I'm a Master's student in AI, with a focus on data science, deep learning, computer vision, and language models.

I enjoy building pipelines that actually work — whether that's benchmarking DINOv2 on CIFAR, restoring blurry images, or fusing human traits across video, text, and audio.

• Charisma Predictor: Predicts personality & charisma scores via multi-modal fusion (video, audio, text). Achieved 92.5% accuracy using custom ensemble logic.
• MiniVision: Benchmarks ResNet, EfficientNet, DINOv2 on CIFAR-10&100. ViT reached 98.7% & 91.5% accuracy.
• Image Restoration: DnCNN vs. NAFNet on GOPRO/RealBlur with metric + perceptual analysis
• Image Stitching: Harris + SIFT + RANSAC full classical CV pipeline

• Deep Learning & Model Fusion
• Vision Transformers & Visual Reasoning
• Human-Centered AI (Multimodal signals)
• Tools that Make Models Usable

• 🌐 LinkedIn
• 📩 Email: [[email protected]]