Reza Shirkavand

Reza Shirkavand

PhD student of Computer Science at the University of Maryland.

About me

I am a PhD candidate in the Department of Computer Science at the University of Maryland, College Park. Currently, I am advised by Dr. Heng Huang. My research interests are in the areas of Efficient Deep Learning, and Generative Models. I am particularly interested in Mixture of Experts. Prior to joining UMD, I received my B.Sc. in Computer Engineering from Sharif University of Technology.

News

Research Highlights

Cost-Aware Contrastive Routing for LLMs

Cost-Aware Contrastive Routing for LLMs

Reza Shirkavand, Shangqian Gao, Peiran Yu, Heng Huang

Code PDF NeurIPS 2025 Spotlight
Bilevel ZOFO: Bridging Parameter-Efficient and Zeroth-Order Techniques for Efficient LLM Fine-Tuning and Meta-Training

Bilevel ZOFO: Bridging Parameter-Efficient and Zeroth-Order Techniques for Efficient LLM Fine-Tuning and Meta-Training

Reza Shirkavand, Peiran Yu, Qi He, Heng Huang

Code PDF NeurIPS 2025
ARGUS: Hallucination and Omission Evaluation in Video-LLMs

ARGUS: Hallucination and Omission Evaluation in Video-LLMs

Ruchit Rawal, Reza Shirkavand, Heng Huang, Gowthami Somepalli, Tom Goldstein

Code PDF ICCV 2025
ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning

ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning

Shangqian Gao, Ting Hua, Reza Shirkavand, Chi-Heng Lin, Zhen Tang, Zhengao Li, Longge Yuan, Fangyi Li, Zeyu Zhang, Alireza Ganjdanesh, Lou Qian, Xu Jie, Yen-Chang Hsu

Code PDF TMLR 2025
Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models

Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models

Reza Shirkavand, Peiran Yu, Shangqian Gao, Gowthami Somepalli, Tom Goldstein, Heng Huang

Code PDF CVPR 2025
Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models

Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models

Reza Shirkavand*, Alireza Ganjdanesh*, Shangqian Gao, Heng Huang

Code PDF ICLR 2025
From Pixels to Prose: A Large Dataset of Dense Image Captions

From Pixels to Prose: A Large Dataset of Dense Image Captions

Vasu Singla, Kaiyu Yue, Sukriti Paul, Reza Shirkavand, Mayuka Jayawardhana, Alireza Ganjdanesh, Heng Huang, Abhinav Bhatele, Gowthami Somepalli, Tom Goldstein

Code PDF
Deep Prompt Tuning for Graph Transformers

Deep Prompt Tuning for Graph Transformers

Reza Shirkavand, Heng Huang

Code PDF
Incomplete Multimodal Learning for Complex Brain Disorders Prediction

Incomplete Multimodal Learning for Complex Brain Disorders Prediction

Reza Shirkavand, Liang Zhan, Heng Huang, Li Shen, Paul M Thompson

Code PDF
Dementia Severity Classification under Small Sample Size and Weak Supervision in Thick Slice MRI

Dementia Severity Classification under Small Sample Size and Weak Supervision in Thick Slice MRI

Reza Shirkavand, Sana Ayromlou, Soroush Farghadani, Maedeh-sadat Tahaei, Fattane Pourakpour, Bahareh Siahlou, Zeynab Khodakarami, Mohammad H Rohban, Mansoor Fatehi, Hamid R Rabiee

Code PDF