Aref Jafari

Researcher, Advanced Micro Devices

PhD student, University of Waterloo

Joined

September 2020

Names

Aref Jafari (Preferred)

Emails

****@uwaterloo.ca (Confirmed)

****@gmail.com (Confirmed)

****@amd.com (Confirmed)

Personal Links

Google Scholar

DBLP

Semantic Scholar

Career & Education History

Researcher

Advanced Micro Devices (amd.com)

2025 – Present

PhD student

University of Waterloo (uwaterloo.ca)

2021 – Present

Researcher

Huawei Technologies Ltd. (huawei.com)

2021 – 2025

Advisors, Relations & Conflicts

PhD Advisor

Ali Ghodsi

2021 – Present

Coworker

Mehdi Rezagholizadeh

2020 – Present

Expertise

Knowledge Distillation

2020 – Present

Deep Learning

2016 – Present

Natural Language Processing

2016 – Present

Publications

DTRNet: Dynamic Token Routing Network to Reduce Quadratic Costs in Transformers
Aman Sharma, Saeed Najafi, Parsa Farinneya, Benyamin Jamialahmadi, Marzieh S. Tahaei, Yuhe Fan, Mehdi Rezagholizadeh, Boxing Chen, Aref Jafari
- OpenReview Archive Direct Upload
- Readers: Everyone
Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling
Parsa Ashrafi Fashi, Utkarsh Saxena, Mehdi Rezagholizadeh, Aref Jafari, Akash Haridas, Mingyu Yang, Vansh Bhatia, Guihong Li, Vikram Appia, Emad Barsoum
- CoRR 2026
- Readers: Everyone
SCOUT: Toward Sub-Quadratic Attention via Segment Compression for Optimized Utility in Transformers
Aref Jafari, Yuhe Fan, Benyamin Jamialahmadi, Parsa Farinneya, Boxing Chen, Marzieh S. Tahaei
- CoRR 2025
- Readers: Everyone
DTRNet: Dynamic Token Routing Network to Reduce Quadratic Costs in Transformers
Aman Sharma, Saeed Najafi, Parsa Farinneya, Benyamin Jamialahmadi, Marzieh S. Tahaei, Yuhe Fan, Mehdi Rezagholizadeh, Boxing Chen, Aref Jafari
- CoRR 2025
- Readers: Everyone
Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models
Benyamin Jamialahmadi, Parsa Kavehzadeh, Mehdi Rezagholizadeh, Parsa Farinneya, Hossein Rajabzadeh, Aref Jafari, Boxing Chen, Marzieh S. Tahaei
- CoRR 2025
- Readers: Everyone
EchoAtt: Attend, Copy, then Adjust for More Efficient Large Language Models
Hossein Rajabzadeh, Aref Jafari, Aman Sharma, Benyamin Jami, Hyock Ju Kwon, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
- CoRR 2024
- Readers: Everyone
Efficient Citer: Tuning Large Language Models for Enhanced Answer Quality and Verification
Marzieh S. Tahaei, Aref Jafari, Ahmad Rashid, David Alfonso-Hermelo, Khalil Bibi, Yimeng Wu, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
- NAACL-HLT (Findings) 2024
- Readers: Everyone
Do we need Label Regularization to Fine-tune Pre-trained Language Models?
Ivan Kobyzev, Aref Jafari, Mehdi Rezagholizadeh, Tianda Li, Alan Do-Omri, Peng Lu, Pascal Poupart, Ali Ghodsi
- 15 Dec 2023
- OpenReview Archive Direct Upload
- Readers: Everyone

View all 26 publications

Co-Authors

View all 38 co-authors