Maksim Kitsak — accepted AI-conference papers

2026

CheckMate! Watermarking Graph Diffusion Models in Polynomial Time

Roberto Gheda, Abele Mălan, Robert Birke, Maksim Kitsak, Lydia Y. Chen

ICLR 2026poster

Watermarking provides an effective means for data governance. However, conventional post-editing graph watermarking approaches degrade the graph quality and involve NP-hard subroutines. Alternatively, recent approaches advocate for embedding watermarking patterns in the noisy latent during data gen…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Connecting Independently Trained Modes via Layer-Wise Connectivity

Yongding Tian, Zaid Al-Ars, Maksim Kitsak, H Peter Hofstee

ICML 2026poster

Empirical studies have shown that continuous low-loss paths can be constructed between independently trained neural network models. This phenomenon, known as mode connectivity, refers to the existence of such paths between distinct modes-i.e., well-trained solutions in parameter space. However, exis…

Cited by 0 Source ↗Scholar ↗