Chelombiev, Ivan

3 publications

ICML 2024 SparQ Attention: Bandwidth-Efficient LLM Inference Luka Ribar, Ivan Chelombiev, Luke Hudlass-Galley, Charlie Blake, Carlo Luschi, Douglas Orr

ICLRW 2024 SparQ Attention: Bandwidth-Efficient LLM Inference Luka Ribar, Ivan Chelombiev, Luke Hudlass-Galley, Charlie Blake, Carlo Luschi, Douglas Orr

ICLR 2019 Adaptive Estimators Show Information Compression in Deep Neural Networks Ivan Chelombiev, Conor Houghton, Cian O'Donnell