Gergely Szilvasy

According to our database, Gergely Szilvasy authored at least 8 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility.

Gergely Szilvasy, Manuel Faysse, Maria Lomeli, Matthijs Douze, Pierre-Emmanuel Mazaré, Loïc Cabannes, Wen-tau Yih, Hervé Jégou

CoRR, May, 2026

The Faiss Library.

Matthijs Douze, Alexandr Guzhva, Chengqi Deng, Jeff Johnson, Gergely Szilvasy, Pierre-Emmanuel Mazaré, Maria Lomeli, Lucas Hosseini, Hervé Jégou

IEEE Trans. Big Data, April, 2026

2025

Short window attention enables long-term memorization.

Loïc Cabannes, Maximilian Beck, Gergely Szilvasy, Matthijs Douze, Maria Lomeli, Jade Copet, Pierre-Emmanuel Mazaré, Gabriel Synnaeve, Hervé Jégou

CoRR, September, 2025

Stochastic activations.

Maria Lomeli, Matthijs Douze, Gergely Szilvasy, Loïc Cabannes, Jade Copet, Sainbayar Sukhbaatar, Jason Weston, Gabriel Synnaeve, Pierre-Emmanuel Mazaré, Hervé Jégou

CoRR, September, 2025

Inference-time sparse attention with asymmetric indexing.

Pierre-Emmanuel Mazaré, Gergely Szilvasy, Maria Lomeli, Francisco Massa, Naila Murray, Hervé Jégou, Matthijs Douze

CoRR, February, 2025

2024

Evaluation data contamination in LLMs: how do we measure it and (when) does it matter?

Aaditya K. Singh, Muhammed Yusuf Kocyigit, Andrew Poulton, David Esiobu, Maria Lomeli, Gergely Szilvasy, Dieuwke Hupkes

CoRR, 2024

Vector search with small radiuses.

Gergely Szilvasy, Pierre-Emmanuel Mazaré, Matthijs Douze

CoRR, 2024

RA-DIT: Retrieval-Augmented Dual Instruction Tuning.

Xi Victoria Lin, Xilun Chen, Mingda Chen, Weijia Shi, Maria Lomeli, Richard James, Pedro Rodriguez, Jacob Kahn, Gergely Szilvasy, Mike Lewis, Luke Zettlemoyer, Wen-tau Yih

Proceedings of the Twelfth International Conference on Learning Representations, 2024