Federated Foundation Models
Advancing privacy-preserving adaptation of large Vision–Language Models (VLMs) and Large Language Models (LLMs) through parameter-efficient federated optimization for multimodal foundation learning.
About
I am a doctoral researcher at the Indian Institute of Technology Bombay, working under the supervision of Prof. Amit Sethi in the MedaL Lab. My research lies at the intersection of artificial intelligence and healthcare, bridging human expertise and machine intelligence in federated settings to enhance personalization, fairness, and reliability of clinical decision support.
I bring deep expertise in machine learning, federated learning, deep learning, and computer vision, with publications and reviews at premier venues such as CVPR, AAAI, NeurIPS, ICLR, and ICML. At IIT Bombay, I also serve as System Administrator for the MedaL Lab, managing NVIDIA DGX systems and high-performance GPU clusters that power large-scale digital-health research.
Current Focus
Multi-Agent Federated Learning
Investigating collaborative intelligence where multiple autonomous agents jointly optimize models under decentralized, privacy-preserving environments.
Federated Domain Generalization
Developing federated algorithms that enable robust cross-domain generalization without centralized data sharing.
Federated Long-Tailed Learning
Designing federated frameworks that balance representation learning under severe label imbalance and non-IID client distributions.
Trustworthy Federated Systems
Designing privacy-preserving training with differential privacy and secure aggregation.
Publications
-
FedNeuro: Multi-Site fMRI Analysis Using Hypernetwork Personalized and Privacy Enhanced Federated Learning
, Shambhavi Shanker, Amit Sethi · Accepted for presentation at the AAAI 2026 Bridge Program: AI for Medicine and Healthcare (AIMedHealth), and published in the Proceedings of Machine Learning Research (PMLR), Singapore.
-
FedHypeVAE: Federated Learning with Hypernetwork Generated Conditional VAEs for Differentially Private Embedding Sharing
, Nikita Jangid, Amit Sethi · Accepted for presentation at the AAAI 2026 Bridge Program: AI for Medicine and Healthcare (AIMedHealth), and published in the Proceedings of Machine Learning Research (PMLR), Singapore.
-
FedVR: Variance Regularized Hypernetwork for Federated Domain Generalization
, Shambhavi Shanker, Amit Sethi · Oral presentation at the AAAI 2026 1st Workshop on Federated Learning for Critical Applications (FLCA @ AAAI 2026), Singapore.
-
BiPrompt: Bilateral Prompt Optimization for Visual and Textual Debiasing in Vision Language Models
, Shounak Das, Amit Sethi · Accepted for presentation at the AAAI 2026 Workshop on AI for Robust Foundation Models (AIR-FM), Singapore.
-
UniVarFL: Uniformity and Variance Regularized Federated Learning for Heterogeneous Data
, Nikita Jangid, Amit Sethi · Accepted as a Student Abstract and Poster at AAAI 2026, Singapore.
-
Federated Cross-Modal Style-Aware Prompt Generation
, Suraj Prasad, Amit Sethi · Accepted as a Student Abstract and Poster at AAAI 2026, Singapore.
-
FEDTAIL: Federated Long-Tailed Domain Generalization with Sharpness-Guided Gradient Matching
, Shounak Das, Nikita Jangid, Amit Sethi · Oral presentation at the ICML 2025 Workshop on Collaborative and Federated Agentic Workflows (CFAgentic @ ICML'25), Vancouver, Canada.
-
FedAlign: Federated Domain Generalization with Cross-Client Feature Alignment
, Vinay Sutar, Varunav Singh, Amit Sethi · Oral presentation at the 4th Workshop on Federated Learning for Computer Vision in conjunction with CVPR'25 (FedVision-2025), Nashville, USA.
-
FedStein: Enhancing Multi-Domain Federated Learning Through James-Stein Estimator
, Nikita Jangid, Amit Sethi · Accepted for presentation at the AAAI Bridge Program 2025: AI for Medicine and Healthcare (AIMedHealth), to appear in PMLR, Philadelphia, USA.
-
FLeNS: Federated Learning with Enhanced Nesterov-Newton Sketch
, Pankhi Kashyap, Pranav Jeevan, Amit Sethi · Oral presentation at IEEE BigData 2024, Washington, DC, USA.
-
FedStein: Enhancing Multi-Domain Federated Learning Through James-Stein Estimator
, Amit Sethi · Oral presentation at the International Workshop on Federated Foundation Models (FL@FM) at NeurIPS 2024, Vancouver, Canada.
-
Sequential Compression Layers for Efficient Federated Learning in Foundational Models
Navyansh Mahla, , Amit Sethi · Accepted at the Open Science for Foundation Models (SCI-FM) Workshop, ICLR 2025, Vienna, Austria.
-
Taming the Tail: Leveraging Asymmetric Loss and Padé Approximation to Overcome Medical Image Long-Tailed Class Imbalance
Pankhi Kashyap, Pavni Tandon, , Abhishek Tiwari, Ritwik Kulkarni, Kshitij Sharad Jadhav · The 35th British Machine Vision Conference (BMVC 2024), Glasgow, UK.
Experience
System Administrator · IIT Bombay
Managing NVIDIA DGX systems, GPU clusters, and high-performance Linux servers to support large-scale digital health research.
R&D Intern · Samsung Research India
Developed decentralized model optimization techniques and privacy-safe AI for edge devices.
Research Associate · IIM Ahmedabad
Applied machine learning and data analytics to behavioral and decision intelligence problems.
Project Research Assistant · IIT Guwahati
Contributed to speech-driven medical diagnostics and multimodal AI models.
Education
Indian Institute of Technology Bombay
Developing and unifying federated learning methodologies for healthcare, emphasizing privacy-preserving models that enable interoperability across siloed medical data.
Maulana Azad National Institute of Technology (MANIT), Bhopal
Completed thesis “Identification of COVID-19 Disease Using Deep Learning Methods,” leveraging transfer learning with CNNs (ResNet, AlexNet, VGG16, Inception, DenseNet) to advance chest X-ray diagnostics.
Noida Institute of Engineering & Technology (NIET)
Built foundations in signal processing, control systems, and embedded computing that underpin current work in distributed and trustworthy AI.
Technical Skills
Python
PyTorch
TensorFlow
JAX
CUDA
NumPy & SciPy
LaTeX
Git
Linux