Sayeh Sharify - RankMe

32 papers A* 8B 1Journal 18Unranked 5

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Early Attentive Sparsification Accelerates Neural Speech Transcription. CoRR Zifei Xu, Sayeh Sharify, Hesham Mostafa, Tristan Webb, Wanzin Yazar, Xin Wang
2025	A*	`conf`	Mixed-Precision Quantization for Deep Vision Models with Integer Quadratic Programming. DAC Zihao Deng, Sayeh Sharify, Xin Wang, Michael Orshansky
2025	A*	`conf`	ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals. ICML Utkarsh Saxena, Sayeh Sharify, Kaushik Roy, Xin Wang
2025	B	`conf`	Understanding the Difficulty of Low-Precision Post-Training Quantization for LLMs. IJCNN Zifei Xu, Sayeh Sharify, Wanzin Yazar, Tristan Webb, Xin Wang
2024	J	`jnl`	Combining multiple post-training techniques to achieve most efficient quantized LLMs. CoRR Sayeh Sharify, Zifei Xu, Wanzin Yazar, Xin Wang
2024	—	`conf`	Post Training Quantization of Large Language Models with Microscaling Formats. ENLSP Sayeh Sharify, Utkarsh Saxena, Zifei Xu, Wanzin Yazar, Ilya Soloveychik, Xin Wang
2024	J	`jnl`	ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals. CoRR Utkarsh Saxena, Sayeh Sharify, Kaushik Roy, Xin Wang
2024	—	`conf`	Scaling laws for post-training quantized large language models. ENLSP Zifei Xu, Alexander Lan, Wanzin Yazar, Tristan Webb, Sayeh Sharify, Xin Wang
2024	J	`jnl`	Scaling laws for post-training quantized large language models. CoRR Zifei Xu, Alexander Lan, Wanzin Yazar, Tristan Webb, Sayeh Sharify, Xin Wang
2024	J	`jnl`	Self-Selected Attention Span for Accelerating Large Language Model Inference. CoRR Tian Jin, Wanzin Yazar, Zifei Xu, Sayeh Sharify, Xin Wang
2024	J	`jnl`	Understanding the difficulty of low-precision post-training quantization of large language models. CoRR Zifei Xu, Sayeh Sharify, Wanzin Yazar, Tristan Webb, Xin Wang
2023	J	`jnl`	Mixed-Precision Quantization with Cross-Layer Dependencies. CoRR Zihao Deng, Xin Wang, Sayeh Sharify, Michael Orshansky
2021	—	`conf`	Boveda: Building an On-Chip Deep Learning Memory Hierarchy Brick by Brick. MLSys Isak Edo Vivancos, Sayeh Sharify, Daniel Ly-Ma, Ameer Abdelhadi, Ciaran Bannon, Milos Nikolic, Mostafa Mahmoud, Alberto Delmas Lascorz, Gennady Pekhimenko, Andreas Moshovos
2020	A*	`conf`	Late Breaking Results: Building an On-Chip Deep Learning Memory Hierarchy Brick by Brick. DAC Isak Edo Vivancos, Sayeh Sharify, Milos Nikolic, Ciaran Bannon, Mostafa Mahmoud, Alberto Delmas Lascorz, Andreas Moshovos
2019	J	`jnl`	Accelerating Image-Sensor-Based Deep Learning Applications. IEEE Micro Mostafa Mahmoud, Dylan Malone Stuart, Zissis Poulos, Alberto Delmas Lascorz, Patrick Judd, Sayeh Sharify, Milos Nikolic, Kevin Siu, Isak Edo Vivancos, Jorge Albericio, Andreas Moshovos
2019	A*	`conf`	Bit-Tactical: A Software/Hardware Approach to Exploiting Value and Bit Sparsity in Neural Networks. ASPLOS Alberto Delmas Lascorz, Patrick Judd, Dylan Malone Stuart, Zissis Poulos, Mostafa Mahmoud, Sayeh Sharify, Milos Nikolic, Kevin Siu, Andreas Moshovos
2019	A*	`conf`	Laconic deep learning inference acceleration. ISCA Sayeh Sharify, Alberto Delmas Lascorz, Mostafa Mahmoud, Milos Nikolic, Kevin Siu, Dylan Malone Stuart, Zissis Poulos, Andreas Moshovos
2019	A*	`conf`	ShapeShifter: Enabling Fine-Grain Data Width Adaptation in Deep Learning. MICRO Alberto Delmas Lascorz, Sayeh Sharify, Isak Edo Vivancos, Dylan Malone Stuart, Omar Mohamed Awad, Patrick Judd, Mostafa Mahmoud, Milos Nikolic, Kevin Siu, Zissis Poulos, Andreas Moshovos
2018	J	`jnl`	Bit-Tactical: Exploiting Ineffectual Computations in Convolutional Neural Networks: Which, Why, and How. CoRR Alberto Delmas, Patrick Judd, Dylan Malone Stuart, Zissis Poulos, Mostafa Mahmoud, Sayeh Sharify, Milos Nikolic, Andreas Moshovos
2018	J	`jnl`	DPRed: Making Typical Activation Values Matter In Deep Learning Computing. CoRR Alberto Delmas, Sayeh Sharify, Patrick Judd, Milos Nikolic, Andreas Moshovos
2018	J	`jnl`	Exploiting Typical Values to Accelerate Deep Learning. Computer Andreas Moshovos, Jorge Albericio, Patrick Judd, Alberto Delmas Lascorz, Sayeh Sharify, Zissis Poulos, Tayler H. Hetherington, Tor M. Aamodt, Natalie D. Enright Jerger
2018	—	`conf`	Identifying and Exploiting Ineffectual Computations to Enable Hardware Acceleration of Deep Learning. NEWCAS Andreas Moshovos, Jorge Albericio, Patrick Judd, Alberto Delmas, Sayeh Sharify, Mostafa Mahmoud, Tayler H. Hetherington, Milos Nikolic, Dylan Malone Stuart, Kevin Siu, Zissis Poulos, Tor M. Aamodt, Natalie D. Enright Jerger
2018	J	`jnl`	Laconic Deep Learning Computing. CoRR Sayeh Sharify, Mostafa Mahmoud, Alberto Delmas Lascorz, Milos Nikolic, Andreas Moshovos
2018	A*	`conf`	Loom: exploiting weight and activation precisions to accelerate convolutional neural networks. DAC Sayeh Sharify, Alberto Delmas Lascorz, Kevin Siu, Patrick Judd, Andreas Moshovos
2018	J	`jnl`	Value-Based Deep-Learning Acceleration. IEEE Micro Andreas Moshovos, Jorge Albericio, Patrick Judd, Alberto Delmas Lascorz, Sayeh Sharify, Tayler H. Hetherington, Tor M. Aamodt, Natalie D. Enright Jerger
2017	—	`conf`	Bit-Pragmatic Deep Neural Network Computing. ICLR (Workshop) Jorge Albericio, Patrick Judd, Alberto Delmas, Sayeh Sharify, Andreas Moshovos
2017	A*	`conf`	Bit-pragmatic deep neural network computing. MICRO Jorge Albericio, Alberto Delmas, Patrick Judd, Sayeh Sharify, Gerard O'Leary, Roman Genov, Andreas Moshovos
2017	J	`jnl`	Cnvlutin2: Ineffectual-Activation-and-Weight-Free Deep Neural Network Computing. CoRR Patrick Judd, Alberto Delmas Lascorz, Sayeh Sharify, Andreas Moshovos
2017	J	`jnl`	Dynamic Stripes: Exploiting the Dynamic Precision Requirements of Activation Values in Neural Networks. CoRR Alberto Delmas, Patrick Judd, Sayeh Sharify, Andreas Moshovos
2017	J	`jnl`	Loom: Exploiting Weight and Activation Precisions to Accelerate Convolutional Neural Networks. CoRR Sayeh Sharify, Alberto Delmas Lascorz, Patrick Judd, Andreas Moshovos
2017	J	`jnl`	Tartan: Accelerating Fully-Connected and Convolutional Layers in Deep Learning Networks by Exploiting Numerical Precision Variability. CoRR Alberto Delmas, Sayeh Sharify, Patrick Judd, Andreas Moshovos
2016	J	`jnl`	Bit-pragmatic Deep Neural Network Computing. CoRR Jorge Albericio, Patrick Judd, Alberto Delmas Lascorz, Sayeh Sharify, Andreas Moshovos