14 papers
Comparative Analysis of Low-Rank Adaptation in Large Language Models versus Dense Embedding Regression for Headline Click-Through Rate Prediction
Samarth Sirsat, Anirudha Shinde, Amit Sethi +1
Optimizing digital content headlines for click-through rate (CTR) is an important problem in online media and recommendation systems. While large language models (LLMs) have demons…
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…
Inverse Design of Realizable Metasurface based Absorbers using Improved Conditioning and Diversity Enhanced Progressively Growing GANs
Vineetha Joy, Mohammad Abdullah, Pramit Pal +3
Metasurfaces enable precise manipulation of electromagnetic waves for applications such as beam steering, sensing, and stealth technology. However, inverse design of metasurfaces w…
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…
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…
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…