Excited to share that our work "F^3OCUS - Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics" has been accepted to #CVPR2025. Paper link: arxiv.org/abs/2411.11912 #CVPR #VLM #PEFT #FL #VQA

Our approach boosts clip localization accuracy by 10–13% (mtIoU) while cutting tokens by 96% for lower compute. ⚡🔍 Check out our poster & swing by our session! 🙌💡 #healthcare #computervision #AAAI2025

Swing by our #AAAI2025 poster #826 today at noon to know more about video understanding and computationally efficient video clip localization in scenarios where detecting temporal boundaries is extremely challenging.

If you’re in Philadelphia 🦅 for #AAAI2025, stop by and see Pramit today! 🥳 He’ll be presenting our latest research 🚀💻 #FederatedLearning #HealthcareAI

I am currently in Tucson for #WACV2025! 🇺🇸🌵 Excited to present our latest research on #FederatedLearning for Brain MRI databases with different modalities and diseases tomorrow. If you’re around and up for a coffee or food, let’s connect, just reach out! 😄☕🌮

Ever wondered what it takes to train a foundation model for multi-modal brain MRIs? 🧠 I’ll be giving an oral talk today at #WACV2025! Catch me in Ballroom 1-5 during the 2 PM session to learn more. Also, I’ll be at Poster Session #2 with Poster #91, come say hi and let’s chat🥳

🚨 #CVPR2025 #Highlights from #Oxford #Noble #Group 𝗣𝗼𝘀𝘁𝗲𝗿 𝗦𝗲𝘀𝘀𝗶𝗼𝗻 𝟰, Saturday, #401, 4 PM! How would you 𝗳𝗶𝗻𝗲-𝘁𝘂𝗻𝗲 𝗙𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗠𝗼𝗱𝗲𝗹𝘀 with small datasets & limited compute? Our #CVPR2025 𝗛𝗶𝗴𝗵𝗹𝗶𝗴𝗵𝘁𝘀 paper looks at this challenge! 👇

Don’t miss Poster Session 4 (#401) tomorrow, 4 PM, at #CVPR2025! Pramit Saha will walk you through fine-tuning vision-language foundation models in resource-constrained federated learning. 😄 happy to be part of this highlights paper 📄 #VisionLanguage #FederatedLearning

🚀 Thrilled to announce our paper, “Self-supervised Normality Learning and Divergence Vector-guided Model Merging for Zero-shot Congenital Heart Disease Detection in Fetal Ultrasound Videos,” is accepted at #MICCAI2025! 🥳 (1/n)

🚀 Excited to announce our paper, “Self-supervised Normality Learning and Divergence Vector-guided Model Merging for Zero-shot Congenital Heart Disease Detection in Fetal Ultrasound Videos,” from the Noble Lab , has been accepted to #MICCAI2025!

🦭 At #NeurIPS2025 in San Diego this week (Dec 1–7), presenting my final PhD project! If you’re working on medical imaging, foundation models, multimodal learning, federated learning, or OOD detection, let’s meet! Happy to grab a coffee ☕️ or beer 🍺. DM me to connect! 🌴

Today I am presenting DIsoN: Decentralized Isolation Networks for OOD Detection in Medical Imaging at #NeurIPS2025! 🧹💨 📍 Poster #1700, Exhibit Hall C–E ⏰ 4:30–7:30 PM (coming up soon!) If you’re curious about decentralized OOD detection, come by and say hi! 👋 #AI #DL

This morning my girlfriend told me I was talking something about Transformers in my sleep last night 🤖💤 This is what a week of #NeurIPS2025 does to you 😂 #AI #MachineLearning