Keivan Alizadeh-Vahid

13 papers A* 4Journal 6Unranked 3
YearRankTypeTitle / Venue / Authors
2025 A* conf
eDKM: An Efficient and Accurate Train-Time Weight Clustering for Large Language Models.
HPCA
Minsik Cho, Keivan Alizadeh-Vahid, Qichen Fu, Saurabh Adya, Carlo C. del Mundo, Mohammad Rastegari, Devang Naik, Peter Zatloukal
2024 — conf
Computational Bottlenecks of Training Small-scale Large Language Models.
ENLSP
Saleh Ashkboos, Seyed-Iman Mirzadeh, Keivan Alizadeh-Vahid, Mohammad Hossein Sekhavat, Moin Nabi, Mehrdad Farajtabar, Fartash Faghri
2024 — conf
Duo-LLM: A Framework for Studying Adaptive Computation in Large Language Models.
ENLSP
Keivan Alizadeh-Vahid, Seyed-Iman Mirzadeh, Hooman Shahrkokhi, Dmitry Belenko, Frank Sun, Minsik Cho, Mohammad Hossein Sekhavat, Moin Nabi, Mehrdad Farajtabar
2024 A* conf
ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models.
ICLR
Iman Mirzadeh, Keivan Alizadeh-Vahid, Sachin Mehta, Carlo C. del Mundo, Oncel Tuzel, Golnoosh Samei, Mohammad Rastegari, Mehrdad Farajtabar
2024 — conf
Scaling Smart: Accelerating Large Language Model Pre-Training with Small Model Initialization.
ENLSP
Mohammad Samragh, Seyed-Iman Mirzadeh, Keivan Alizadeh-Vahid, Fartash Faghri, Minsik Cho, Moin Nabi, Devang Naik, Mehrdad Farajtabar
2024 J jnl
Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization.
CoRR
Mohammad Samragh, Iman Mirzadeh, Keivan Alizadeh-Vahid, Fartash Faghri, Minsik Cho, Moin Nabi, Devang Naik, Mehrdad Farajtabar
2024 J jnl
eDKM: An Efficient and Accurate Train-Time Weight Clustering for Large Language Models.
IEEE Comput. Archit. Lett.
Minsik Cho, Keivan Alizadeh-Vahid, Qichen Fu, Saurabh Adya, Carlo C. del Mundo, Mohammad Rastegari, Devang Naik, Peter Zatloukal
2023 J jnl
FLUID: A Unified Evaluation Framework for Flexible Sequential Data.
Trans. Mach. Learn. Res.
Matthew Wallingford, Aditya Kusupati, Keivan Alizadeh-Vahid, Aaron Walsman, Aniruddha Kembhavi, Ali Farhadi
2023 J jnl
eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language Models.
CoRR
Minsik Cho, Keivan Alizadeh-Vahid, Qichen Fu, Saurabh Adya, Carlo C. del Mundo, Mohammad Rastegari, Devang Naik, Peter Zatloukal
2022 A* conf
DKM: Differentiable k-Means Clustering Layer for Neural Network Compression.
ICLR
Minsik Cho, Keivan Alizadeh-Vahid, Saurabh Adya, Mohammad Rastegari
2021 J jnl
DKM: Differentiable K-Means Clustering Layer for Neural Network Compression.
CoRR
Minsik Cho, Keivan Alizadeh-Vahid, Saurabh Adya, Mohammad Rastegari
2020 A* conf
Butterfly Transform: An Efficient FFT Based Neural Architecture Design.
CVPR
Keivan Alizadeh-Vahid, Anish Prabhu, Ali Farhadi, Mohammad Rastegari
2020 J jnl
In the Wild: From ML Models to Pragmatic ML Systems.
CoRR
Matthew Wallingford, Aditya Kusupati, Keivan Alizadeh-Vahid, Aaron Walsman, Aniruddha Kembhavi, Ali Farhadi