Torsten Hoefler

Artificial Intelligence · International Conference on Learning Representations · 2014–2024

A researcher in the Science corpus: 14 papers; trusts 1,121 researchers and is trusted by 35 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 394 citations into it; #5,938 of 35,345 by trust here, #3,551 by citations
• Computer Vision and Pattern Recognition — 270 citations into it; #6,398 of 21,575 by trust here, #4,067 by citations
• Optimization & Training — 174 citations into it; #1,109 of 2,601 by trust here, #661 by citations
• Efficiency & Compression — 120 citations into it; #627 of 1,264 by trust here, #461 by citations
• Model Architectures — 102 citations into it
• Large Language Models — 62 citations into it; #572 of 799 by trust here, #544 by citations
• ML Systems & Hardware — 62 citations into it
• Natural Language Processing — 60 citations into it

Whom Torsten Hoefler trusts overall

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

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

Who trusts Torsten Hoefler overall

1. Elias Frantar
2. Ahmed Khaled
3. Tim Dettmers
4. Hanlin Tang
5. Dan Alistarh
6. Sebastian U. Stich
7. Peter Richtárik
8. Mingjie Sun
9. Marwa El Halabi
10. Tal Ben-Nun

Papers from Torsten Hoefler's perspective

Ordered by how strongly the researchers Torsten Hoefler 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. Long Short-Term Memory
5. Attention is All you Need (Neural Information Processing Systems)
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. Going deeper with convolutions

Their papers

• Augment Your Batch: Improving Generalization Through Instance Repetition (2020) — 256 citations
• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers (2022) — 2,286 citations
• Data Movement Is All You Need: A Case Study on Optimizing Transformers (2020) — 190 citations
• Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks (2021) — 986 citations
• Demystifying Parallel and Distributed Deep Learning (2018) — 809 citations
• Neural Code Comprehension: A Learnable Representation of Code Semantics (2018) — 276 citations
• Augment your batch: better training with larger batches (2019) — 79 citations
• The Convergence of Sparsified Gradient Methods (2018) — 553 citations
• SparCML: High-Performance Sparse Communication for Machine Learning (2018) — 149 citations
• SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression (2023) — 444 citations
• SliceGPT: Compress Large Language Models by Deleting Rows and Columns (2024) — 412 citations
• QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs (2024) — 576 citations
• OPTQ: Accurate Quantization for Generative Pre-trained Transformers (2023) — 431 citations
• Slim Fly: A Cost Effective Low-Diameter Network Topology (2014) — 301 citations