Prakash Chandra Chhipa
AI at RISE-Scalable Systems, Sweden | Research Scientist – Foundation Models, Computer Vision, & Multimodal AI
A35374, Luleå Universtiy of Technology, Sweden
Click here for updated CV!
Prakash is a Research Scientist and AI professional working at the intersection of foundation models, multimodal AI, and computer vision, with a strong focus on translating advanced research into real-world impact.
He recently completed his PhD in Machine Learning from Luleå University of Technology, Sweden, where his research focused on self-supervised learning, robustness, and multimodal systems. His work has been published at top-tier venues including ICLR, ECCV, and WACV, and he is a member of the European Laboratory for Learning and Intelligent Systems (ELLIS).
Prior to his PhD, Prakash spent over a decade in industrial R&D, building and deploying large-scale AI systems across domains. At Samsung Research (2012–2018), he developed and scaled audio-visual recognition and recommendation systems used by millions of devices, contributing to 11 international patents (including 5 granted) with citations from major technology companies. He later joined ARKRAY R&D (2018–2020), where he led the development of AI-driven medical imaging systems, resulting in the commercialization of the Aution Eye AI 4510 for urine sediment analysis.
Currently, Prakash works as an AI Expert at RISE, contributing to the MIMER AI Factory. His work focuses on enabling AI transformation across industry, public sector, and research by designing, adapting, and deploying foundation models and multimodal systems on high-performance computing infrastructure. He helps bridge the gap between cutting-edge research and scalable, production-ready AI solutions.
Prakash is particularly interested in advancing reliable, adaptive, and robust AI systems for real-world applications, while contributing to foundational research that shapes the next generation of multimodal and foundation models. Please check his updated CV here.
AskMeAnythingInCharts – Qwen2.5-VL-7B (LoRA) for Chart QA - get your question answered on charts and plots. [Opensourced and released on Oct 2025] - Open-source model on Hugging Face Try the live demo Training code
Möbius Perspective Distortion (MPD) augmentation for PyTorch & Albumentations [Opensourced and released on June 2025] - visit PyPI for pip install
Academic Research Highlights
Currently Posdoctoral Researcher funded by Wallenberg AI, Autonomous Systems, and Software Program (WASP). Recieved PhD in Machine Learning from Luleå tekniska universitet, Sweden. Research focused on robustness and domain-aware self-supervised representation learning. Published rsearch works in top conferences including ICLR, ECCV, WACV, ICIP and ICCV/ECCV workshops. Have been a reviewer at CVPR, NeurIPS, ICLR, and other conferences, industrial research with Swedish companies, and secured multiple grants.
Visiting Researcher at Center for Research in Computer Vision (CRCV), University of Central Florida, USA. Guided by host Prof. Mubarak Shah. Working on robust representation learning and also focusing Geo-localization domain. (Mar-June 2024)
Invited research talk at MBZUAI, UAE, EMBL-European Bioinformatics Institute at Cambridge, UK and MIRAI 2.0 Research and Innovation week at Kyushu University, Fukuoka, Japan. Accepted and participated in machine learning school at Cambridge University, UK and other venues.
Industrial R&D Work Tenure
Built a team and led computer vision research and development in the microscopic histopathology visual domain at Arkray R&D. Proudly contributed to achieving novel sediment recognition method on low-resolution histopathology for successful commercialization of Urinary Sediment Analyzer AUTION EYE AI-4510. Have been inventor for multiple patent applications (2018-2020).
Machine learning at AI & Data Intelligence Group (Now Advanced Research - Vision AI), Samsung R&D Institute for 6+ years (2012-2018) in different roles. Have been in forefornt for long-term R&D of successful large-scale products Samsung ACR and Samsung Ads focusing majorly on computer vision and reinforcement learning. Have been inventor for multiple granted patents/IP applications and awardee for Innovator of the Year-2017 for multiple IPs.
Worked with HCL Technologies for two years (2010-2012) and have been a contributor for enterprise-scale development of a platform for leading Telcom service provider T-Mobile.
news
| Oct 20, 2025 | 🧠 Released opensource A new LoRA-fine-tuned version of Qwen2.5-7B model ‘AskAnythingInCharts-Qwen2.5-7B’ on Hugging Face for robust and improved Q&A capability on charts and plots. Try demo at ‘HF Spaces’. |
|---|---|
| Jun 29, 2025 | 📚 Released opensource library ‘Möbius Perspective Distortion (MPD) augmentation for PyTorch & Albumentations’ for synthesizing perspective distortion based on work on Möbius transform in ECCV2024. |
| Apr 22, 2025 | 🎤 Gave invited research talk titled ‘Towards Robust Self-Supervised Representation Learning’ video presentation slides at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE. 🇦🇪 |
| Apr 08, 2025 | 🎓 Sucessfully defended PhD with thesis titled ‘Towards Robust and Domain-aware Self-supervised Representation Learning’). 🇸🇪 |
| Jan 22, 2025 | 🎉 Paper titled ‘ASTrA: Adversarial Self-supervised Training with Adaptive-Attacks’ accepted in ICLR 2025. 🎉 |
| Nov 02, 2024 | 🥇 Featured in Swedish Trans-Atlantic Researchers and Scholars Network (STARS) for recent work. 🇸🇪 🇺🇸 |
| Oct 29, 2024 | 🎓 Received DAAD AI-Net Fellow 2024 fellowship to visit and collaborate with host German research institute on Artificial Intelligence. 🇩🇪 |
| Sep 20, 2024 | 🎉 Paper titled ‘LCM: Log Conformal Maps for Robust Representation Learning to Mitigate Perspective Distortion’ accepted in ACCV 2024. 🎉 |
| Aug 15, 2024 | 🎉 Paper titled ‘Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts’ accepted in ECCV OOD-CV workshop 2024. 🎉 |
| Jul 03, 2024 | 🎉 Paper titled ‘Möbius Transform for Mitigating Perspective Distortions in Representation Learning’ accepted in ECCV 2024. 🎉 |
| Jun 20, 2024 | 📰 Visiting research experience at CRCV, University of Central Florida, USA featured in The Swedish Society for Automated Image Analysis (SSBA) ‘Magazine (June 2024 edition)’. 🇸🇪 |
| Mar 10, 2024 | ✈️ Started research visit at Center for Research in Computer Vision (‘CRCV’), University of Central Florida, hosted by Prof. Mubarak Shah. 🇺🇸 |
| Oct 08, 2023 | 🎉 Paper titled ‘Functional knowledge transfer with self-supervised representation learning’ accepted in ICIP 2023. 🎉 |
| Mar 17, 2023 | 🎓 Sucessfully defended Licentiate thesis titled ‘Self-supervised Representation Learning for Visual Domains Beyond Natural Scenes’. 🇸🇪 |
| Jan 03, 2023 | 🎉 Paper titled ‘Magnification Prior A Self-Supervised Method for Learning Representations on Breast Cancer Histopathological Image’ accepted in WACV 2023. 🎉 |
| Nov 24, 2022 | 🎤 Invited to present my research titled ‘Learning Self-supervised Representations on Histopathological Images - Why and How?’ at European Molecular Biology Lab European Bioinformatics Institute (EMBL-EBI), Cambridge, United Kingdom. 🇬🇧 |
| Nov 06, 2022 | 🎤 Invited to present my research titled ‘Self-supervised Representation Learning on Beyond the Natural Visual Concepts’ during MIRAI2.0 R&D Week at Kyushu University, Fukuoka, Japan. 🇯🇵 |
| Oct 23, 2022 | 🎉 Paper titled ‘Depth Contrast Self-Supervised Pretraining on 3DPM Images for Mining Material Classification’ accepted in ECCV Workshops 2022. 🎉 |
