2 papers
cs.LG2025
Lost in Serialization: Invariance and Generalization of LLM Graph Reasoners
Daniel Herbst, Lea Karbevska, Divyanshu Kumar +3
While promising, graph reasoners based on Large Language Models (LLMs) lack built-in invariance to symmetries in graph representations. Operating on sequential graph serializations…
cs.CV2023
SeasFire as a Multivariate Earth System Datacube for Wildfire Dynamics
Ilektra Karasante, Lazaro Alonso, Ioannis Prapas +3
The global occurrence, scale, and frequency of wildfires pose significant threats to ecosystem services and human livelihoods. To effectively quantify and attribute the antecedent…