Farshid Nooshi

I am an M.Sc. student in Complexity Science and Engineering at The University of Tokyo, where I am fortunate to be advised by Prof. Masashi Sugiyama in the Sugiyama–Yokoya–Ishida Laboratory. I received my B.Sc. in Computer Engineering from Amirkabir University of Technology.

Google Scholar / GitHub

Research

My research interests lie in reliable machine learning and reinforcement learning. In particular, I am interested in sequential decision-making under distribution shift and imperfect feedback, robust policy adaptation, and multi-agent learning. More recently, I have also been exploring robust watermarking and reliability for diffusion language models.

News

October 2026: Our DenMark paper has been accepted to the NeurIPS 2026 DiffuLM Workshop.
October 2026: I started my M.Sc. in Complexity Science and Engineering at The University of Tokyo.
August 2026: Our paper HAGAS was accepted to ACM SIGSPATIAL 2026.
April 2026: I joined The University of Tokyo as a research student.

Preprints
DenMark: Robust Semantic Watermarking for Diffusion Language Models Tianhao Ma, Weihao Xuan, Dong-Dong Wu, Farshid Nooshi, Takashi Ishida, Gang Niu, Naoto Yokoya, Masashi Sugiyama arXiv preprint, 2026 Accepted at the NeurIPS 2026 DiffuLM Workshop. Paper / Code

Selected Publications
Hierarchically-Adaptive Global-Local Grouping for Multi-Agent Reinforcement Learning in Urban Mobility Resource Rebalancing Farshid Nooshi, Suining He ACM SIGSPATIAL 2026, Accepted Project Related workshop paper: UrbComp 2025
CLBSR: A Deep Curriculum Learning-based Blind Image Super Resolution Network using Geometrical Prior Alireza Esmaeilzehi, Amir Mohammad Babaei, Farshid Nooshi, Hossein Zaredar, M. Omair Ahmad Image and Vision Computing, Volume 154, February 2025 Paper
DHBSR: A Deep Hybrid Representation-based Network for Blind Image Super Resolution Alireza Esmaeilzehi, Farshid Nooshi, Hossein Zaredar, M. Omair Ahmad Computer Vision and Image Understanding, Volume 246, September 2024 Paper
See all publications on Google Scholar →

Education

The University of Tokyo
Graduate School of Frontier Sciences
M.Sc. in Complexity Science and Engineering, Oct. 2026 – Present

Amirkabir University of Technology (Tehran Polytechnic)
B.Sc. in Computer Engineering, 2019 – January 2024
GPA: 18.74/20
Undergraduate thesis: Image-to-Image Translation using Deep Generative Models and StyleGAN for Enhanced Visual Quality and Realism

Awards & Honors

MEXT Scholarship, Japanese Government (Monbukagakusho), 2026.
1st place, Amirkabir University of Technology ICPC Contest, 2021.
14th place, ICPC Asia Tehran Regional Contest, 2021.
Ranked among the top 0.1% in Iran's Nationwide University Entrance Examination, 2019.
Direct admission to the M.Sc. program at Amirkabir University of Technology based on academic excellence, 2023.

Academic Service

Reviewer, The ACM Web Conference (WWW), 2026.
Reviewer, ACM SIGSPATIAL, 2026.