Aayan Yadav

BTech Student
IIT Roorkee

About Me

I am a third-year student at the Mehta Family School of Data Science and Artificial Intelligence at IIT Roorkee. I am interested in Computer Vision. I have worked with segmentation, datasets and AI - generated image detection. I am currently interested in 3D vision. Hence exploring different topics like 3D reconstruction and generation, SLAM and depth estimation. I am currently looking for exciting projects in 3D if you have any ideas or openings please reach out !

▸

News

[July 2024]: COCO-ReM is accepted to ECCV 2024 !

[December 2023]: Reached finals of Smart India Hackathon 2023 !

[October 2022]: Joining IIT Roorkee as a bachelors student.

Publications

Benchmarking Object Detectors with COCO: A New Path Forward

Shweta Singh^*, Aayan Yadav^*, Jitesh Jain, Humphrey Shi, Justin Johnson, Karan Desai

ECCV 2024 paper | bibtex | code | website

StegaVision: Enhancing Steganography with Attention Mechanism (Student Abstract)

Abhinav Kumar, Pratham Singla,Aayan Yadav

AAAI 2025 paper | bibtex | code |

Projects

Sirius

An agentic RAG system using SoTA techniques like AdaRAG, PlanRAG, HyDE, SPLADE, MetRAG, RRF etc.
gradient descent.
GitHub

MedMatcher

Similar Document Template Matching for Medical Dataset. Fine-tuned LayoutLMv3 model on custom medical document dataset using weighted cross entropy loss and minibatch gradient descent.
GitHub

Image Captioning Model

Build an image captioning model using transfer learning techniques on the Flickr8k dataset. We fine-tuned a combination of pretrained Inceptionv3 and LSTM with regularization.
GitHub

Blogs

Dismantling Disentanglement in VAEs

In this blog post I give a brief introduction of variational autoencoders and then explain how we can acieve disentanglement in latent space. It is an explanation of this paper.
Read more

Activation Functions

This is a beginner's introduction to activation functions. This was my first ever blog which I wrote for Blogathon organised by DSG IITR !
Read more