Tim Dettmers
Artificial Intelligence · 2015–2023
A researcher in the Science corpus: 14 papers; trusts 1,562 researchers and is trusted by 228 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 590 citations into it; #2,245 of 36,961 by trust here, #2,240 by citations
- Computer Vision and Pattern Recognition — 314 citations into it; #5,830 of 21,973 by trust here, #2,206 by citations
- Efficiency & Compression — 192 citations into it; #85 of 1,273 by trust here, #138 by citations
- Large Language Models — 178 citations into it; #403 of 810 by trust here, #294 by citations
- Natural Language Processing — 168 citations into it
- Optimization & Training — 82 citations into it; #884 of 2,605 by trust here, #1,387 by citations
- Evaluation & Benchmarks — 81 citations into it
- Model Architectures — 74 citations into it
Whom Tim Dettmers trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Yoshua Bengio
- Geoffrey E. Hinton
- Kaiming He
- Diederik P. Kingma
- Yann LeCun
- Ilya Sutskever
- Jimmy Ba
- J. Urgen Schmidhuber
- Alex Graves
Who trusts Tim Dettmers overall
- Elias Frantar
- Luke S. Zettlemoyer
- Dan Alistarh
- Sidak Pal Singh
- Seyed Mehran Kazemi
- Ji Lin
- Gaurav Menghani
- Sehoon Kim
- Tal Ben-Nun
- Wenqi Shao
Papers from Tim Dettmers's perspective
Ordered by how strongly the researchers Tim Dettmers trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- BLOOM: A 176B-Parameter Open-Access Multilingual Language Model (2022) — 2,975 citations
- BASE Layers: Simplifying Training of Large, Sparse Models (2021) — 411 citations
- Convolutional 2D Knowledge Graph Embeddings (2017) — 3,143 citations
- LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale (2022) — 1,133 citations
- 8-bit Optimizers via Block-wise Quantization (2021) — 509 citations
- Sparse Networks from Scratch: Faster Training without Losing Performance (2019) — 378 citations
- QLoRA: Efficient Finetuning of Quantized LLMs (2023) — 5,083 citations
- Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models (2022) — 213 citations
- The case for 4-bit precision: k-bit Inference Scaling Laws (2022) — 338 citations
- 8-Bit Approximations for Parallelism in Deep Learning (2015) — 203 citations
- Stable and low-precision training for large-scale vision-language models (2023) — 94 citations
- SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression (2023) — 444 citations
- GPT3.int8(): 8-bit Matrix Multiplication for Transformers at Scale (2022) — 933 citations
- High Performance Natural Language Processing (2020) — 6 citations