activity
20242026
collaborators

12 papers

cs.AI2026

Amortizing Federated Adaptation: Hypernetwork Driven LoRA for Personalized Foundation Models

Sunny Gupta, Shambhavi Shanker, Amit Sethi

Federated fine-tuning of foundation models using Low-Rank Adaptation (LoRA) offers a communication efficient solution for distributed learning. However, existing federated LoRA met…

cs.CV2026

BiPrompt: Bilateral Prompt Optimization for Visual and Textual Debiasing in Vision-Language Models

Sunny Gupta, Shounak Das, Amit Sethi

Vision language foundation models such as CLIP exhibit impressive zero-shot generalization yet remain vulnerable to spurious correlations across visual and textual modalities. Exis…

cs.LG2026

FedHypeVAE: Federated Learning with Hypernetwork Generated Conditional VAEs for Differentially Private Embedding Sharing

Sunny Gupta, Amit Sethi

Federated data sharing promises utility without centralizing raw data, yet existing embedding-level generators struggle under non-IID client heterogeneity and provide limited forma…

cs.CV2025

CCVA-FL: Cross-Client Variations Adaptive Federated Learning for Medical Imaging

Sunny Gupta, Amit Sethi

Federated Learning (FL) offers a privacy-preserving approach to train models on decentralized data. Its potential in healthcare is significant, but challenges arise due to cross-cl…

cs.CV2025

Federated Cross-Modal Style-Aware Prompt Generation

Suraj Prasad, Navyansh Mahla, Sunny Gupta +1

Prompt learning has propelled vision-language models like CLIP to excel in diverse tasks, making them ideal for federated learning due to computational efficiency. However, convent…

cs.AI2025

FEDTAIL: Federated Long-Tailed Domain Generalization with Sharpness-Guided Gradient Matching

Sunny Gupta, Nikita Jangid, Shounak Das +1

Domain Generalization (DG) seeks to train models that perform reliably on unseen target domains without access to target data during training. While recent progress in smoothing th…