Seyedarmin Azizi

21 papers A* 1A 2Journal 15Unranked 3
YearRankTypeTitle / Venue / Authors
2026 J jnl
Power-SMC: Low-Latency Sequence-Level Power Sampling for Training-Free LLM Reasoning.
CoRR
Seyedarmin Azizi, Erfan Baghaei Potraghloo, Minoo Ahmadi, Souvik Kundu, Massoud Pedram
2025 J jnl
Activation Steering for Chain-of-Thought Compression.
CoRR
Seyedarmin Azizi, Erfan Baghaei Potraghloo, Massoud Pedram
2025 J jnl
From Filters to VLMs: Benchmarking Defogging Methods through Object Detection and Segmentation Performance.
CoRR
Ardalan Aryashad, Parsa Razmara, Amin Mahjoub, Seyedarmin Azizi, Mahdi Salmani, Arad Firouzkouhi
2025 — conf
MORFI: Mutimodal Zero-Shot Reasoning for Financial Time-Series Inference.
ICCVW
Tina Khezresmaeilzadeh, Parsa Razmara, Mohammad Erfan Sadeghi, Seyedarmin Azizi, Erfan Baghaei Potraghloo
2025 A* conf
MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba.
ICLR
Seyedarmin Azizi, Souvik Kundu, Mohammad Erfan Sadeghi, Massoud Pedram
2025 J jnl
SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models.
CoRR
Jiayi Tian, Seyedarmin Azizi, Yequan Zhao, Erfan Baghaei Potraghloo, Sean McPherson, Sharath Nittur Sridhar, Zhengyang Wang, Zheng Zhang, Massoud Pedram, Souvik Kundu
2025 J jnl
Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation.
CoRR
Erfan Baghaei Potraghloo, Seyedarmin Azizi, Souvik Kundu, Massoud Pedram
2025 J jnl
VISTA: Vision-Language Inference for Training-Free Stock Time-Series Analysis.
CoRR
Tina Khezresmaeilzadeh, Parsa Razmara, Seyedarmin Azizi, Mohammad Erfan Sadeghi, Erfan Baghaei Portaghloo
2024 A conf
Automated Optimization of Deep Neural Networks: Dynamic Bit-Width and Layer-Width Selection via Cluster-Based Parzen Estimation.
DATE
Seyedarmin Azizi, Mahdi Nazemi, Arash Fayyazi, Massoud Pedram
2024 J jnl
Efficient Noise Mitigation for Enhancing Inference Accuracy in DNNs on Mixed-Signal Accelerators.
CoRR
Seyedarmin Azizi, Mohammad Erfan Sadeghi, Mehdi Kamal, Massoud Pedram
2024 — conf
LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation.
EMNLP (Findings)
Seyedarmin Azizi, Souvik Kundu, Massoud Pedram
2024 J jnl
LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation.
CoRR
Seyedarmin Azizi, Souvik Kundu, Massoud Pedram
2024 J jnl
Low-Precision Mixed-Computation Models for Inference on Edge.
IEEE Trans. Very Large Scale Integr. Syst.
Seyedarmin Azizi, Mahdi Nazemi, Mehdi Kamal, Massoud Pedram
2024 — conf
Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy.
ECCV Workshops (11)
Seyedarmin Azizi, Mahdi Nazemi, Massoud Pedram
2024 J jnl
Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy.
CoRR
Seyedarmin Azizi, Mahdi Nazemi, Massoud Pedram
2024 A conf
PEANO-ViT: Power-Efficient Approximations of Non-Linearities in Vision Transformers.
ISLPED
Mohammad Erfan Sadeghi, Arash Fayyazi, Seyedarmin Azizi, Massoud Pedram
2024 J jnl
PEANO-ViT: Power-Efficient Approximations of Non-Linearities in Vision Transformers.
CoRR
Mohammad Erfan Sadeghi, Arash Fayyazi, Seyedarmin Azizi, Massoud Pedram
2023 J jnl
Low-Precision Mixed-Computation Models for Inference on Edge.
CoRR
Seyedarmin Azizi, Mahdi Nazemi, Mehdi Kamal, Massoud Pedram
2023 J jnl
SNT: Sharpness-Minimizing Network Transformation for Fast Compression-friendly Pretraining.
CoRR
Jung Hwan Heo, Seyedarmin Azizi, Arash Fayyazi, Mahdi Nazemi, Massoud Pedram
2023 J jnl
Sensitivity-Aware Mixed-Precision Quantization and Width Optimization of Deep Neural Networks Through Cluster-Based Tree-Structured Parzen Estimation.
CoRR
Seyedarmin Azizi, Mahdi Nazemi, Arash Fayyazi, Massoud Pedram
2022 J jnl
Performance enhancement of an uncertain nonlinear medical robot with optimal nonlinear robust controller.
Comput. Biol. Medicine
Seyedarmin Azizi, Reza Soleimani, Mohsen Ahmadi, Ali Malekan, Laith Abualigah, Fatemeh Dashtiahangar