Publications

* Equal Contribution

2026

  1. Preprint
    Flash-WAM: Modality-Aware Distillation for World Action Models
    Arman Akbari, Ci Zhang, Arash Akbari, Lin Zhao, Yixiao Chen, Weiwei Chen, Xuan Zhang, Geng Yuan, and Yanzhi Wang
    arXiv preprint arXiv:2606.05254, 2026
    PDF Website
  2. Preprint
    ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
    Arash Akbari, Arman Akbari, Masih Eskandar, Qitao Tan, Yixiao Chen, Jingwu Luo, Bertha Pangaribuan, Liyun Zhang, Jennifer Dy, Geng Yuan, Xue Lin, Gaowen Liu, Stratis Ioannidis, and Yanzhi Wang
    arXiv preprint arXiv:2605.24011, 2026
    PDF Website
  3. Preprint
    PhyGround: Benchmarking Physical Reasoning in Generative World Models
    Juyi Lin*, Arash Akbari*, Yumei He, Lin Zhao, Haichao Zhang, Arman Akbari, Xingchen Xu, Zoe Y. Lu, Enfu Nan, Hokin Deng, Edmund Yeh, Sarah Ostadabbas, Yun Fu, Jennifer Dy, Pu Zhao, and Yanzhi Wang
    arXiv preprint arXiv:2605.10806, 2026
    PDF Code Website
  4. GLSVLSI
    Cross-Platform Scaling of Vision-Language-Action Models from Edge to Cloud GPUs
    Amir Taherin, Juyi Lin, Arash Akbari, Arman Akbari, Pu Zhao, Weiwei Chen, David Kaeli, and Yanzhi Wang
    In ACM Great Lakes Symposium on VLSI (GLSVLSI), 2026
    PDF
  5. Preprint
    Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs
    Qinxin Tan, Xiao Song, Arash Akbari, Arman Akbari, Yanzhi Wang, Xinyu Zhai, Lichao Hong, Zhuolin Xiang, Jiahao Lu, and  others
    arXiv preprint arXiv:2605.24154, 2026
    PDF Code Demo
  6. Preprint
    PhyWorld: Physics-Faithful World Model for Video Generation
    Pu Zhao, Juyi Lin, Timothy Rupprecht, Arash Akbari, Changdi Yang, Ratul Chowdhury, Elahe Motamedi, and  others
    arXiv preprint arXiv:2605.19242, 2026
    PDF
  7. Preprint
    Human Cognition in Machines: A Unified Perspective of World Models
    Timothy Rupprecht, Pu Zhao, Amir Taherin, Arash Akbari, Arman Akbari, Yi He, Sean Duffy, Juyi Lin, and  others
    arXiv preprint arXiv:2604.16592, 2026
    PDF
  8. ICANN
    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, and Yanzhi Wang
    In International Conference on Artificial Neural Networks (ICANN), 2026
    PDF Code

2025

  1. Tech Report
    Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLA
    Pu Zhao, Arash Akbari, Xuan Shen, Zhenglun Kong, Yumei Shen, Sung-En Chang, Timothy Rupprecht, Lei Lu, Enfu Nan, and  others
    2025
    PDF
  2. ITSC
    Beyond Overall Accuracy: Pose- and Occlusion-driven Fairness Analysis in Pedestrian Detection for Autonomous Driving
    Mohammad Khoshkdahan, Arman Akbari, Arash Akbari, and Xuan Zhang
    In IEEE International Conference on Intelligent Transportation Systems (ITSC), 2025
    PDF
  3. ICLR
    7B Fully Open Source Moxin-LLM – From Pretraining to GRPO-based Reinforcement Learning Enhancement
    Pu Zhao, Xuan Shen, Zhenglun Kong, Yixin Shen, Sung-En Chang, Arash Akbari, Timothy Rupprecht, Lei Lu, Enfu Nan, Changdi Yang, and  others
    In SCI-FM @ ICLR Workshop, 2025
    PDF Code
  4. Preprint
    Rags to Riches: RAG-like Few-shot Learning for Large Language Model Role-playing
    Timothy Rupprecht, Enfu Nan, Arash Akbari, Arman Akbari, Lei Lu, P. Maan, Sean Duffy, Pu Zhao, and  others
    arXiv preprint arXiv:2509.12168, 2025
    PDF

2023

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