15 papers
DistMoE: Private-data Rehearsal-free Routing in Mixture-of-Experts for Distributed Instruction Tuning
Mainak Singha, Niccolò Biondi, Elisa Ricci +1
Multimodal Large Language Models (MLLMs) have shown strong multimodal instruction-following ability, but adapting them to diverse visual-language domains typically assumes centrali…
CLIPoint3D: Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptation
Mainak Singha, Sarthak Mehrotra, Paolo Casari +3
Recent vision-language models (VLMs) such as CLIP demonstrate impressive cross-modal reasoning, extending beyond images to 3D perception. Yet, these models remain fragile under dom…
BioVLM: Routing Prompts, Not Parameters, for Cross-Modality Generalization in Biomedical VLMs
Mainak Singha, Tanisha Gupta, Ankit Jha +3
Pretrained biomedical vision-language models (VLMs) such as BioMedCLIP perform well on average but often degrade on challenging modalities where inter-class margins are small and a…
GeoMeld: Toward Semantically Grounded Foundation Models for Remote Sensing
Maram Hasan, Md Aminur Hossain, Savitra Roy +6
Effective foundation modeling in remote sensing requires spatially aligned heterogeneous modalities coupled with semantically grounded supervision, yet such resources remain limite…
How (Mis)calibrated is Your Federated CLIP and What To Do About It?
Mainak Singha, Masih Aminbeidokhti, Paolo Casari +3
While vision-language models like CLIP have been extensively studied, their calibration, crucial for reliable predictions, has received limited attention. Although a few prior work…
The Need for Ultra High Resolution X-ray Imaging
Kimberly A. Weaver, Jenna M. Cann, Ryan Pfeifle +20
This paper discusses the broad science case for obtaining milliarcsecond to microarcsecond astronomical imaging resolution in the soft to medium-energy X-ray band (~0.5 to ~8 keV).…