DOI,IST REx ID,Research Group,Title of publication
null,20032,"DaAl,FrLo",Scalable mechanistic neural networks
null,20033,MaMo,High-dimensional analysis of knowledge distillation: Weak-to-Strong generalization and scaling laws
null,20034,DaAl,LDAdam: Adaptive optimization from low-dimensional gradient statistics
null,20035,MaMo,Wide neural networks trained with weight decay provably exhibit neural collapse
null,20036,FrLo,"Near, far: Patch-ordering enhances vision foundation models' scene understanding"
null,20037,DaAl,"Wasserstein distances, neuronal entanglement, and sparsity"
null,20038,DaAl,The journey matters: Average parameter count over pre-training unifies sparse and dense scaling laws