Marc Szafraniec
Artificial Intelligence · 2021–2025
A researcher in the Science corpus: 5 papers; trusts 98 researchers and is trusted by 2 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 170 citations into it; #30,609 of 35,345 by trust here, #7,657 by citations
- Computer Vision and Pattern Recognition — 160 citations into it
- Natural Language Processing — 51 citations into it; #4,979 of 5,688 by trust here, #4,449 by citations
- Information Systems — 36 citations into it; #7,288 of 8,771 by trust here, #4,682 by citations
- Large Language Models — 26 citations into it
- Software — 18 citations into it; #1,021 of 1,227 by trust here, #674 by citations
- Signal Processing — 17 citations into it
- Code Generation & Program Synthesis — 16 citations into it
Whom Marc Szafraniec trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Ilya Sutskever
- Yoshua Bengio
- Geoffrey E. Hinton
- Jimmy Ba
- Alex Krizhevsky
- Guillaume Lample
- Kaiming He
- Dzmitry Bahdanau
- Jacob Devlin
Who trusts Marc Szafraniec overall
Papers from Marc Szafraniec's perspective
Ordered by how strongly the researchers Marc Szafraniec trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Attention is All you Need (Neural Information Processing Systems)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- DINOv2: Learning Robust Visual Features without Supervision (2023) — 9,372 citations
- DOBF: A Deobfuscation Pre-Training Objective for Programming Languages (2021) — 173 citations
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning (2025) — 527 citations
- DINOv3 (2025) — 1,140 citations
- Code Translation with Compiler Representations (2022) — 95 citations