We are pleased to announce a new publication, a long paper at #CIKM2025 (Seoul, Korea), from the A3 and RCLN teams at the LIPN laboratory, in collaboration with Centrale Supélec. This paper, titled “Dynamic Triangulation-Based Graph Rewiring for Graph Neural Networks” proposes a new graph rewiring method that dynamically selects task-relevant triangles to mitigate oversquashing in GNNs. Congratulations to Hugo Attali (LIPN), Thomas Papastergiou (LIPN), Nathalie Pernelle (LIPN) and Fragkiskos Malliaros (Centrale Supélec) ! 👏

Our paper "Multimodal RAG Enhanced Visual Descriptions", led by @amitkumarjaiswal.bsky.social, has been accepted as a #CIKM2025 short paper! 🎉. We use RAG (retrieval-augmented generation) to address the modality gap between images and text in the same embedding space, e.g. for automatic captioning.