I am a Senior Data Scientist/Research enthusiast. I have worked on Traditional ML and Computer vision:
Object Detection | Object Classification |
Instance segmentation | Semantic segmentation |
keypoint segmentation | Face detection |
Image similarity | OCR |
and in NLP and in Multimodality:
NLP | Multimodality |
---|---|
Text classification | CLIP |
Text summarization(abstract&extract) | DINO |
Text translation | Image captioning |
Large Language Models | MultiModal RAG |
π¬ My research interests are in bridging vision and language modalities or MultiModality Space +Diffusers.
- Portfolio - https://purnasai.github.io/
- linkedin- https://www.linkedin.com/in/purnasai-gudikandula/
- Medium - https://medium.com/@purnasaigudikandula
- Github - https://github.com/purnasai