- Implementation, Training, and Benchmarking of the Various Diffusion Models
[1]
[2]
from the scratch in PyTorch.
[1] Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models
.
NeurIPS, 2020.
[2] Dhariwal, P., & Nichol, A. (2021). Diffusion Models Beat GANs on Image Synthesis, NeurIPS, 2021.
- This course project considers the distributed optimization problem over a network, where
the objective is to optimize a global function formed by a sum of local functions,
using only local computation and communication.
- We propose an algorithm
which gives better convergence rate and sub-optimality compared to the existing
algorithms.
- Comprehensive analysis of YOLO versions 1 to 7 and a from-scratch
implementation of YOLOv7 [1] in PyTorch.
-
Implementation and Benchmarking of the Several Vision architectures
[1]
[2]
and SOTA Data augmentations from the scratch in Pytorch.
-
Pytorch Implementation of the paper "Attention is all you need."
[3]
[1] He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for Image Recognition. CVPR 2016.
[2] Tan, M., & Le, Q. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. ICML 2019.
[3] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017).
Attention Is All You Need. NeurIPS 2017.
-
In this Kaggle competition [1], the objective was to train a language model to assess summaries written
by students in grades 3 to 12 for a given prompt.
-
I proposed a simple Data pre-processing approach to incorporate contextual information
from the prompt text into summaries before feeding them into the transformers. We got bronze medal
in this competition.
[1] Franklin, A., Asiegel, HCL-Jevster, King, J., Julianmante, Maggie, Baffour, P., Holbrook, R., & Crossley, S. (2023).
CommonLit - Evaluate Student Summaries. Kaggle.