activity
20242026
most citedFedPIA -- Permuting and Integrating Adapters leveraging Wasserstein Barycenters for Finetuning Foundation Models in Multi-Modal Federated Learning

1 citations · 1 across the 5 of their papers we have counts for

collaborators

12 papers

cs.AI2026

Coherent Hierarchical Multi-Label Learning to Defer for Medical Imaging

Joshua Strong, Pramit Saha, Emma Sun +2

Learning to Defer (L2D) enables a model to predict autonomously or defer to an expert, but prior work largely assumes flat label spaces. We study the first L2D setting with hierarc…

cs.CV2026

Experience-Guided Self-Adaptive Cascaded Agents for Breast Cancer Screening and Diagnosis with Reduced Biopsy Referrals

Pramit Saha, Mohammad Alsharid, Joshua Strong +1

We propose an experience-guided cascaded multi-agent framework for Breast Ultrasound Screening and Diagnosis, called BUSD-Agent, that aims to reduce diagnostic escalation and unnec…

cs.LG2026

Picking the Right Specialist: Attentive Neural Process-based Selection of Task-Specialized Models as Tools for Agentic Healthcare Systems

Pramit Saha, Joshua Strong, Mohammad Alsharid +2

Task-specialized models form the backbone of agentic healthcare systems, enabling the agents to answer clinical queries across tasks such as disease diagnosis, localization, and re…

cs.CL2026

Clustering-driven Memory Compression for On-device Large Language Models

Ondrej Bohdal, Pramit Saha, Umberto Michieli +2

Large language models (LLMs) often rely on user-specific memories distilled from past interactions to enable personalized generation. A common practice is to concatenate these memo…

cs.LG2025

FedAgentBench: Towards Automating Real-world Federated Medical Image Analysis with Server-Client LLM Agents

Pramit Saha, Joshua Strong, Divyanshu Mishra +2

Federated learning (FL) allows collaborative model training across healthcare sites without sharing sensitive patient data. However, real-world FL deployment is often hindered by c…

cs.CV2025

Neural Collapse-Inspired Multi-Label Federated Learning under Label-Distribution Skew

Can Peng, Yuyuan Liu, Yingyu Yang +3

Federated Learning (FL) enables collaborative model training across distributed clients while preserving data privacy, but remains challenging when client data are highly heterogen…