Sheng Shen

Artificial Intelligence · 2019–2024

A researcher in the Science corpus: 20 papers; trusts 789 researchers and is trusted by 10 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 796 citations into it; #14,893 of 35,345 by trust here, #1,444 by citations
• Computer Vision and Pattern Recognition — 471 citations into it; #10,171 of 21,575 by trust here, #3,057 by citations
• Natural Language Processing — 284 citations into it; #5,008 of 5,688 by trust here, #2,695 by citations
• Large Language Models — 234 citations into it
• Efficiency & Compression — 192 citations into it; #646 of 1,264 by trust here, #352 by citations
• Evaluation & Benchmarks — 149 citations into it
• Model Architectures — 115 citations into it
• Multimodal Learning — 90 citations into it

Whom Sheng Shen trusts overall

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

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

Who trusts Sheng Shen overall

1. Zi-Mei Yao
2. Sehoon Kim
3. A. Gholami
4. Derya Soydaner
5. J. Scott McCarley
6. Canwen Xu
7. Chris Kedzie
8. Kurt Keutzer
9. Wei Zhang
10. Sedigheh Eslami

Papers from Sheng Shen's perspective

Ordered by how strongly the researchers Sheng Shen 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. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Multitask Prompted Training Enables Zero-Shot Task Generalization (2021) — 2,030 citations
• How Much Can CLIP Benefit Vision-and-Language Tasks? (2021) — 516 citations
• Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT (2019) — 675 citations
• Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers (2020) — 157 citations
• Crosslingual Generalization through Multitask Finetuning (2023) — 602 citations
• Pragmatically Informative Text Generation (2019) — 71 citations
• What Language Model to Train if You Have One Million GPU Hours? (2022) — 125 citations
• K-LITE: Learning Transferable Visual Models with External Knowledge (2022) — 107 citations
• Aligning Large Multimodal Models with Factually Augmented RLHF (2023) — 811 citations
• Learned Token Pruning for Transformers (2021) — 225 citations
• Poisoning Language Models During Instruction Tuning (2023) — 359 citations
• ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning (2020) — 383 citations
• AgentBench: Evaluating LLMs as Agents (2023) — 1,063 citations
• The Llama 3 Herd of Models (2024) — 17,085 citations
• RAFT: Adapting Language Model to Domain Specific RAG (2024) — 371 citations
• SqueezeLLM: Dense-and-Sparse Quantization (2023) — 345 citations
• BLOOM: A 176B-Parameter Open-Access Multilingual Language Model (2022) — 2,975 citations
• MLPruning: A Multilevel Structured Pruning Framework for Transformer-based Models (2021) — 14 citations
• PowerNorm: Rethinking Batch Normalization in Transformers (2020) — 90 citations
• An annotated dataset of literary entities (2019) — 104 citations