Charbel Sakr

Joined

September 2018

Names

Charbel Sakr (Preferred)

Emails

****@illinois.edu (Confirmed)

****@nvidia.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Researcher

NVIDIA (nvidia.com)

2021 – 2025

PhD student

University of Illinois, Urbana Champaign (illinois.edu)

2015 – 2021

Advisors, Relations & Conflicts

PhD Advisor

Naresh Shanbhag

2015 – 2020

Expertise

Deep Learning Hardware

2015 – 2020

Publications

EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation
Shih-Yang Liu, Maksim Khadkevich, Nai Chit FUNG, Charbel Sakr, Chao-Han Huck Yang, Chien-Yi Wang, Saurav Muralidharan, Hongxu Yin, Kwang-Ting Cheng, Jan Kautz, Yu-Chiang Frank Wang, Pavlo Molchanov, Min-Hung Chen
- TTU at ICLR 2026 (Main)
- Readers: Everyone
EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation
Shih-Yang Liu, Maksim Khadkevich, Nai Chit FUNG, Charbel Sakr, Chao-Han Huck Yang, Chien-Yi Wang, Saurav Muralidharan, Hongxu Yin, Kwang-Ting Cheng, Jan Kautz, Yu-Chiang Frank Wang, Pavlo Molchanov, Min-Hung Chen
- ICLR 2026 Workshop ICBINB
- Readers: Everyone
ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models
Akshat Ramachandran, Marina Neseem, Charbel Sakr, Rangharajan Venkatesan, Brucek Khailany, Tushar Krishna
- ICLR 2026 Oral
- Readers: Everyone
LO-BCQ: Locally Optimal Block Clustered Quantization for 4-bit (W4A4) LLM Inference
Reena Elangovan, Charbel Sakr, Anand Raghunathan, Brucek Khailany
- Accepted by TMLR
- Readers: Everyone
BCQ: Block Clustered Quantization for 4-bit (W4A4) LLM inference
Reena Elangovan, Charbel Sakr, Anand Raghunathan, Brucek Khailany
- Submitted to ICLR 2025
- Readers: Everyone
ESPACE: Dimensionality Reduction of Activations for Model Compression
Charbel Sakr, Brucek Khailany
- NeurIPS 2024 poster
- Readers: Everyone
Fundamental Limits on Energy-Delay-Accuracy of In-Memory Architectures in Inference Applications
Sujan K. Gonugondla, Charbel Sakr, Hassan Dbouk, Naresh R. Shanbhag
- 2022 (modified: 01 Oct 2022)
- IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 2022
- Readers: Everyone
Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training
Charbel Sakr, Steve Dai, Rangharajan Venkatesan, Brian Zimmer, William J. Dally, Brucek Khailany
- 2022 (modified: 01 Oct 2022)
- CoRR 2022
- Readers: Everyone
Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training
Charbel Sakr, Steve Dai, Rangharajan Venkatesan, Brian Zimmer, William J. Dally, Brucek Khailany
- 2022 (modified: 01 Oct 2022)
- ICML 2022
- Readers: Everyone
Optimizing Selective Protection for CNN Resilience
Abdulrahman Mahmoud, Siva Kumar Sastry Hari, Christopher W. Fletcher, Sarita V. Adve, Charbel Sakr, Naresh R. Shanbhag, Pavlo Molchanov, Michael B. Sullivan, Timothy Tsai, Stephen W. Keckler
- 2021 (modified: 01 Oct 2022)
- ISSRE 2021
- Readers: Everyone

View all 29 publications

Co-Authors

View all 45 co-authors