Armin Gerami

agerami@umd.edu

🔥 Welcome to my webpage!

📜 Bio

I'm a Computer Science Ph.D. candidate at the University of Maryland, working under the guidance of Prof. Ramani Duraiswami. My research interests lie in the domains of differentiable programming, high performance computing, and signal processing. Currently, I'm working on improving the computational efficiency of transformers, and matrix multiplication in neural networks.

📚 Education

Ph.D., Computer Science, University of Maryland, 2023 - Present.

M.Sc., Electrical Engineering, University of Maryland, 2022 - 2023.

B.Sc., Electrical Engineering, Sharif University of Technology, 2016 - 2020.

🏆 Awards

Recipient of the NSF NeuroPAC Fellowship Award for Summer 2025.

Outstanding graduate research assistant awrad for AY 2023-2024.

Ranked 21st in Iran's National University Entrance Exam (Konkour) in 2016.

🔬 Research

Fastmax: Extensively Optimized Linear Attention Implementation
Armin Gerami, Ramani Duraiswami; Supercomputing'25
Summary: Linear attention (Kernel Separation) is a promising approach for calculating the attention in transformers with linear time complexity. However, it introduces a significant data movement overhead. We present a CUDA library that achieves a 3.3× speedup and 3.6× reduction in memory consumption for linear attention implementation compared to the state-of-the-art.

GUST: Graph Edge-Coloring Utilization for Accelerating Sparse Matrix Vector Multiplication
Armin Gerami, Bahar Asgari; ASPLOS'25
Summary: A software/hardware codesign to accelerate sparse matrix-vector multiplication. The harware enables resource sharing while the graph-edge-coloring schedules the input stream to prevent collisions.

Efficient Spatial Audio Rendering Via Differentiable FIR To IIR Estimation
Armin Gerami, Bowen Zhi, Dmitry N. Zotkin, Ramani Duraiswami; ICASSP'25
Summary: We introduce a novel convex optimization algorithm for estimating FIR filters with an IIR filter, and achieve 2× speedup with an accuracy of %0.01 through differential programming.

Room Impulse Response Synthesis via Differentiable Feedback Delay Networks
Armin Gerami, Ramani Duraiswami; WASPAA'25
Summary: We introduce a computationally efficient and tunable feedback-delay-network (FDN) architecture for real-time room-impulse-response (RIR) rendering, addressing the computational and latency challenges inherent in traditional convolution and Fourier transform-based methods.

🚀 Invention Disclosures

Differentiable FIR To IIR Filter Estimation

Rapid Energy and Emission Auditor

💻 Coding Languages

CUDA, C++, Python, Verilog

(Bonus) Puzzle:

I've chosen a number between 1, 2 and 3. You can ask me one question, and I'll answer with either yes, no or IDK. What should you ask me to determine my chosen number?
(The answer's not say "yes" if it's 1, "no" if 2, and "IDK" if 3. That's lame.)

(Bonus Bonus) Daily Chess Puzzle:

Logo       Logo       Logo       Logo