OpenReview
.net
OpenReview
.net
Login
OpenReview
.net
Login
Maximilian L. Croci
Member of Technical Staff, Microsoft AI
Joined
September 2021
Names
Maximilian L. Croci
(Preferred)
,
Maximilian Croci
,
Maximilian Louis Croci
Emails
****@cam.ac.uk
(Confirmed)
,
****@microsoft.com
(Confirmed)
,
****@microsoft.com
(Confirmed)
Personal Links
Google Scholar
DBLP
Career & Education History
Member of Technical Staff
Microsoft AI
(microsoft.com)
2024
–
Present
Postdoc
Microsoft Research
(microsoft.com)
2022
–
2024
PhD student
University of Cambridge
(cam.ac.uk)
2018
–
2022
MS student
University of Cambridge
(cam.ac.uk)
2017
–
2018
Undergrad student
University of Cambridge
(cam.ac.uk)
2014
–
2017
Advisors, Relations & Conflicts
Coauthor
James Hensman
2022
–
Present
PhD Advisor
Matthew P. Juniper
2018
–
2022
Coauthor
Ushnish Sengupta
2018
–
2022
Expertise
Large language model compression
2022
–
Present
Generative modelling
2022
–
Present
Deep learning
2018
–
Present
Neural networks
2018
–
Present
Bayesian machine learning
2018
–
2022
Inverse problems
2018
–
2022
Stochastic filtering
2018
–
2022
Publications
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
Saleh Ashkboos
,
Amirkeivan Mohtashami
,
Maximilian L. Croci
,
Bo Li
,
Pashmina Cameron
,
Martin Jaggi
,
Dan Alistarh
,
Torsten Hoefler
,
James Hensman
NeurIPS 2024
Readers:
Everyone
Pyramid Vector Quantization for LLMs
Tycho F. A. van der Ouderaa
,
Maximilian L. Croci
,
Agrin Hilmkil
,
James Hensman
Submitted to ICLR 2025
Readers:
Everyone
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
Saleh Ashkboos
,
Amirkeivan Mohtashami
,
Maximilian L. Croci
,
Bo Li
,
Pashmina Cameron
,
Martin Jaggi
,
Dan Alistarh
,
Torsten Hoefler
,
James Hensman
NeurIPS 2024 poster
Readers:
Everyone
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
Saleh Ashkboos
,
Maximilian L. Croci
,
Marcelo Gennari do Nascimento
,
Torsten Hoefler
,
James Hensman
ICLR 2024 poster
Readers:
Everyone
Bayesian parameter inference of a vortically perturbed flame model for the prediction of thermoacoustic instability
Maximilian L. Croci
,
Joel Varun Vasanth
,
Ushnish Sengupta
,
Ekrem Ekici
,
Matthew P Juniper
Published: 17 Nov 2022, Last Modified: 05 May 2023
AI4Science Poster
Readers:
Everyone
Bayesian Inference in Physics-Based Nonlinear Flame Models
Maximilian L. Croci
,
Ushnish Sengupta
,
Matthew P Juniper
Published: 19 Oct 2021, Last Modified: 05 May 2023
NeurIPS 2021 Deep Inverse Workshop Poster
Readers:
Everyone
Online parameter inference for the simulation of a Bunsen flame using heteroscedastic Bayesian neural network ensembles
Maximilian L. Croci
,
Ushnish Sengupta
,
Matthew P. Juniper
2021 (modified: 15 Sept 2021)
CoRR 2021
Readers:
Everyone
Data Assimilation Using Heteroscedastic Bayesian Neural Network Ensembles for Reduced-Order Flame Models
Maximilian L. Croci
,
Ushnish Sengupta
,
Matthew P. Juniper
2021 (modified: 15 Sept 2021)
ICCS (5) 2021
Readers:
Everyone
Real-time parameter inference in reduced-order flame models with heteroscedastic Bayesian neural network ensembles
Ushnish Sengupta
,
Maximilian L. Croci
,
Matthew P. Juniper
2020 (modified: 15 Sept 2021)
CoRR 2020
Readers:
Everyone
Co-Authors
Agrin Hilmkil
Amirkeivan Mohtashami
Bo Li
Dan Alistarh
Ekrem Ekici
James Hensman
Joel Varun Vasanth
Marcelo Gennari do Nascimento
Martin Jaggi
Matthew P Juniper
Matthew P. Juniper
Pashmina Cameron
Saleh Ashkboos
Torsten Hoefler
Tycho F. A. van der Ouderaa
Ushnish Sengupta