Organizing Committee

Meet the Organizers

Dr. Deepak K. Gupta is currently an Adjunct Professor at IIT ISM Dhanbad, where he leads the Transmute AI Lab (Texmin Hub). He is also a Lead Data Scientist at AIQ in UAE. Earlier, he was an associate professor at UiT Tromso in Norway. He is working on building novel methods to make the deep learning processes compute time efficient as well as memory efficient (example works at ICLR and CVPR include ChipNet, RotSiam and MetaDOCK. 

Webpage: https://www.linkedin.com/in/deepak-gupta-05b48828/

Dr. Zhiqiang Shen is currently an Assistant Professor at MBZUAI. He was a postdoc at Carnegie Mellon University and a joint-training PhD student at Fudan University and University of Illinois at Urbana-Champaign. His research interests span machine learning, efficient deep learning, computer vision, knowledge distillation, etc. He has published about 40 papers in top-tier machine learning and vision conferences, including ICLR, ICML, CVPR, ICCV, ECCV, etc. He was the co-organizer of workshop ``Hardware-friendly and lightweight deep learning'' in PRCV 2021 conference. 

Webpage: https://zhiqiangshen.com/

Dr. Dilip Prasad is an associate professor at UiT The Arctic University of Norway and a visiting professor at National University of Singapore since 2023. He has published 100+ internationally peer-reviewed research articles (in CVPR, ECCV, TIP, etc.) and patents. He is author of the book Interpretability in Deep Learning, Springer, 2023. He was program chair of CVIP2017 and co-organizer of ICONIP 2022 workshop "Deep Learning and Security Techniques for Secure Video Processing". His research interests include efficient image processing, pattern recognition and artificial intelligence. 

Webpage: https://en.uit.no/ansatte/person?p_document_id=615677

Sadaf Gulshad is a Computer Vision and Machine Learning Researcher at Multix lab, University of Amsterdam where she focuses on understanding decisions of black box neural networks for videos. Earlier, she did her Ph.D. at Bosch Deltalab, where her research focused on robustifying and explaining the decisions of visual classifiers. She believes that it is important to make the AI systems robust as well as interpretable before deploying them into the real world.

Webpage: https://sites.google.com/view/sadafgulshad/home

Dr. Devanshu Arya is currently a research scientist at Serket Tech working on real-time behavior monitoring of livestock in indoor farming environment. He focuses on developing efficient computer vision models for estimating the pose and actions of livestock animals and deploying it on edge devices such as NVIDIA Jetsons in animal farms. He has received his Ph.D. from University of Amsterdam where his thesis was on developing hypergraph-based techniques to learn relations in dynamically evolving real-world dataset which contains heterogeneous information from multiple modalities. 

Webpage: https://devanshuarya.github.io/

Dr. Amirhossein Habibian is a senior staff engineering manager at Qualcomm AI Research in Amsterdam. He leads a team developing efficient video processing solutions for both low- and high-level video perception that have been published in top-tier vision conferences. Amirhossein received his Ph.D. from the University of Amsterdam in 2016 on video representation learning from vision and language. 

Webpage: https://habibian.github.io/

Dr. Amir Ghodrati is a staff engineering manager at Qualcomm AI Research in Amsterdam. Amir received his Ph.D. from KU Leuven in Belgium in 2016. After that, He was a postdoctoral fellow at the University of Amsterdam for two years. His research interests include video understanding and efficient deep learning. 

Webpage: https://aghodrati.github.io/

Dr. Babak Ehteshami Bejnordi is a Research Scientist at Qualcomm AI Research in the Netherlands, leading a research team focusing on conditional computation for efficient deep learning. His research interests are in Conditional Computation, Efficient Deep Learning for Computer Vision, Multi-Task Learning, and Continual Learning. Babak obtained his Ph.D. in machine learning for breast cancer diagnosis from Radboud University in the Netherlands. Before joining Qualcomm he was a visiting researcher at Harvard University, BeckLab, and a member of the Broad Institute of MIT and Harvard. He has been the organizer of the Qualcomm Innovation Fellowship Program in Europe since 2019.

Webpage: http://babakint.com/

Dr. Zhuang Liu (FAIR, Meta): He is currently a Research Scientist at FAIR, Meta. He received his PhD degree from EECS, UC Berkeley. He worked as a visiting researcher or an intern at Cornell University, Intel Labs and Adobe Research. His research focuses on deep learning methods/architectures for visual recognition and representation learning. He is particularly interested in developing simple methods and studying baseline methods. His work on DenseNet received CVPR Best Paper Award in 2017. 

Webpage: https://liuzhuang13.github.io/

Dr. Jiahui Yu is currently a Staff Research Scientist and Manager at Google Brain. He received his PhD at University of Illinois at Urbana-Champaign in 2020, and Bachelor with distinction at School of the Gifted Young in Computer Science, University of Science and Technology of China in 2016. His interest is in sequence modeling (language, speech, video, financial data), machine perception (vision), generative models (GANs), high performance computing and efficient deep learning. He has published "Slimmable Neural Networks'', "Universally Slimmable Networks and Improved Training Techniques'', "AutoSlim: Towards One-Shot Architecture Search for Channel Numbers'' and "BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models''. 

Webpage:

Arnav Chavan is currently a research assistant at MBZUAI working on designing efficient transformers. In the past, he has worked towards making deep learning efficient and has published on related topics in CVPR and ICLR. Some of his recent work include vision transformer slimming, ChipNet, and MetaDOCK. He is also the co-founder of Nyun AI an early stage startup focused on compressing deep learning frameworks. 

Webpage:

Rishabh Tiwari is a Pre-Doctoral Researcher at Google Research, India. He completed his bachelors in Applied Physics from IIT Dhanbad. He is currently working on foundational machine learning, covering topics like simplicity bias, continual learning, pruning, etc. He has published his works at top conferences like ICLR, AAAI, CVPR that includes Chipnet, ICBM, GCR.

Webpage: https://www.rishabhtiwari.org/

Dr. Samir Malakar is currently a postdoc fellow at the Bio-AI Lab, Dept. of Comp. Sc., UiT The Arctic University of Norway, and he is currently working on developing novel deep learning methods to handle very large images from the domains of microscopy and nanoscopy.

Webpage: