3 citations · 6 across the 19 of their papers we have counts for
20 papers
A Controlled Evaluation of Curvature Inspired Scalar Feature Scaling for Domain Generalization
Sunny Gupta, Amit Sethi
Domain-specific curvature is an appealing idea for domain generalization (DG), but curvature learning can denote substantially different computations. This paper evaluates one deli…
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…
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…
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…
UniVarFL: Uniformity and Variance Regularized Federated Learning for Heterogeneous Data
Sunny Gupta, Nikita Jangid, Amit Sethi
Federated Learning (FL) often suffers from severe performance degradation when faced with non-IID data, largely due to local classifier bias. Traditional remedies such as global mo…
FedAlign: Federated Domain Generalization with Cross-Client Feature Alignment
Sunny Gupta, Vinay Sutar, Varunav Singh +1
Federated Learning (FL) offers a decentralized paradigm for collaborative model training without direct data sharing, yet it poses unique challenges for Domain Generalization (DG),…
Evaluation Metric for Quality Control and Generative Models in Histopathology Images
Pranav Jeevan, Neeraj Nixon, Abhijeet Patil +1
Our study introduces ResNet-L2 (RL2), a novel metric for evaluating generative models and image quality in histopathology, addressing limitations of traditional metrics, such as Fr…
Sequential Compression Layers for Efficient Federated Learning in Foundational Models
Navyansh Mahla, Sunny Gupta, Amit Sethi
Federated Learning (FL) has gained popularity for fine-tuning large language models (LLMs) across multiple nodes, each with its own private data. While LoRA has been widely adopted…
FLD+: Data-efficient Evaluation Metric for Generative Models
Pranav Jeevan, Neeraj Nixon, Amit Sethi
We introduce a new metric to assess the quality of generated images that is more reliable, data-efficient, compute-efficient, and adaptable to new domains than the previous metrics…
WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency
Pranav Jeevan, Neeraj Nixon, Amit Sethi
Recent advancements in single image super-resolution have been predominantly driven by token mixers and transformer architectures. WaveMixSR utilized the WaveMix architecture, empl…
Normalizing Flow-Based Metric for Image Generation
Pranav Jeevan, Neeraj Nixon, Amit Sethi
We propose two new evaluation metrics to assess realness of generated images based on normalizing flows: a simpler and efficient flow-based likelihood distance (FLD) and a more exa…
FedStein: Enhancing Multi-Domain Federated Learning Through James-Stein Estimator
Sunny Gupta, Nikita Jangid, Amit Sethi
Federated Learning (FL) facilitates data privacy by enabling collaborative in-situ training across decentralized clients. Despite its inherent advantages, FL faces significant chal…
FLeNS: Federated Learning with Enhanced Nesterov-Newton Sketch
Sunny Gupta, Mohit Jindal, Pankhi Kashyap +2
Federated learning faces a critical challenge in balancing communication efficiency with rapid convergence, especially for second-order methods. While Newton-type algorithms achiev…
EDSNet: Efficient-DSNet for Video Summarization
Ashish Prasad, Pranav Jeevan, Amit Sethi
Current video summarization methods largely rely on transformer-based architectures, which, due to their quadratic complexity, require substantial computational resources. In this…
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…
Which Backbone to Use: A Resource-efficient Domain Specific Comparison for Computer Vision
Pranav Jeevan, Amit Sethi
In contemporary computer vision applications, particularly image classification, architectural backbones pre-trained on large datasets like ImageNet are commonly employed as featur…