NeuroVision: EEG-to-Video Generation using Multimodal Deep Learning
Brain-signal-driven video generation and cross-modal representation learning: decoding what a person sees from their EEG, then generating it as video.
EEE @ BUET · Deep Learning · Computer Vision · Multimodal AI · Speech · Robotics
Life is what how we define it, so define yourself to define your life

Electrical and Electronic Engineering student at Bangladesh University of Engineering and Technology (BUET) with research experience in Deep Learning, Computer Vision, Multimodal AI, Speech Recognition, and Foundation Models.
Author of peer-reviewed publications and an arXiv preprint, with multiple top placements in IEEE AI competitions. Experienced in PyTorch, TensorFlow, model optimization, multimodal learning, and developing practical AI systems, from drones that find survivors to apps that teach.
Drag the sphere to spin it. Pick a category to light up its skills.
Brain-signal-driven video generation and cross-modal representation learning: decoding what a person sees from their EEG, then generating it as video.
Hover or tap a paper to flip it.
Drag or use the arrows to spin the ring.
Open to research collaborations, internships, and interesting engineering problems, or just a friendly chat.