4 papers
Crystalite: A Lightweight Transformer for Efficient Crystal Modeling
Tin Hadži VeljkoviÄ, Joshua Rosenthal, Ivor LonÄariÄ +1
Generative models for crystalline materials often rely on equivariant graph neural networks, which capture geometric structure well but are costly to train and slow to sample. We p…
[Re] Benchmarking LLM Capabilities in Negotiation through Scoreable Games
Jorge Carrasco Pollo, Ioannis Kapetangeorgis, Joshua Rosenthal +1
Large Language Models (LLMs) demonstrate significant potential in multi-agent negotiation tasks, yet evaluation in this domain remains challenging due to a lack of robust and gener…
Efficient Optimization of Hierarchical Identifiers for Generative Recommendation
Federica Valeau, Odysseas Boufalis, Polytimi Gkotsi +2
SEATER is a generative retrieval model that improves recommendation inference efficiency and retrieval quality by utilizing balanced tree-structured item identifiers and contrastiv…
Symmetry-Aware Graph Metanetwork Autoencoders: Model Merging through Parameter Canonicalization
Odysseas Boufalis, Jorge Carrasco-Pollo, Joshua Rosenthal +2
Neural network parameterizations exhibit inherent symmetries that yield multiple equivalent minima within the loss landscape. Scale Graph Metanetworks (ScaleGMNs) explicitly levera…