Boris Knyazev

REAM: Merging Improves Pruning of Experts in LLMs

arXiv 2026

Celo2: Towards Learned Optimization Free Lunch

arXiv 2026

Generating $π$-Functional Molecules Using STGG+ with Active Learning

arXiv 2025

Graph Neural Networks for Learning Equivariant Representations of Neural Networks

arXiv 2024

LoGAH: Predicting 774-Million-Parameter Transformers using Graph HyperNetworks with 1/100 Parameters

arXiv 2024

Accelerating Training with Neuron Interaction and Nowcasting Networks

arXiv 2024

Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?

arXiv 2023

Parameter Prediction for Unseen Deep Architectures

NeurIPS 2021 12

Generative Compositional Augmentations for Scene Graph Prediction

ICCV 2021 10

Eugene Belilovsky

Abhinav Moudgil

Alexia Jolicoeur-Martineau

Graham W. Taylor

Simon Lacoste-Julien

Yan Zhang

Aaron Courville

Adriana Romero-Soriano

Ali Parviz

Ali Saheb Pasand