Ali Vosoughi

阿力

Ali Vosoughi is a PhD candidate at the University of Rochester, where he is studying in the Department of Electrical and Computer Engineering under the supervision of Professor Chenliang Xu and Professor Axel Wismueller. His research focuses on multimodality and complex reasoning, with the goal of enabling AI to assist humans in performing complex physical and imaginative tasks.

He obtained his Bachelor’s degree from the Electrical Engineering Department of Sharif University of Technology, Tehran, Iran, and Master degree from Electrical Engineering Department of Bogazici University, Istanbul, Turkey. He also holds a second Master degree in Electrical and Computer Engineering from University of Rochester, Rochester, New York, United States of America.


Write ✉️ to Ali Vosoughi: (ali.vosoughi) 🙂 (rochester.edu)


GitHub
LinkedIn
Scholar


News

03/2024: One paper accepted at NAACL 2024.
02/2024: One paper accepted at IEEE TMM.
01/2024: We published survey on Vid-LLMs.
12/2023: One paper accepted at ICASSP 2024.
11/2023: PTG team meetings held at MIT.
10/2023: A US Patent was filed in the area of audio and language.
08/2023: Two papers accepted at ICCV 2023, AV4D Workshop.
07/2023: Will be serving as ICCV 2023 reviewer.
07/2023: Three papers accepted at RSNA 2023.
07/2023: Will be serving as PC for AAAI 2023.
06/2023: Will be serving as EMNLP 2023 reviewer.
05/2023: Presenting research in Bosch Research USA Center for AI.
05/2023: Will be serving as Nature Communications reviewer.
04/2023: Started Internship at Bosch Cen. for AI.
04/2023: Serving as IEEE TMM reviewer.
04/2023: Two papers accepted at SPIE Emerging Topics in AI.
03/2023: Will be serving as ACL 2023 reviewer.
03/2023: We hosted a national DARPA PI meeting.
02/2023: Will be serving as CVPR 2023 reviewer.
08/2022: One paper accepted at Nature, digital medicine.
08/2022: Five papers accepted at RSNA 2022.
05/2022: Will be serving as EMNLP 2022 reviewer.
04/2022: Nominated for the Donald M. and Janet C. Barnard Fellowship.
02/2022: One paper accepted at ICASSP 2022.
02/2022: Will be serving as CVPR 2022 reviewer.
01/2022: Two papers accepted at SPIE Defense Sensing 2022.
12/2021: Will be serving as IEEE TMI reviewer.
10/2021: Three papers accepted at Medical Imaging 2022.
10/2021: One paper accepted at Computer-Aided Diagnosis 2022.
08/2021: Accepted as a PhD scholar in NSF program for AR/VR.
08/2021: One paper accepted at EUSIPCO 2021.
03/2021: Will be serving as ESANN 2021 reviewer.
02/2021: Received travel grant from GSA of U. of Rochester.
02/2021: One paper accepted at Nature.
11/2020: One paper accepted at Computer-Aided Diagnosis 2021.
11/2020: Three papers accepted at Medical Imaging 2021.
10/2020: One paper accepted at Proceedings of SPIE.
03/2020: Will be serving as ESANN 2020 reviewer.
01/2020: Will be TA for Detection and Estimation Theory.


Publications

Cross Modality Bias in Visual Question Answering: A Causal View with Possible Worlds VQA
Ali Vosoughi*, Shijian Deng*, Songyang Zhang, Yapeng Tian, Chenliang Xu
IEEE Transactions on Multimedia’24

[Paper][Code]

OSCaR: Object State Captioning and State Change Representation
Nguyen Nguyen, Jing Bi, Ali Vosoughi, Yapeng Tian, Pooyan Fazli, Chenliang Xu
NAACL’24
[Paper][Code]

Multimodal LLM that encompasses all multimodal tasks in one umbrella.
Under Double Blind Review
ACM MM’24
[Paper][Code][Website]

Video Understanding with Large Language Models: A Survey
Yunlong Tang, Jing Bi, Siting Xu, Luchuan Song, Susan Liang, Teng Wang, Daoan Zhang, Jie An, Jingyang Lin, Rongyi Zhu, Ali Vosoughi, Chao Huang, Zeliang Zhang, Feng Zheng, Jianguo Zhang, Ping Luo, Jiebo Luo, Chenliang Xu
[Paper][Code]

Learning Audio Concepts from Counterfactual Natural Language
Ali Vosoughi, Luca Bondi, Ho-Hsiang Wu, Chenliang Xu
ICASSP’24
[Paper][Code]

Separating Invisible Sounds Toward Universal Audiovisual Scene-Aware Sound Separation
Yiyang Su*, Ali Vosoughi*, Shijian Deng*, Yapeng Tian, Chenliang Xu
ICCV’23: ICCV AV4D Workshop
[Paper][Code]

MISAR: A Multimodal Instructional System with Augmented Reality
Jing Bi*, Nguyen Manh Nguyen*, Ali Vosoughi* Chenliang Xu
ICCV’23: ICCV AV4D Workshop
[Paper][Code][Video]

Detecting Landmarks in Anatomical Medical Images using Transformer-based Networks
Akhil Kasturi*, Ali Vosoughi*, Nathan Hadjiyski, Larry Stockmaster, William J Sehnert, Axel Wismueller
SPIE’23
[Paper]

Cross Modal Global Local Representation Learning from Radiology Reports and X-Ray Chest Images
Nathan Hadjiyski, Ali Vosoughi, Axel Wismueller
SPIE’23
[Paper]

Relation Discovery in Nonlinearly Related Large-scale Settings
Ali Vosoughi, Adora DSouza, Anas Abidin, Axel Wismueller
ICASSP’22
[Paper][Code]

Leveraging Pre-Images to Discover Nonlinear Relationships in Multivariate Environments
Ali Vosoughi, Axel Wismueller
EUSIPCO’21
[Paper]

Large-scale Nonlinear Granger Causality for Inferring Directed Dependence from Short Multivariate Time-series Data
Axel Wismueller, Adora Dsouza, Ali Vosoughi, Anas Abidin
Nature’21
[Paper][Code]


Personal Gallery

Ali Vosoughi
Ali Vosoughi

Go to the page: