collaborators

5 papers

cs.IR2026

Quantifying Document Impact in RAG-LLMs

Armin Gerami, Kazem Faghih, Ramani Duraiswami

Retrieval Augmented Generation (RAG) enhances Large Language Models (LLMs) by connecting them to external knowledge, improving accuracy and reducing outdated information. However,…

cs.LG2025

Auditing Algorithmic Bias in Transformer-Based Trading

Armin Gerami, Ramani Duraiswami

Transformer models have become increasingly popular in financial applications, yet their potential risk making and biases remain under-explored. The purpose of this work is to audi…

cs.LG2025

Transformer Based Linear Attention with Optimized GPU Kernel Implementation

Armin Gerami, Ramani Duraiswami

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between tokens, each embedded in a $D…

eess.SP2025

A Scalable MVDR Beamforming Algorithm That is Linear in the Number of Antennas

Sanjaya Herath, Armin Gerami, Kevin Wagner +2

The Minimum Variance Distortionless Response (MVDR) beamforming technique is widely applied in array systems to mitigate interference. However, applying MVDR to large arrays is com…

eess.AS2025

Room Impulse Response Synthesis via Differentiable Feedback Delay Networks for Efficient Spatial Audio Rendering

Armin Gerami, Ramani Duraiswami

We introduce a computationally efficient and tunable feedback delay network (FDN) architecture for real-time room impulse response (RIR) rendering that addresses the computational…