Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.


A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.


The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.

Normalization in Attention Dynamics

Authors: Nikita Karagodin, Shu Ge, Yury Polyanskiy, Philippe Rigollet

NeurIPS 2025 | Venue PDF | LLM Run Details | Input Tokens: 25,356 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 2,256 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.

Reproducibility Variable Result LLM Response
Research Type Theoretical The paper has no experiments to reproduce
Researcher Affiliation Academia 1Department of EECS, MIT, Cambridge, MA, USA 2Department of Mathematics, MIT, Cambridge, MA, USA
Pseudocode No The paper describes mathematical formulations and tables of normalization schemes, but it does not contain explicit pseudocode or algorithm blocks.
Open Source Code No Paper does not include experiments requiring code.
Open Datasets No The paper does not use any specific datasets for empirical evaluation. It is a theoretical paper as indicated by 'The paper has no experiments to reproduce'.
Dataset Splits No The paper does not use any datasets, thus no dataset split information is provided.
Hardware Specification No There are no experiments
Software Dependencies No Paper does not include experiments requiring code.
Experiment Setup No The paper does not include experiments