Get started
Author

Seyedarmin Azizi

Observed name: Azizi, Seyedarmin
Observed institution: University of Southern California
ORCID: 0009-0006-8955-3577
Observed ORCID: 0009-0006-8955-3577
OpenAlex ID: A5103091182
Activation Steering for Chain-of-Thought Compression
2026 · Seyedarmin Azizi, Erfan Baghaei Potraghloo, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · 21
PDF
PEANO-ViT: Power-Efficient Approximations of Non-Linearities in Vision Transformers
2024 · Mohammad Erfan Sadeghi, Arash Fayyazi, et al. · International Symposium on Low Power Electronics and Design (ISLPED) · 21
Power-SMC: Low-Latency Sequence-Level Power Sampling for Training-Free LLM Reasoning
2026 · Azizi, Seyedarmin, Potraghloo, Erfan Baghaei, et al. · arXiv (Cornell University) · 20
PDF
LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation
2024 · Seyedarmin Azizi, Souvik Kundu, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 16
PDF
Labels Override Definitions in Jev-Style Typed Decision Models
2026 · Azizi, Seyedarmin, Potraghloo, Erfan Baghaei, et al. · arXiv (Cornell University) · 9
PDF
VISTA: Vision-Language Inference for Training-Free Stock Time-Series Analysis
2025 · Khezresmaeilzadeh, Tina, Razmara, Parsa, et al. · arXiv (Cornell University) · 8
PDF
Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation
2025 · Erfan Baghaei Potraghloo, Seyedarmin Azizi, et al. · neural information processing systems · 7
PDF
Low-Precision Mixed-Computation Models for Inference on Edge
2024 · Seyedarmin Azizi, Mahdi Nazemi, et al. · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · 7
PDF
Sensitivity-Aware Mixed-Precision Quantization and Width Optimization of Deep Neural Networks Through Cluster-Based Tree-Structured Parzen Estimation
2023 · Azizi, Seyedarmin, Nazemi, Mahdi, et al. · arXiv (Cornell University) · 4
PDF
One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails
2026 · Azizi, Seyedarmin, Potraghloo, Erfan Baghaei, et al. · arXiv (Cornell University) · 3
PDF
CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits
2026 · Saadatinia, Mehrshad, Razmara, Parsa, et al. · arXiv (Cornell University) · 3
PDF
Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy
2025 · Seyedarmin Azizi, Mahdi Nazemi, et al. · Lecture notes in computer science · 3
PDF
The Sharp Directions Are Against You: Curvature Analysis of Activation Steering
2026 · Azizi, Seyedarmin, Fayyazi, Arya, et al. · arXiv (Cornell University) · 2
PDF
MORFI: Mutimodal Zero-Shot Reasoning for Financial Time-Series Inference
2025 · Tina Khezresmaeilzadeh, Parsa Razmara, et al. · IEEE International Conference on Computer Vision Workshops · 2
Efficient Noise Mitigation for Enhancing Inference Accuracy in DNNs on Mixed-Signal Accelerators
2024 · Azizi, Seyedarmin, Sadeghi, Mohammad Erfan, et al. · arXiv (Cornell University) · 2
PDF
Automated Optimization of Deep Neural Networks: Dynamic Bit-Width and Layer-Width Selection via Cluster-Based Parzen Estimation
2024 · Seyedarmin Azizi, Mahdi Nazemi, et al. · Design, Automation, and Test in Europe · 2
CrAFT: Compression-Aware Fine-Tuning for Efficient Visual Task Adaptation
2023 · Heo, Jung Hwan, Azizi, Seyedarmin, et al. · arXiv (Cornell University) · 2
PDF
Chopthin-Consensus Power Sampling: A Diversity-Preserving Approach to LLM Decoding
2026 · Ahmadi, Minoo, Azizi, Seyedarmin, et al. · arXiv (Cornell University) · 1
PDF
One Token Away from Collapse: The Fragility of Instruction-Tuned Helpfulness
2026 · Potraghloo, Erfan Baghaei, Azizi, Seyedarmin, et al. · arXiv (Cornell University) · 1
PDF
From Filters to VLMs: Benchmarking Defogging Methods Through Object Detection and Segmentation Performance
2026 · Ardalan Aryashad, Parsa Razmara, et al. · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · 1
PDF
SafeStart: Mitigating the Overlooked Safety Cost of Active Expert Reduction in MoE LLM Serving
2026 · Potraghloo, Erfan Baghaei, Shokoufa, Saeid, et al. · arXiv (Cornell University)
Reasoning for Generation, Generation for Reasoning: A Survey of Unified Multimodal Models
2026 · Tina Khezresmaeilzadeh, Seyedarmin Azizi, et al. · Preprints.org
C-GRPO: Conformal Group Relative Policy Optimization
2026 · Fayyazi, Arya, Azizi, Seyedarmin, et al. · arXiv (Cornell University)
When Pointing Becomes Profiling: Social Bias and Refusal in Text-Steerable Visual Encoders
2026 · Azizi, Seyedarmin, Razmara, Parsa, et al. · arXiv (Cornell University)
PDF
Keep the Lineages Alive: Diversity-Preserving SMC for Diffusion LLM Decoding
2026 · Ahmadi, Minoo, Azizi, Seyedarmin, et al. · arXiv (Cornell University)
PDF
Works count: 32
Citation count: 135
H-index: 7
I10-index: 4
Year
Topic
Type