Saikat Dutta is a PhD scholar at IITB-Monash Research Academy, where he works with Dr. Biplab Banerjee and Dr. Hamid Rezatofighi. His research interests include vision-language models (VLMs) and foundational models and their applications in downstream tasks. Prior to his doctoral studies, he worked as a Data Scientist at LG Ad Solutions for two years. He completed his MS (by Research) in Computer Science and Engineering from IIT Madras, and obtained his BE in CSE from Jadavpur University.

Chaman Banolia is a researcher works at the intersection of machine learning, deep learning, and remote sensing, with a specialized focus on hyperspectral imaging. My work centers on developing intelligent systems that extract actionable insights from complex, high‑dimensional data—driving innovation in sensing, environmental analysis, and AI‑driven decision support.

I am a PhD student at the Indian Institute of Technology, Bombay, supervised by Prof. Biplab Banerjee, Prof. Subhasis Chaudhuri and Prof. Gemma Roig. I did my Master's from the Indian Institute of Technology Patna, working on AI for code.

My research focuses on making vision-language models strictly reliable and adaptable. I work at the intersection of domain generalization and test-time prompt tuning, building topological regularizers and uncertainty-aware pipelines that prioritize robustness over mere accuracy. My goal is to deploy generalizable, scalable AI into dynamic, unseen environments, particularly within geospatial and remote sensing domains. Research Focus: Reliable Test-Time Prompt Tuning | Domain Generalization | Vision-Language Models | Geospatial AI Always open to discussing robust visual prompting, model calibration, and potential collaborations.

Aniket Junghare is a PhD Researcher at the Indian Institute of Technology Bombay, pursuing an M.Tech–PhD program under the supervision of Dr. Biplab Banerjee in Artificial Intelligence for Remote Sensing. Prior to joining the lab, he worked as a Machine Learning Engineer after receiving his B.Tech from the National Institute of Technology, Trichy. His research focuses on foundation models for remote sensing, with an emphasis on self-supervised and multimodal representation learning for large-scale Earth observation data, aiming to capture spectral, spatial, and semantic information across heterogeneous sensing modalities. Through this work, he aims to develop scalable and generalizable models for large-scale Earth observation and geospatial understanding. Research Interests : Self-Supervised Representation Learning, Multimodal AI for Earth Observation, Computer Vision for Remote Sensing, Geospatial AI

Ankit Khivasara is currently pursuing his Ph.D. at Indian Institute of Technology Bombay, where his research focuses on deep learning–based change detection in remote sensing images. He also serves as a faculty member in the Department of Electronics and Telecommunication Engineering at K J Somaiya College of Engineering and has over 12 years of academic experience. He completed his M.Tech in Electrical Engineering from Indian Institute of Technology Roorkee in 2011.

I am a Scientist/Engineer-SE at the Space Applications Centre (SAC), ISRO, where I have been contributing since March 2017. My professional work focuses on Remote Sensing Data Processing for High-Resolution Satellites. Alongside my role at ISRO, I am pursuing a PhD at the Centre of Studies in Resources Engineering (CSRE), IIT Bombay, specializing in Computer Vision and Deep Learning. I hold an M.Sc. in Mathematics from IIT Kharagpur and a B.Sc. (Hons) in Mathematics from Barasat Government College (WBSU).

Exploring computer vision and deep learning

PhD student at CMInDS, IIT Bombay, under Prof. Biplab Banerjee. Research areas include vision-language models, compositional zero-shot learning, and domain generalization.

Exploring the depths of Artificial Intelligence.

I am a research enthusiast in the field of deep learning, working on generalisation multimodal/multisource data.

PhD candidate at IIT Bombay working at the intersection of computer vision and multimodal AI, with a core focus on advancing multimodal learning for remote sensing image analysis.

I work on core problems in Machine Learning, Computer Vision, and Generalizable Recognition Systems — Domain Generalization, Generalized Category Discovery, Representation Learning, and Fine-Grained Recognition.

B.Tech in Electrical Engineering. Worked as software engineer at Accenture for 2 years before joining for PhD.