Keivan Alizadeh

Machine Learning Engineer, Apple

Joined

May 2020

Names

Keivan Alizadeh (Preferred)

Keivan Alizadeh vahid

Keivan Alizadeh-Vahid

Emails

****@cs.washington.edu (Confirmed)

****@apple.com (Confirmed)

Personal Links

Google Scholar

Career & Education History

Machine Learning Engineer

Apple (apple.com)

2020 – Present

MS student

University of Washington, Seattle (uw.edu)

2018 – 2020

Undergrad student

Sharif University of Technology (sharif.edu)

2013 – 2017

Advisors, Relations & Conflicts

PhD Advisor

Ali Farhadi

2018 – 2020

Expertise

Large Language Models Reasoning

2024 – 2026

Large Language Models Efficiency

2023 – 2024

Efficienet Neural networks

2018 – 2021

Computer Vision

2018 – 2021

Bayesian Nonparametrics

2016 – 2017

Publications

Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity
Amir Joudaki, Giulia Lanzillotta, Mohammad Samragh, Seyed Iman Mirzadeh, Keivan Alizadeh, Thomas Hofmann, Mehrdad Farajtabar, Fartash Faghri
- ICLR 2026 Poster
- Readers: Everyone
The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
Parshin Shojaee, Seyed Iman Mirzadeh, Keivan Alizadeh, Maxwell Horton, Samy Bengio, Mehrdad Farajtabar
- NeurIPS 2025 poster
- Readers: Everyone
Model Soup for Better RLHF: Weight Space Averaging to Improve Alignment in LLMs
Atoosa Chegini, Hamid Kazemi, Seyed Iman Mirzadeh, Dong Yin, Maxwell Horton, Moin Nabi, Mehrdad Farajtabar, Keivan Alizadeh
- FITML 2024 Poster
- Readers: Everyone
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
Seyed Iman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi, Oncel Tuzel, Samy Bengio, Mehrdad Farajtabar
- ICLR 2025 Poster
- Readers: Everyone
SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHF
Atoosa Chegini, Hamid Kazemi, Seyed Iman Mirzadeh, Dong Yin, Maxwell Horton, Moin Nabi, Mehrdad Farajtabar, Keivan Alizadeh
- Submitted to ICLR 2025
- Readers: Everyone
ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
Seyed Iman Mirzadeh, Keivan Alizadeh-Vahid, Sachin Mehta, Carlo C del Mundo, Oncel Tuzel, Golnoosh Samei, Mohammad Rastegari, Mehrdad Farajtabar
- ICLR 2024 oral
- Readers: Everyone
eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language Models
Minsik Cho, Keivan Alizadeh-Vahid, Qichen Fu, Saurabh Adya, Carlo C del Mundo, Mohammad Rastegari, Devang Naik, Peter Zatloukal
- SAGE 2023
- Readers: Everyone
FLUID: A Unified Evaluation Framework for Flexible Sequential Data
Matthew Wallingford, Aditya Kusupati, Keivan Alizadeh-Vahid, Aaron Walsman, Aniruddha Kembhavi, Ali Farhadi
- Accepted by TMLR
- Readers: Everyone
DKM: Differentiable k-Means Clustering Layer for Neural Network Compression
Minsik Cho, Keivan Alizadeh-Vahid, Saurabh Adya, Mohammad Rastegari
- Published: 28 Jan 2022, Last Modified: 12 Oct 2025
- ICLR 2022 Poster
- Readers: Everyone
In the Wild: From ML Models to Pragmatic ML Systems
Matthew Wallingford, Aditya Kusupati, Keivan Alizadeh-Vahid, Aaron Walsman, Aniruddha Kembhavi, Ali Farhadi
- 28 Sept 2020 (modified: 12 Oct 2025)
- ICLR 2021 Conference Withdrawn Submission
- Readers: Everyone

Co-Authors

View all 30 co-authors