Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Fully Sharded Data Parallel 01-06-2023
Fit model more than GPU size.
publications
Paper Title Number 1
Published in Journal 1, 2009
This paper is about the number 1. The number 2 is left for future work.
Recommended citation: Your Name, You. (2009). "Paper Title Number 1." Journal 1. 1(1). http://academicpages.github.io/files/paper1.pdf
Paper Title Number 2
Published in Journal 1, 2010
This paper is about the number 2. The number 3 is left for future work.
Recommended citation: Your Name, You. (2010). "Paper Title Number 2." Journal 1. 1(2). http://academicpages.github.io/files/paper2.pdf
Paper Title Number 3
Published in Journal 1, 2015
This paper is about the number 3. The number 4 is left for future work.
Recommended citation: Your Name, You. (2015). "Paper Title Number 3." Journal 1. 1(3). http://academicpages.github.io/files/paper3.pdf
talks
Attention is All You Need - Birth Of Modern AI
Published:
This is more of my understanding of Transformers rather than the paper summary.
Contrastive Language Image Pretraining (CLIP)
Published:
Image & Text as single Multimodality Embedding space.
Dino V2- DIstillation with NO knowledge
Published:
Paper here
CLIP for Segmentation CLIPSEG
Published:
Segmentation using CLIPs Multimodality Embedding space & a Conditinal Decoder
ImageBIND- 6 Modalities in One Embedding space with Image as BinD
Published:
6 modalities embeddings into a common Embedding space. But all these 6 are binded with Image embeddings using image paired data for every single modality as a single shared representation space. hence the name ImageBind. Till now self supervised models like CLIP has only a bi modal space for Text and Image embeddings.
Fully Sharded Data Paralell
Published:
Fit large model on small GPU
MarkupLM- LayoutLM for HTML Pages
Published:
Multimodal pretraining with text, image, and layout made progress in recent times. One uses 2D positional information i.e. BBoxes to identify the position of text in the layout. For the Large no of digital documents with consistent changes in layouts, existing models are not working.
TryONDiffusion Paper summary
Published:
A Tale of 2 U-Nets with Cross-Attention Communication
Dreamsim- Ensemble of Embeddings as Metric
Published:
For Image similarity.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.