← Search

Maria Drencheva

2 accepted papers

2026

The Open Proof Corpus: A Large-Scale Study of LLM-Generated Mathematical Proofs

ICLR 2026poster

In recent months, large language models (LLMs) have made significant progress in mathematical proof generation, but further advancement is hindered by the lack of a large-scale, high-quality dataset of human-evaluated proofs. While expensive to create, such a dataset is essential for driving improve…

Cited by 0SourcecodeScholar
2025

GRAIN: Exact Graph Reconstruction from Gradients

ICLR 2025poster

Federated learning claims to enable collaborative model training among multiple clients with data privacy by transmitting gradient updates instead of the actual client data. However, recent studies have shown the client privacy is still at risk due to the, so called, gradient inversion attacks which…