Posts by Collection

Visual prompts using data augmentations for robust out-of-distribution image classification

less than 1 minute read

Tunable Visual prompting using data augmentation techniques such as DeepAugment, CutMix and CutOut for robust predictions for vision-language models like CLIP. Performance evaluations led to 2-3% improvement on different corruptions of CIFAR-C dataset

Seeing is not believing: Privacy preserving facial manipulation using adversarial mask generation and diffusion models

less than 1 minute read

Identified salient features in input images and generated adversarial masks using various techniques such as saliency gradient maps, GRAD-CAM and random patch masking. Created non-private representations of the input images using latent diffusion models, so that private information is not transmitted to downstream tasks such as FaceNet’s recognition model.

Distributed Heterogeneous Training for Large Language Models using Ray and DeepSpeed

less than 1 minute read

Conducted ablation studies for exploring efficient heterogeneous (CPU + GPU) distributed training for language models such as BeRT and RoBeRTa over different factors such as batch size, number of CPU/GPU parallel workers etc. Ray was used for parallelizing CPU processes and Deepspeed’s ZeRO optimization was used for data parallelism along with mixed precision training for sentiment analysis.

Efficiently building ML workflows at scale for production pipelines

Published: March 01, 2012

Personalized BI dashboards for hands-off-the-wheel (HOTW) ML workflows

Published: February 01, 2014

Generating explainations for deals recommendations using SHAP

Published: March 01, 2014

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.