[Vidushee :)]
Vidushee Vats
Undergraduate Student with interest in Computer Vision, Deep Learning, Multimodality
Contact: {X @ Y}, X=vatsvidushee, Y=gmail.com
Biography
Hi, I am a final-year CSE undergrad with interest in Computer Vision and Multi-Modality. Currently I am working as an AI Research Intern @Georgia Institute of Technology, advised by Prof. Vijay K Madisetti. I have interned as a Computer Vision Intern @ZocketAI. I am interested in learning and working on multi-modality, Computer Vision and Deep Learning. [...]
Name

Family name: 馬(Mǎ) means horse.

Given name: 平(Píng)川(chuān) means flat and level ground without geographical barrier.

Quoted from a Chinese idiom 一馬平川, my full name means the flat ground that one can ride straight across and thus implies enjoying a smooth life.

眾峰來自天目山，勢若駿馬奔平川。

There are lots of mountains from Tianmu Mountain, which have the might of fine horses galloping across flat ground.

Experience
Logo

Georgia Institute of Technology

Research Intern

Sep 2024 - Present

Currently Working: Improving vision-language models (VLMs) for visual grounding and developing a multi-agent framework to transcribe live sports, emulating the style of human commentators.

Zocket Logo

ZocketAI

Computer Vision Intern

May 2024 - Nov 2024

Worked with multimodals and Vision-Language Alignment, fine-tuning SDXL on custom data, built framework to retrieve visually semantic video

Research
[LLaVA-PlantDiag]
LLaVA-PlantDiag: Integrating Large-scale Vision-Language Abilities for Conversational Plant Pathology Diagnosis
Karun Sharma, Vidushee Vats Abhinendra Singh, Rahul Sahani, Deepak Rai, and Ashok Sharma,
IJCNN 2024 / bibtex 
@INPROCEEDINGS{10651096,
  author={Sharma, Karun and Vats, Vidushee and Singh, Abhinendra and Sahani, Rahul and Rai, Deepak and Sharma, Ashok},
  booktitle={2024 International Joint Conference on Neural Networks (IJCNN)},
  title={LLaVA-PlantDiag: Integrating Large-scale Vision-Language Abilities for Conversational Plant Pathology Diagnosis},
  year={2024},
  volume={},
  number={},
  pages={1-7},
  keywords={Pathology;Visualization;Plant diseases;Accuracy;Generative AI;Convolution;Neural networks;Multimodal;LLM;LLaVA;Phytopathological Multimodal Data},
  doi={10.1109/IJCNN60899.2024.10651096}}

}