-
MetaMerge: Model Merging with Meta Networks
Merging ViTs and LLMs using a pretrained (graph) neural net.
-
REAM: Compressing Mixture-of-Experts LLMs
Merging experts in Mixture-of-Experts (MoE) LLMs to compress a 235B LLM.
-
NiNo: Learning to Accelerate Training of Neural Networks
Explaining our ICLR 2025 paper and visualizing neuron permutation symmetry.
-
Can we do better than Convolutional Neural Networks?
-
Spectral Graph Convolution Explained and Implemented Step By Step