Hi, I’m Pratinav Seth! 👋

I currently work as a Research Scientist at AryaXAI Alignment Labs (Arya.ai, an Aurionpro Company) (July 2024 – Present), where I work at the intersection of Explainable AI (XAI), AI alignment, and AI safety for high-stakes, real-world applications. At AryaXAI, I focus on advancing explainable AI through model-agnostic approaches. I enhanced the DLBacktrace method and developed benchmarking frameworks for XAI evaluation. My work spans investigating alignment and optimization strategies across various architectures like CNNs, BERT, and LLaMA. I’m also actively developing foundation models for tabular data with applications in risk modeling and financial safety.

I completed my Bachelor’s (B.Tech) in Data Science from Manipal Institute of Technology, during which I had the privilege of working at Mila Quebec AI Institute (under Dr. David Rolnick), Bosch Research India (with Dr. Amit Kale and Mr. Koustav Mullick), and KLIV Lab at IIT Kharagpur (PI: Dr. Debdoot Sheet). I conducted much of my research alongside my peers at Mars Rover Manipal AI Research (alongside Dr. Ujjwal Verma), Research Society MIT, and under Dr. Abhilash K. Pai .

In 2023, I was honored to be selected as an AAAI Undergraduate Consortium Scholar, where I presented a proposal on Model Agnostic Uncertainty Aware Metrics.

I’m deeply passionate about building responsible AI systems that are aligned, safe, and transparent, with a particular interest in AI for Social Good and its applications in Medical Imagery and Remote Sensing.

I’m always eager to connect and exchange ideas on AI research, innovation, and shaping the future of responsible AI—let’s connect! 🚀

For a more detailed overview of my professional journey, projects, and contributions, feel free to take a look at my Resume.

🔥 News

Recent Publications & Acceptances

• 2025.07:  🎉 Interpretability-aware pruning for efficient medical image analysis accepted at MICCAI Workshop 2025!
• 2025.05:  🎉 SELF-PERCEPT: Mental Manipulation Detection accepted at ACL 2025!
• 2025.05:  🎉 Alberta Wells Dataset accepted at ICML 2025! (Really Grateful to the Team for their efforts and Prof. David Rolnick)!
• 2025.05:  🎉 Obscure to Observe: A Lesion-Aware MAE for Glaucoma Detection accepted at MIDL 2025 Short Paper Track!
• 2025.03:  🎉 DL-Backtrace accepted at IJCNN Conference 2025!

Academic Service & Reviewing

• 2025.08:  📝 Program Committee at AAAI 2026
• 2025.09:  📝 Reviewer at RegML Workshop, NeurIPS 2025
• 2025.05:  📝 Reviewer at Actionable Interpretability Workshop, ICML 2025
• 2025.04:  📝 Reviewer at ICCV 2025
• 2025.03:  📝 Reviewer at IJCNN 2025 & Advances in Financial AI Workshop, ICLR 2025
• 2025.02:  📝 Reviewer at CVPR 2025

📝 Publications

ICML 2025 / CCAI ICLR 2025

Alberta Wells Dataset: Pinpointing Oil and Gas Wells from Satellite Imagery

Pratinav Seth(#), Michelle Lin(#), Brefo Dwamena Yaw, Jade Boutot, Mary Kang, David Rolnick

Citations

ACL 2025 / NAACL SRW Workshop 2025

SELF-PERCEPT: Introspection Improves Large Language Models’ Detection of Multi-Person Mental Manipulation in Conversations

Danush Khanna, Pratinav Seth, Sidhaarth Sredharan Murali, Aditya Kumar Guru, Siddharth Shukla, Tanuj Tyagi, SANDEEP CHAURASIA, Kripabandhu Ghosh

Citations

IJCNN 2025

DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models

Vinay Kumar Sankarapu, Chintan Chitroda, Yashwardhan Rathore, Neeraj Kumar Singh, Pratinav Seth

Citations

MICCAI Workshop 2025

Interpretability-aware pruning for efficient medical image analysis

Nikita Malik, Pratinav Seth, Neeraj Kumar Singh, Chintan Chitroda, Vinay Kumar Sankarapu

Citations

MIDL 2025

Obscure to Observe: A Lesion-Aware MAE for Glaucoma Detection from Retinal Context

Siddhant Bharadwaj, Pratinav Seth, Chandra Sekhar Seelamantula

Citations

WACV Workshop 2024

Does the Fairness of Your Pre-Training Hold Up? Examining the Influence of Pre-Training Techniques on Skin Tone Bias in Skin Lesion Classification

Pratinav Seth, Abhilash K Pai

Citations

CVPR Workshop 2023

CoReFusion: Contrastive Regularized Fusion for Guided Thermal Super-Resolution

Aditya Kasliwal, Pratinav Seth, Sriya Rallabandi, Sanchit Singhal

Citations

AAAI Student Abstract 2023

LaMAR: Laplacian Pyramid for Multimodal Adaptive Super Resolution (Student Abstract)

Aditya Kasliwal, Aryan Kamani, Ishaan Gakhar, Pratinav Seth, Sriya Rallabandi

Citations

Pre-Print

LapGSR: Laplacian Reconstructive Network for Guided Thermal Super-Resolution

Aditya Kasliwal, Ishaan Gakhar, Aryan Kamani, Pratinav Seth, Ujjwal Verma

Citations

3rd Workshop on NLP for Positive Impact @ EMNLP 2024

AgriLLM: Harnessing transformers for farmer queries.

Krish Didwania (†), Pratinav Seth (†), Aditya Kasliwal, Amit Agarwal

Citations

• Performance Evaluation of Deep Segmentation Models for Contrails Detection, Akshat Bhandari, Sriya Rallabandi, Sanchit Singhal, Aditya Kasliwal, Pratinav Seth, Tackling Climate Change with Machine Learning Workshop at NeurIPS 2022. Citations

• Sailing Through Spectra: Unveiling the Potential of Multi-Spectral Information in Marine Debris Segmentation, Dyutit Mohanty, Aditya Kasliwal, Bharath Udupa, Pratinav Seth, The Second Tiny Papers Track at ICLR 2024. Citations

• ReFuSeg: Regularized Multi-Modal Fusion for Precise Brain Tumour Segmentation, Aditya Kasliwal, Sankarshanaa Sagaram, Laven Srivastava, Pratinav Seth, Adil Khan, 9th Edition of the Brain Lesion (BrainLes) workshop, MICCAI 2023. Citations

• UATTA-ENS: Uncertainty Aware Test Time Augmented Ensemble for PIRC Diabetic Retinopathy Detection, Pratinav Seth, Adil Khan, Ananya Gupta, Saurabh Kumar Mishra, Akshat Bhandhari, Medical Imaging meets NeurIPS Workshop, NeurIPS 2022. Citations

• UATTA-EB: Uncertainty-Aware Test-Time Augmented Ensemble of BERTs for Classifying Common Mental Illnesses on Social Media Posts, Pratinav Seth (†), Mihir Agarwal (†), 1st Tiny Paper Track at ICLR 2023. Citations

• Evaluating Predictive Uncertainty and Robustness to Distributional Shift Using Real World Data, Kumud Lakara (†), Akshat Bhandari (†), Pratinav Seth (†), Ujjwal Verma, Bayesian Deep Learning Workshop, NeurIPS 2021. Citations

• SSS at SemEval-2023 Task 10: Explainable Detection of Online Sexism using Majority Voted Fine-Tuned Transformers, Sriya Rallabandi, Sanchit Singhal, Pratinav Seth, Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), ACL 2023 Citations

• RSM-NLP at BLP-2023 Task 2: Bangla Sentiment Analysis using Weighted and Majority Voted Fine-Tuned Transformers,Pratinav Seth, Rashi Goel, Komal Mathur, Swetha Vemulapalli, Proceedings of the 1st Workshop on Bangla Language Processing (BLP 2023), EMNLP 2023 Citations

• HGP-NLP at Shared Task: Leveraging LoRA for Lay Summarization of Biomedical Research Articles using Seq2Seq Transformers,Hemang Malik,Gaurav Pradeep,Pratinav Seth, Accepted at BioNLP 2024 Workshop, ACL 2024. Citations

• Analyzing Effects of Fake Training Data on the Performance of Deep Learning Systems,Pratinav Seth (†), Akshat Bhandari (†), Kumud Lakara (†), Pre-Print Citations

• xai_evals: A Framework for Evaluating Post-Hoc Local Explanation Methods,Pratinav Seth, Yashwardhan Rathore, Neeraj Kumar Singh, Chintan Chitroda, Vinay Kumar Sankarapu, Technical Report Citations

• Bridging the gap in XAI-why reliable metrics matter for explainability and compliance,Pratinav Seth, Vinay Kumar Sankarapu, Pre-Print 2025 Citations

🎓 Academic Service

Conference Reviewing & Program Committee

• Main Conference Reviewer: CVPR 2025, ICCV 2025, IJCNN 2025, ECCV 2024, WACV 2026, AAAI 2026,
• Workshop Reviewer:
  • SyntheticData4ML Workshop (NeurIPS 2022, 2023)
  • Actionable Interpretability Workshop (ICML 2025)
  • Advances in Financial AI Workshop (ICLR 2025)
  • Frontiers in Probabilistic Inference (ICLR 2025)
  • Bayesian Decision-making and Uncertainty Workshop (NeurIPS 2024)
  • NLP for Positive Impact Workshop (EMNLP 2024)
  • FAIMI Workshop (MICCAI 2024)
  • Domain Adaptation and Representation Transfer Workshop (MICCAI 2023)
  • Topological, Algebraic, and Geometric P.R.A. Workshop (CVPR 2023)
  • RegML Workshop (NeurIPS 2025)

💻 Professional Experience

Research Positions

• 2024.07 - Present, Research Scientist at AryaXAI Alignment Labs, Remote / Mumbai, India
  • Explainability: Enhanced DLBacktrace method for model-agnostic explainability; co-developed benchmarking framework for XAI techniques
  • XAI-guided Optimization: Investigating alignment strategies across CNNs, BERT, LLaMA architectures for safer model behavior
  • Tabular Foundation Models: Developing foundation models for risk modeling, fraud detection, and financial safety
  • Leadership: Mentored 8+ research interns; led recruitment for Paris and India teams
  • Industry Engagement: R&D representative in client-facing engagements; presented at 5th MLOps Conference
• 2024.01 - 2024.06, Research Intern at Rolnick Lab, Mila Quebec AI Institute, Remote
  • Project: Computer vision and deep learning for geospatial applications targeting climate change
  • Focus: Detecting abandoned oil and gas wells from satellite imagery; created new geospatial dataset and benchmarked deep learning models
  • Mentor: Dr. David Rolnick (McGill University, Université de Montréal, Mila)
  • Outcome: Led to ICML 2025 publication on Alberta Wells Dataset
• 2023.06 - 2023.10, Computer Vision Research Intern at Robert Bosch Research and Technology Center India, Bangalore
  • Project: Vision-based generative AI for autonomous driving using Latent Diffusion Models
  • Focus: Generating additional data for difficult or misclassified samples to improve downstream task network optimization
  • Mentors: Mr. Koustav Mullick (CR/RDT-2), Dr. Amit Kale
• 2021.03 - 2024.01, Research Progression at Mars Rover Manipal
  • Advanced from Trainee to Senior Researcher and Mentor
  • Led AI research initiatives leading to multiple publications at NeurIPS, ACL, AAAI, CVPR, etc withprojects in Generative AI, Medical Image Analysis, and Climate Change.
  • Built a team of 10+ members and mentored them in their research.
• 2023.04 - 2023.12, Research Assistant under Dr. Abhilash K. Pai, Dept. of DSCA, MIT MAHE
  • Focused on medical image analysis and fairness in AI.
  • Worked on a study on effects of pretraining techniques on skin tone bias in skin lesion classification with support from MAHE Undergraduate Research Grant leading to a publication at Pre-Train Workshop at WACV 2024.

Research Collaborations

• 2023.12 - 2024.01, Research Collaboration with Dr. Amit Agarwal, Wells Fargo AI COE
• 2022.05 - 2023.12, Research Intern at KLIV Lab, IIT Kharagpur under Dr. Debdoot Sheet and mentored by Mr. Rakshith Satish. Worked on integrating domain knowledge in medical image analysis using Graph Convolutional Networks and Explainable AI for chest radiographs.
• 2022.10 - 2023.03, Research Collaboration with IIT Roorkee.

Leadership Roles

• 2022.09 - 2023.09, Co-President & AI Research Mentor, Research Society MIT Manipal
• 2022.11 - 2023.08, Co-founder & Head of AI, The Data Alchemists

Early Career Experience

• 2022.06 - 2022.09, Research Assistant, Dept. of DSCA, MIT MAHE under Dr. Vidya Rao & Dr. Poornima P.K. working on International Cyber Security Data Mining Competition leading to a position of 5th out of 134+ teams.
• 2022.03 - 2022.05, Machine Learning Intern, Eedge.ai
• 2022.01 - 2022.02, Data Science (NLP) Intern, CUREYA

🎖 Honors and Awards

• 2023.02 One of the 11 Undergraduates Selected as an AAAI Undergraduate Consortium Scholar 2023. Included a Travel Grant of $2000 to present at AAAI-23 at Washington DC, USA.
• 2023.01 Received MAHE Undergraduate Research Grant Worth 10K INR for Project : Explainable & Trustworthy Skin Lesion Classification under Dr. Abhilash K. Pai, Dept. of DSCA, Manipal Institute of Technology, MAHE.

📖 Education

• 2020.10 - 2024.07, Bachelors of Technology in Data Science & Engineering (B.Tech), Manipal Academy of Higher Education, Manipal, Karnataka, India.
  • CGPA: 8.31/10

🛠️ Technical Skills

Programming Languages & Frameworks

• Languages: Python, C++, SQL, Java, C, LaTeX
• ML/DL Frameworks: TensorFlow, Keras, PyTorch, Scikit-Learn, NetworkX
• Libraries: NumPy, Pandas, Seaborn, Matplotlib, OpenCV, PIL, HuggingFace, GeoPandas, Shapely, NLTK, SpaCy

Tools & Technologies

• Development: HTML, CSS, Git, Jupyter Notebook, Google Colab
• Platforms: Linux, Windows, HPC
• Specialized: Weka, Excel, LaTeX

Online Learning & Certifications

• Deep Learning Specialization - DeepLearning.ai
• 6th Summer School on AI - CVIT IIITH

💬 Invited Talks & Presentations

2024-2025

• AryaXAI Alignment Lab Webinars:
  • “Inside the Black Box: Interpreting LLMs with DL-Backtrace (DLB)”
  • “Beyond Explainability – Evaluating XAI Methods with Confidence Using xai evals”
  • “Interpretability Aware Pruning in Medical Imagery” (Paper Podcast)
• SSI Club AI Paper-Fest: “DL-Backtrace by AryaXAI” (October 2024)
• 2024.03, Introduction to Research, at ACM-W Manipal Chapter.
• 2024.02, Data Dialogue invited by The Data Alchemists, The Official Data Science Club of MIT Manipal. | [link]

2023

• 2023.03, Research as Undergrad, at ACM-W Manipal Chapter.