aradhye agarwal

aradhye agarwal

resume | scholar | github | email


I am a final-year Dual Degree (UG) student in Computer Science and Engineering at the Indian Institute of Technology, Delhi. I am a part of the LCS2 lab, under Prof. Tanmoy Chakraborty, where we work on reducing the computational costs associated with LLM finetuning and inference. Earlier, I had the opportunity to work with Prof. Chetan Arora, with whom I published my very first paper in CVPR'24 which was on monocular depth estimation. Before this, I worked with Prof. Rohan Paul on robust verbal communication with field robots through the use of contextual correction of transcriptions.

news

Nov 12, 2024 This webpage is live.

publications

(* denotes equal contribution)
  1. ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation
    Suraj Patni*, Aradhye Agarwal*, Chetan Arora
    Computer Vision and Pattern Recognition (CVPR), 2024
    paper | arxiv | code | website | cite
  2. The Third Monocular Depth Estimation Challenge
    Computer Vision and Pattern Recognition Workshop (CVPRW), 2024
    paper | arxiv | website | cite
  3. Step-by-Step Unmasking for Parameter-Efficient Fine-tuning of Large Language Models
    Aradhye Agarwal*, Suhas Kamasetty Ramesh*, Ayan Sengupta*, Tanmoy Chakraborty
    Under review
    paper | arxiv | code | cite