Arman Akbari

I'm a first year PhD student in Computer Engineering at Northeastern University, co-advised by Prof. Yanzhi Wang and Prof. Xuan Zhang. My research interests focus on Efficient AI, specifically for LLMs, Multi-modal LLMs, and Diffusion Models. I received my B.Sc. in Computer Science from the University of Tehran.

Open to academic collaboration. Feel free to contact me if our research aligns.

Research

My research centers on Efficient AI. I develop methods to accelerate pre-training, fine-tuning, and inference of generative models. My work includes model compression, optimization for large language and vision models, and designing fast, robust architectures that reduce computational cost without sacrificing performance.

News

Selected Publications

Preprints

VOTE
VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting
Juyi Lin, Amir Taherin, Arash Akbari, Arman Akbari, Lei Lu, Guangyu Chen, Taskin Padir, Xiaomeng Yang, Weiwei Chen, Yiqian Li, Xue Lin, David Kaeli, Pu Zhao, Yanzhi Wang

We propose VOTE, an efficient and general framework for the optimization and acceleration of VLA models.

Published

CircuitSense
CircuitSense: A Hierarchical Circuit System Benchmark Bridging Visual Comprehension and Symbolic Reasoning in Engineering Design Process
Arman Akbari, Jian Gao, Yifei Zou, Mei Yang, Jinru Duan, Dmitrii Torbunov, Yanzhi Wang, Yihui Ren, Xuan Zhang

We present CircuitSense, a benchmark of 8,006+ problems evaluating circuit understanding across three tasks—Perception, Analysis, and Design—with emphasis on deriving symbolic equations from visual inputs. Additionally, we propose a hierarchical synthetic pipeline that generates schematics and block diagrams with guaranteed ground-truth equations.

Fairness Analysis
Beyond Overall Accuracy: Pose- and Occlusion-driven Fairness Analysis in Pedestrian Detection for Autonomous Driving
Mohammad Khoshkdahan, Arman Akbari, Arash Akbari, Xuan Zhang

In this work, we systematically investigate how variations in the pedestrian pose—including leg status, elbow status, and body orientation—as well as individual joint occlusions, affect detection performance.

Grasping Pose
A 2D Geometry Based Grasping Pose Generation Algorithm for a Two-Finger Robot Hand
Arash Akbari, Arman Akbari, Mehdi Tale Masouleh
ICEE 2023 (International Conference on Electrical Engineering)

In this paper, a geometry-based algorithm is presented which can find grasp poses based on the geometry of the unknown object and propose the ones which may lead to successful grasping.

Professional Services

  • Conference Reviewer
    • NeurIPS'25, ICCV'25