Open to opportunities

Chanda Grover

@chandagrover6

Message

PhD candidate in multimodal learning and diffusion models for vision-language tasks.

India

Message

What I'm looking for

I seek research-focused roles building multimodal, generative, and vision-language systems in collaborative, interdisciplinary teams with opportunities to publish and deploy impactful models.

I am a PhD candidate (thesis submitted, defense pending) in Computer Science at Ashoka University specializing in multimodal learning, diffusion models, and vision-language representations. I build models that align and generate across text, image, and audio for tasks such as zero-shot classification, semantic style transfer, and generative visual understanding.

I have designed multimodal fusion architectures using CLIP and transformer backbones, developed the ObjMST framework for object-based multimodal style transfer, and created text-to-image generation and retrieval pipelines leveraging diffusion models. I also built a PDF-QA system using LLMs (GPT + LangChain) and have published first-author work in top venues including CVPR (CVEU 2025), ICIP, and ICVGIP.

I bring interdisciplinary collaboration experience from industry and academia—working on property-conditioned generative models for small-molecule synthesis and mentoring students in ML, CV, and deep learning. I am driven to translate cutting-edge research into robust, controllable multimodal systems that address real-world problems.

Experience

Work history, roles, and key accomplishments

Research Scholar

Ashoka University

Aug 2019 - Dec 2025 (6 years 4 months)

Led development of multimodal learning and diffusion-model pipelines for zero-shot classification, text-to-image generation, and object-based multimodal style transfer; published five first-author papers and presented at CVPR and ICIP. Built PDF-QA system using GPT and LangChain to enable contextual retrieval and summarization.

Multimodal Learning Diffusion Models Vision Language Models PyTorch Transformers GPT Lang Chain

Research Assistant

Mphasis

Nov 2020 - Dec 2022 (2 years 1 month)

Designed property-conditioned generative models for small-molecule synthesis to reduce experimental costs and automated early-stage molecule screening using deep latent representations in collaboration with chemistry teams.

Generative Models Deep Learning Latent Representations Python PyTorch Computational Chemistry Model Evaluation

Research Fellow

Indian Institute of Technology Gandhinagar

Jul 2017 - Dec 2018 (1 year 5 months)

Mentored undergrad and master’s students in machine learning and computer vision, and delivered lab sessions on Python, PyTorch, and CNN architectures for image recognition.

Machine Learning Computer Vision PyTorch Python CNN Teaching Lab Instruction

System Engineer

Tata Consultancy Services

Sep 2014 - Jul 2017 (2 years 10 months)

Developed and administered SAS-based dashboards integrating Google Analytics for real-time performance monitoring of client systems (Lloyds Bank Group).

SAS Google Analytics Dashboarding SQL Shell Scripting ETL

Education

Degrees, certifications, and relevant coursework

Ashoka University

Doctorate, Computer Science

2019 -

Activities and societies: Research on multimodal fusion, diffusion-based generation, zero-shot classification, ObjMST; publications and conference presentations (CVPR, ICIP, ICVGIP).

PhD candidate in Computer Science (thesis submitted, defense pending) specializing in multimodal learning, diffusion models, and vision-language representations with publications in top-tier venues.

Indian Institute of Technology Gandhinagar

Postgraduate Diploma in Information Technology, Computer Science

2017 - 2018

Activities and societies: Guided students in ML/CV, delivered labs on Python, PyTorch, and CNNs.

Postgraduate Diploma in Information Technology with Computer Science focus, involving research assistance and teaching in machine learning and computer vision.