Foroozan Karimzadeh

15 papers A* 1C 5Journal 6Unranked 2
YearRankTypeTitle / Venue / Authors
2025 A* conf
CommVQ: Commutative Vector Quantization for KV Cache Compression.
ICML
Junyan Li, Yang Zhang, Muhammad Yusuf Hassan, Talha Chafekar, Tianle Cai, Zhile Ren, Pengsheng Guo, Foroozan Karimzadeh, Colorado Reed, Chong Wang, Chuang Gan
2025 J jnl
CommVQ: Commutative Vector Quantization for KV Cache Compression.
CoRR
Junyan Li, Yang Zhang, Muhammad Yusuf Hassan, Talha Chafekar, Tianle Cai, Zhile Ren, Pengsheng Guo, Foroozan Karimzadeh, Colorado Reed, Chong Wang, Chuang Gan
2025 — conf
MemQuant: Towards Memory-aware Post-Training Quantization for Multimodal Transformers.
AICAS
Kazi Barria Nine, Foroozan Karimzadeh, Zishen Wan, Arijit Raychowdhury
2024 J jnl
Twofold Sparsity: Joint Bit- and Network-Level Sparsity for Energy-Efficient Deep Neural Network Using RRAM Based Compute-In-Memory.
IEEE Access
Foroozan Karimzadeh, Arijit Raychowdhury
2023 — —
Hardware-Friendly Model Compression techniques for Deep Learning Accelerators.
Foroozan Karimzadeh
2023 C conf
Memory-Based Computing for Energy-Efficient AI: Grand Challenges.
VLSI-SoC
Foroozan Karimzadeh, Mohsen Imani, Bahar Asgari, Ningyuan Cao, Yingyan Lin, Yan Fang
2022 J jnl
BitS-Net: Bit-Sparse Deep Neural Network for Energy-Efficient RRAM-Based Compute-In-Memory.
IEEE Trans. Circuits Syst. I Regul. Pap.
Foroozan Karimzadeh, Jong-Hyeok Yoon, Arijit Raychowdhury
2022 C conf
Towards CIM-friendly and Energy-Efficient DNN Accelerator via Bit-level Sparsity.
VLSI-SoC
Foroozan Karimzadeh, Arijit Raychowdhury
2022 C conf
Towards Energy Efficient DNN accelerator via Sparsified Gradual Knowledge Distillation.
VLSI-SoC
Foroozan Karimzadeh, Arijit Raychowdhury
2021 J jnl
A Hardware-Friendly Approach Towards Sparse Neural Networks Based on LFSR-Generated Pseudo-Random Sequences.
IEEE Trans. Circuits Syst. I Regul. Pap.
Foroozan Karimzadeh, Ningyuan Cao, Brian Crafton, Justin Romberg, Arijit Raychowdhury
2020 C conf
Hardware-Aware Pruning of DNNs using LFSR-Generated Pseudo-Random Indices.
ISCAS
Foroozan Karimzadeh, Ningyuan Cao, Brian Crafton, Justin Romberg, Arijit Raychowdhury
2020 C conf
Memory and Energy Efficient Method Toward Sparse Neural Network Using LFSR Indexing.
VLSI-SOC
Foroozan Karimzadeh, Arijit Raychowdhury
2019 J jnl
Hardware-aware Pruning of DNNs using LFSR-Generated Pseudo-Random Indices.
CoRR
Foroozan Karimzadeh, Ningyuan Cao, Brian Crafton, Justin Romberg, Arijit Raychowdhury
2017 J jnl
A comparative review on sleep stage classification methods in patients and healthy individuals.
Comput. Methods Programs Biomed.
Reza Boostani, Foroozan Karimzadeh, Mohammad Nami
2015 — conf
Presenting efficient features for automatic CAP detection in sleep EEG signals.
TSP
Foroozan Karimzadeh, Esmaeil Seraj, Reza Boostani, Mohammad Torabi-Nami