Mohammad Samragh

43 papers A* 3A 4Misc 6Journal 27Unranked 3
YearRankTypeTitle / Venue / Authors
2026 J jnl
SpecMD: A Comprehensive Study On Speculative Expert Prefetching.
CoRR
Duc N. M. Hoang, Ajay Jaiswal, Mohammad Samragh, Minsik Cho
2025 J jnl
MoEs Are Stronger than You Think: Hyper-Parallel Inference Scaling with RoE.
CoRR
Soheil Zibakhsh, Mohammad Samragh, Kumari Nishu, Lauren Hannah, Arnav Kundu, Minsik Cho
2025 A* conf
SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models.
ICML
Han-Byul Kim, Duc N. M. Hoang, Arnav Kundu, Mohammad Samragh, Minsik Cho
2025 J jnl
SPD: Sync-Point Drop for efficient tensor parallelism of Large Language Models.
CoRR
Han-Byul Kim, Duc N. M. Hoang, Arnav Kundu, Mohammad Samragh, Minsik Cho
2025 J jnl
Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential.
CoRR
Mohammad Samragh, Arnav Kundu, David Harrison, Kumari Nishu, Devang Naik, Minsik Cho, Mehrdad Farajtabar
2024 Misc conf
Improving Vision-Inspired Keyword Spotting Using Dynamic Module Skipping in Streaming Conformer Encoder.
ICASSP
Alexandre Bittar, Paul Dixon, Mohammad Samragh, Kumari Nishu, Devang Naik
2024 J jnl
Scalable Binary Neural Network Applications in Oblivious Inference.
ACM Trans. Embed. Comput. Syst.
Xinqiao Zhang, Mohammad Samragh, Siam U. Hussain, Ke Huang, Farinaz Koushanfar
2024 — conf
Scaling Smart: Accelerating Large Language Model Pre-Training with Small Model Initialization.
ENLSP
Mohammad Samragh, Seyed-Iman Mirzadeh, Keivan Alizadeh-Vahid, Fartash Faghri, Minsik Cho, Moin Nabi, Devang Naik, Mehrdad Farajtabar
2024 J jnl
Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization.
CoRR
Mohammad Samragh, Iman Mirzadeh, Keivan Alizadeh-Vahid, Fartash Faghri, Minsik Cho, Moin Nabi, Devang Naik, Mehrdad Farajtabar
2023 Misc conf
HEiMDaL: Highly Efficient Method for Detection and Localization of Wake-Words.
ICASSP
Arnav Kundu, Mohammad Samragh, Minsik Cho, Priyanka Padmanabhan, Devang Naik
2023 Misc conf
I See What You Hear: A Vision-Inspired Method to Localize Words.
ICASSP
Mohammad Samragh, Arnav Kundu, Ting-Yao Hu, Aman Chadha, Ashish Srivastava, Minsik Cho, Oncel Tuzel, Devang Naik
2023 J jnl
Improving vision-inspired keyword spotting using dynamic module skipping in streaming conformer encoder.
CoRR
Alexandre Bittar, Paul Dixon, Mohammad Samragh, Kumari Nishu, Devang Naik
2023 J jnl
Weight subcloning: direct initialization of transformers using larger pretrained ones.
CoRR
Mohammad Samragh, Mehrdad Farajtabar, Sachin Mehta, Raviteja Vemulapalli, Fartash Faghri, Devang Naik, Oncel Tuzel, Mohammad Rastegari
2022 J jnl
I see what you hear: a vision-inspired method to localize words.
CoRR
Mohammad Samragh, Arnav Kundu, Ting-Yao Hu, Minsik Cho, Aman Chadha, Ashish Shrivastava, Oncel Tuzel, Devang Naik
2021 J jnl
AutoRank: Automated Rank Selection for Effective Neural Network Customization.
IEEE J. Emerg. Sel. Topics Circuits Syst.
Mojan Javaheripi, Mohammad Samragh, Farinaz Koushanfar
2021 A* conf
COINN: Crypto/ML Codesign for Oblivious Inference via Neural Networks.
CCS
Siam Umar Hussain, Mojan Javaheripi, Mohammad Samragh, Farinaz Koushanfar
2021 J jnl
CuRTAIL: ChaRacterizing and Thwarting AdversarIal Deep Learning.
IEEE Trans. Dependable Secur. Comput.
Mojan Javaheripi, Mohammad Samragh, Bita Darvish Rouhani, Tara Javidi, Farinaz Koushanfar
2021 J jnl
Hardware/Algorithm Codesign for Adversarially Robust Deep Learning.
IEEE Des. Test
Mojan Javaheripi, Mohammad Samragh, Bita Darvish Rouhani, Tara Javidi, Farinaz Koushanfar
2021 — conf
On the Application of Binary Neural Networks in Oblivious Inference.
CVPR Workshops
Mohammad Samragh, Siam U. Hussain, Xinqiao Zhang, Ke Huang, Farinaz Koushanfar
2021 — conf
Trojan Signatures in DNN Weights.
ICCVW
Greg Fields, Mohammad Samragh, Mojan Javaheripi, Farinaz Koushanfar, Tara Javidi
2021 J jnl
Trojan Signatures in DNN Weights.
CoRR
Greg Fields, Mohammad Samragh, Mojan Javaheripi, Farinaz Koushanfar, Tara Javidi
2021 J jnl
Unsupervised Information Obfuscation for Split Inference of Neural Networks.
CoRR
Mohammad Samragh, Hossein Hosseini, Aleksei Triastcyn, Kambiz Azarian, Joseph Soriaga, Farinaz Koushanfar
2020 J jnl
AdaNS: Adaptive Non-Uniform Sampling for Automated Design of Compact DNNs.
IEEE J. Sel. Top. Signal Process.
Mojan Javaheripi, Mohammad Samragh, Tara Javidi, Farinaz Koushanfar
2020 J jnl
CLEANN: Accelerated Trojan Shield for Embedded Neural Networks.
CoRR
Mojan Javaheripi, Mohammad Samragh, Gregory Fields, Tara Javidi, Farinaz Koushanfar
2020 A conf
CleaNN: Accelerated Trojan Shield for Embedded Neural Networks.
ICCAD
Mojan Javaheripi, Mohammad Samragh, Gregory Fields, Tara Javidi, Farinaz Koushanfar
2020 J jnl
EncoDeep: Realizing Bit-flexible Encoding for Deep Neural Networks.
ACM Trans. Embed. Comput. Syst.
Mohammad Samragh, Mojan Javaheripi, Farinaz Koushanfar
2020 J jnl
GeneCAI: Genetic Evolution for Acquiring Compact AI.
CoRR
Mojan Javaheripi, Mohammad Samragh, Tara Javidi, Farinaz Koushanfar
2020 A conf
GeneCAI: genetic evolution for acquiring compact AI.
GECCO
Mojan Javaheripi, Mohammad Samragh, Tara Javidi, Farinaz Koushanfar
2019 J jnl
ASCAI: Adaptive Sampling for acquiring Compact AI.
CoRR
Mojan Javaheripi, Mohammad Samragh, Tara Javidi, Farinaz Koushanfar
2019 J jnl
CodeX: Bit-Flexible Encoding for Streaming-based FPGA Acceleration of DNNs.
CoRR
Mohammad Samragh, Mojan Javaheripi, Farinaz Koushanfar
2019 J jnl
Safe Machine Learning and Defeating Adversarial Attacks.
IEEE Secur. Priv.
Bita Darvish Rouhani, Mohammad Samragh, Tara Javidi, Farinaz Koushanfar
2019 Misc conf
SparseHD: Algorithm-Hardware Co-optimization for Efficient High-Dimensional Computing.
FCCM
Mohsen Imani, Sahand Salamat, Behnam Khaleghi, Mohammad Samragh, Farinaz Koushanfar, Tajana Rosing
2019 A* conf
XONN: XNOR-based Oblivious Deep Neural Network Inference.
USENIX Security Symposium
M. Sadegh Riazi, Mohammad Samragh, Hao Chen, Kim Laine, Kristin E. Lauter, Farinaz Koushanfar
2019 J jnl
XONN: XNOR-based Oblivious Deep Neural Network Inference.
CoRR
M. Sadegh Riazi, Mohammad Samragh, Hao Chen, Kim Laine, Kristin E. Lauter, Farinaz Koushanfar
2019 J jnl
XONN: XNOR-based Oblivious Deep Neural Network Inference.
IACR Cryptol. ePrint Arch.
M. Sadegh Riazi, Mohammad Samragh, Hao Chen, Kim Laine, Kristin E. Lauter, Farinaz Koushanfar
2018 A conf
Assured deep learning: practical defense against adversarial attacks.
ICCAD
Bita Darvish Rouhani, Mohammad Samragh, Mojan Javaheripi, Tara Javidi, Farinaz Koushanfar
2018 A conf
DeepFense: online accelerated defense against adversarial deep learning.
ICCAD
Bita Darvish Rouhani, Mohammad Samragh, Mojan Javaheripi, Tara Javidi, Farinaz Koushanfar
2018 J jnl
RAPIDNN: In-Memory Deep Neural Network Acceleration Framework.
CoRR
Mohsen Imani, Mohammad Samragh, Yeseong Kim, Saransh Gupta, Farinaz Koushanfar, Tajana Rosing
2018 Misc conf
ReBNet: Residual Binarized Neural Network.
FCCM
Mohammad Ghasemzadeh, Mohammad Samragh, Farinaz Koushanfar
2017 J jnl
CAMsure: Secure Content-Addressable Memory for Approximate Search.
ACM Trans. Embed. Comput. Syst.
M. Sadegh Riazi, Mohammad Samragh, Farinaz Koushanfar
2017 J jnl
CuRTAIL: ChaRacterizing and Thwarting AdversarIal deep Learning.
CoRR
Bita Darvish Rouhani, Mohammad Samragh, Tara Javidi, Farinaz Koushanfar
2017 Misc conf
Customizing Neural Networks for Efficient FPGA Implementation.
FCCM
Mohammad Samragh, Mohammad Ghasemzadeh, Farinaz Koushanfar
2017 J jnl
ResBinNet: Residual Binary Neural Network.
CoRR
Mohammad Ghasemzadeh, Mohammad Samragh, Farinaz Koushanfar