Scholar
Niklas Stefan Nolte
Google Scholar ID: 5elJ_uIAAAAJ
FAIR, Meta
Citations & Impact
Citations
22,089
H-index
74
i10-index
244
Publications
20
Co-authors
0
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Published multiple papers including:
- ‘Transformers Can Navigate Mazes With Multi-Step Prediction’ (Preprint)
- ‘MagicPIG: LSH Sampling for Efficient LLM Generation’ (ICLR)
- ‘The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More’ (NeurIPS)
- ‘Memory Mosaics’ (ICLR)
- ‘From Neurons to Neutrons: A Case Study in Interpretability’ (ICML)
- ‘Towards Understanding Grokking: An Effective Theory of Representation Learning’ (NeurIPS)
- ‘Robust and Provably Monotonic Networks’ (ML: Sci. Technol.) and ‘Expressive Monotonic Neural Networks’ (ICLR)
- Contributed to LHCb software and algorithms enabling data collection, with work published in ACAT, CHEP, Comp. Soft. Big Sci., etc.
Co-authors