songfang Huang trusts overall

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

1. Andreas Stolcke
2. Frederick Jelinek
3. Slava M. Katz
4. Yee Whye Teh
5. John K. Kruschke
6. Irving John Good
7. Yoshua Bengio
8. Geoffrey E. Hinton
9. Diederik P. Kingma
10. Kaiming He

Who trusts Songfang Huang overall

1. Li Deng
2. Dong Yu
3. Yuhao Zhang
4. Zhijiang Guo
5. Yanping Chen
6. Nigel G. Ward
7. Arzoo Katiyar

Papers from Songfang Huang's perspective

Ordered by how strongly the researchers Songfang Huang 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. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)

Their papers

• E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning (2021) — 130 citations
• mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections (2022) — 295 citations
• Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling (2015) — 303 citations
• Question Answering on Freebase via Relation Extraction and Textual Evidence (2016) — 303 citations
• StructuralLM: Structural Pre-training for Form Understanding (2021) — 149 citations
• SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels (2021) — 41 citations
• RRHF: Rank Responses to Align Language Models with Human Feedback without tears (2023) — 545 citations
• Hierarchical Bayesian Language Models for Conversational Speech Recognition (2010) — 40 citations
• Cross-language document summarization via extraction and ranking of multiple summaries (2019) — 32 citations
• Addressing Semantic Drift in Generative Question Answering with Auxiliary Extraction (2021) — 29 citations
• Achieving Human Parity on Visual Question Answering (2021) — 24 citations
• Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning (2021) — 228 citations
• VECO: Variable Encoder-decoder Pre-training for Cross-lingual Understanding and Generation (2020) — 23 citations
• Cross-language document summarization via extraction and ranking of multiple summaries (2018)
• Using Prosodic Features in Language Models for Meetings (2007) — 14 citations