activity
20242026
collaborators
Showing cs.CVShow all

15 papers · 1 filter

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

bi-modal textual prompt learning for vision-language models in remote sensing

Pankhi Kashyap, Mainak Singha, Biplab Banerjee

Prompt learning (PL) has emerged as an effective strategy to adapt vision-language models (VLMs), such as CLIP, for downstream tasks under limited supervision. While PL has demonst…