I am an undergraduate student, majoring in computer science and engineering at the National Institute of Technology Rourkela, India. I am broadly interested in deep learning and machine learning research, with a focus on multi-modal learning and interpretability.
Currently, I am working on continual learning and test-time training for Vision Transformers at the Visual Computing Lab (VCL), IISc Bangalore, under the guidance of Dr. Anirban Chakraborty.
Previously, in the summer of 2024, I worked with Dr. Konda Reddy Mopuri at IIT Hyderabad on Vision Transformers and explainability; in the summer of 2025, I worked with Prof. Vineeth Balasubramanian on faithful Concept Bottleneck Models (CBMs) for medical imaging; and in the subsequent semester, I worked with Dr. Prasenjit Dey on diffusion-based sketch-to-face synthesis.
For more details, drop me an email.News & Honors
- Spending my final semester at IISc Bangalore, at the Visual Computing Lab (VCL) under Dr. Anirban Chakraborty!
- Ranked 5th in the Computer Science and Engineering department at NIT Rourkela (upto 7th semester).
- Accepted into the highly competitive ACM-IKDD Uplink 2025 program, where I will be working with Prof. Vineeth Balasubramanian on Reasoning in Vision-Language Models back at IIT Hyderabad.
- Accepted into the prestigious RISC 2025 program at the University of Maryland.
- Ranked 5th in the Capsule Vision Challenge 2024 as Team Seq2Cure, organized by CVIP 2024.
- Selected among 170 from 20,000+ applicants for the SURE program at IIT Hyderabad.
- Achieved 2nd place in HackFest 24, a hackathon organized by ML4E for undergraduate students.
- Recognized as a Kaggle Expert in Datasets & Notebooks.
Publications
CapsoNet: A CNN-Transformer Ensemble for Multi-Class Abnormality Detection in Video Capsule Endoscopy
, Ranya Batsyas
arXiv preprint |
Oct, 2024
pdf
abstract
code
Selected Projects
SketchWarp
Developed a self-supervised learning framework in PyTorch for dense photo-to-sketch correspondences, enabling automatic image-to-sketch warping. Designed and implemented training and evaluation pipelines inspired by the “Learning Dense Correspondences between Photos and Sketches” paper.
code
paper
NeurIPS Ariel Data Challenge 2024
Developed a pipeline for predicting spectral values in the NeurIPS Ariel Data Challenge 2024 using time-series calibration, spatial aggregation, and gradient-based phase detection.
Ranked 257/1,152 by applying Nelder-Mead optimization and cubic polynomial fitting to model planetary transits from raw sensor data.
code
kaggle
Paper Implementations
Implemented significant AI and machine learning research papers, including transformers (such as GPT variants, BERT, ViTs) as well as LoRA and neural style transfer.
I actively implement new papers and continuously update this repository.
code
Measuring Patch Importance in ViT's (Vanilla & Attention Rollout)
Analyzed patch importance in Vision Transformers using attention scores of the [CLS] token across MHSA mechanims in all blocks, visualizing the distribution of top-k patch tokens.
Implemented Attention Rollout to propagate attention through layers, creating interpretable visualizations of information flow and enhancing understanding of self-attention mechanisms.
code
