New preprint: MUX, continuous reasoning via multiplexed tokens
MUX compresses step-by-step reasoning of language models into continuous latent tokens that each multiplex a span of reasoning.
News
All the news from the group.
New preprint: RelAgent
RelAgent uses LLM agents as data scientists for relational learning, producing predictors that are fast and interpretable.
Two papers accepted to ICML 2026
Categorical Flow Maps and MacroGuide: Topological Guidance for Macrocycle Generation were accepted to ICML 2026.
Louis Tichelman and Angelo Gnazzo join the group
Louis Tichelman and Angelo Gnazzo joined the group as PhD students at TU Wien.
Three papers accepted to ICLR 2026
Topological Flow Matching, HYPER, and Flock were accepted to ICLR 2026.
İsmail is now Associate Professor at TU Wien
İsmail İlkan Ceylan was appointed Associate Professor at TU Wien.
Paper accepted to LoG 2025
One Model, Any Conjunctive Query: Graph Neural Networks for Answering Queries over Incomplete Knowledge Graphs was accepted to the Learning on Graphs Conference 2025.
Two papers accepted to NeurIPS 2025
Equivariance Everywhere All At Once and Curly Flow Matching were accepted to NeurIPS 2025.
Looking for older posts? See the news archive or subscribe via RSS.