
Dr Arpit Garg
Research Fellow
Australian Institute for Machine Learning - Projects
Faculty of Sciences, Engineering and Technology
Eligible to supervise Masters and PhD (as Co-Supervisor) - email supervisor to discuss availability.
- My Research
- Career
- Publications
- Grants and Funding
- Teaching
- Supervision
- Professional Activities
- Contact
My research focuses on developing robust and responsible AI systems that can operate reliably in real-world environments with imperfect data. I specialize in instance-dependent noisy label learning, where I've pioneered novel graphical model approaches and adaptive estimation techniques that significantly improve model performance when training labels are corrupted or unreliable. Through my work at TikTok, I advanced multimodal large language models (MLLMs) for Trust & Safety applications, achieving substantial AUC improvements by integrating diverse vision backbones with state-of-the-art language models.
Currently, as a Grant-Funded Research Fellow at the Responsible AI Research Centre, I'm developing privacy-preserving machine learning frameworks for Australian data sovereignty and AI safety protocols for critical infrastructure. My research bridges theoretical advances with practical applications, from contributing ML innovations to major film productions (Mad Max: Furiosa, Wolverine & Deadpool) to architecting scalable AI systems with multi-million dollar revenue impact. I maintain active collaborations with leading international institutions and contribute regularly to top-tier conferences including ECCV, WACV, and ICCV.
-
Education
Date Institution name Country Title 2021 - 2025 University of Adelaide Australia PhD 2019 - 2021 University of Adelaide Australia Master of Data Science 2015 - 2019 Rajasthan Technical University India Bachelors of Technology in Computer Science
-
Journals
Year Citation - Verma, M. A. K. (2017). BLOCKCHAIN: AN ANALYSIS ON NEXT-GENERATION INTERNET. International Journal of Advanced Research in Computer Science, 8(8), 429-432.
-
Conference Papers
Year Citation 2025 Garg, A., Nguyen, C., Felix, R., Do, T. -T., & Carneiro, G. (2025). Instance-Dependent Noisy-Label Learning with Graphical Model Based Noise-Rate Estimation. In Lecture Notes in computer science Vol. 15062 LNCS (pp. 372-389). Milan, Italy: Springer Nature Switzerland.
2023 Garg, A., Nguyen, C., Felix, R., Do, T. -T., & Carneiro, G. (2023). Instance-Dependent Noisy Label Learning via Graphical Modelling. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023) (pp. 2287-2297). Online: IEEE.
Scopus29 WoS272021 Shah, P., Garg, A., & Gajjar, V. (2021). PeR-ViS: Person Retrieval in Video Surveillance using Semantic Description. In 2021 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW) (pp. 41-50). Virtual, Waikola: IEEE.
Scopus12 WoS4
My research on Noisy label was supported by prestigious international funding including the Australian Research Council grants DP180103232 and FT190100525, which fund my collaborative work on robust machine learning and computer vision applications. Additionally, I'm supported by the UK's Engineering and Physical Sciences Research Council (EPSRC) grant EP/Y018036/1, enabling cross-institutional research with the University of Oxford and University of Surrey.
This comprehensive funding support has enabled me to focus on high-impact research while collaborating with leading institutions across Australia, the UK, and internationally, positioning my work at the forefront of responsible AI development.
Lecturer for COMP SCI 7306 - Mining Big Data (Tri 1, 2022)
As a Research Fellow at the Australian Institute for Machine Learning, I actively mentor next-generation Australian AI researchers, providing guidance on responsible AI development and advanced machine learning techniques. My teaching philosophy emphasizes hands-on learning through real-world applications, drawing from my diverse industry experience at TikTok, Rising Sun Pictures, and defense research organizations.
I contribute to the academic community by serving as a reviewer for premier machine learning conferences including ICCV, WACV, ECCV, and ICLR, helping maintain high standards in AI research publication. My mentoring extends beyond formal academic settings, as I've guided team members across cross-functional industry collaborations and contributed to open-source projects that have received over 140,000 GitHub visits, demonstrating my commitment to knowledge sharing and community education in the AI field.
-
Other Supervision Activities
Date Role Research Topic Location Program Supervision Type Student Load Student Name 2025 - 2023 Principal Supervisor Live AI Art Gallery Australian Institute for Machine Learning Bachelor of IT Other Full Time Abhijith Sreekumar 2025 - ongoing Principal Supervisor Fine-tuning Spatial Language Models for Food Quantity Estimation from Images University of Adelaide Master Of Artificial Intelligence and Machine Learning Master - Varun Chahar 2025 - ongoing Principal Supervisor Fine-tuning Spatial Language Models for Food Quantity Estimation from Images University of Adelaide Master Of Artificial Intelligence and Machine Learning Master - Sreehari Suraj 2025 - ongoing Principal Supervisor Fine-tuning Spatial Language Models for Food Quantity Estimation from Images University of Adelaide Master Of Artificial Intelligence and Machine Learning Master - Sweedal Jacintha Dsouza 2023 - 2024 Principal Supervisor Live AI ART Gallery Australian Institute for Machine Learning Master of Data Science Master Full Time Divye Maggo
-
Committee Memberships
Date Role Committee Institution Country 2025 - 2025 Co-Chair Digital Image Computing: Techniques and Applications (DICTA 2025) Australian Institute for Machine Learning Australia -
Memberships
Date Role Membership Country 2022 - ongoing Member Australian Computer Society Australia 2021 - ongoing Member Association for Computing Machinery United States 2021 - ongoing Member Institution of Engineers India
Connect With Me
External Profiles