.png&w=256&q=75)
Dr Deepali Bongulwar@deepalibongulwar42626
1
Events attended
1
Submissions made
India
1 year of experience
About me
Dr. Deepali M. Bongulwar is an AI researcher, educator, and Generative AI practitioner with over 15 years of combined academic and industry experience, including 13+ years in higher education and 2 years in research. She specialises in Machine Learning, Deep Learning, Computer Vision, Natural Language Processing, and Generative AI. Her recent work focuses on Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents, multimodal AI, and enterprise AI applications. She has built intelligent AI systems using open-source models, vector databases, and modern AI frameworks, with a strong interest in developing scalable, efficient, and real-world AI solutions. At the AMD AI Hackathon, she is excited to leverage AMD Instinct™ GPUs and cloud-based AI infrastructure to build high-performance AI agents capable of solving complex real-world challenges. She looks forward to collaborating with innovators worldwide, exploring GPU-accelerated AI workflows, and pushing the boundaries of agentic AI and next-generation intelligent applications.
🤓 Latest Submissions
Submission Title: SceneScribe AI
SceneScribe AI is an AI-powered video captioning agent that analyzes video content across multiple temporal frames and generates captions in four requested styles: formal, sarcastic, humorous tech, and humorous non-tech. The system extracts uniformly distributed frames with FFmpeg, builds a grounded factual representation of visible objects, actions, scene context, and temporal changes, and then transforms that representation into style-specific captions. The agent is packaged as a Linux AMD64 Docker container, reads tasks from /input/tasks.json, processes each video URL, validates all requested output styles, writes valid JSON to /output/results.json, and exits automatically. The pipeline has been tested successfully on the three official example videos covering urban traffic, an animal scene, and a person working in an office. It uses MiniMax M3 through Fireworks AI for multimodal video understanding and caption generation.
13 Jul 2026
