activity
20242026
collaborators

6 papers

cs.LG2026

Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees

Mohammed Nowaz Rabbani Chowdhury, Kaoutar El Maghraoui, Hsinyu Tsai +4

Sparse Mixture-of-Experts (MoE) allows scaling of language and vision models efficiently by activating only a small subset of experts per input. While this reduces computation, the…

cs.AR2025

Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System

Yunhua Fang, Rui Xie, Asad Ul Haq +6

Large Language Model (LLM) inference is increasingly constrained by memory bandwidth, with frequent access to the key-value (KV) cache dominating data movement. While attention spa…

cs.CV2025

EvidenceMoE: A Physics-Guided Mixture-of-Experts with Evidential Critics for Advancing Fluorescence Light Detection and Ranging in Scattering Media

Ismail Erbas, Ferhat Demirkiran, Karthik Swaminathan +6

Fluorescence LiDAR (FLiDAR), a Light Detection and Ranging (LiDAR) technology employed for distance and depth estimation across medical, automotive, and other fields, encounters si…

physics.optics2024

Unlocking Real-Time Fluorescence Lifetime Imaging: Multi-Pixel Parallelism for FPGA-Accelerated Processing

Ismail Erbas, Aporva Amarnath, Vikas Pandey +3

Fluorescence lifetime imaging (FLI) is a widely used technique in the biomedical field for measuring the decay times of fluorescent molecules, providing insights into metabolic sta…

eess.IV2024

Compressing Recurrent Neural Networks for FPGA-accelerated Implementation in Fluorescence Lifetime Imaging

Ismail Erbas, Vikas Pandey, Aporva Amarnath +4

Fluorescence lifetime imaging (FLI) is an important technique for studying cellular environments and molecular interactions, but its real-time application is limited by slow data a…

cs.LG2024

A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts

Mohammed Nowaz Rabbani Chowdhury, Meng Wang, Kaoutar El Maghraoui +3

The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks, i.e., experts, through trainable routers. MoE reduces the training computa…