Aayan Yadav

Aayan Yadav

Joint Seceretary, DSG IIT Roorkee


Education

  • B.Tech, Data Science and Artificial Intelligence, IIT Roorkee (2022–2026)

Research Interests

  • Machine Learning
  • Object Detection
  • 3D Recontruction and Scene Understanding
  • Vision Language Models

Publications

  • Singh, S.*, Yadav, A.*, Jain, J., Shi, H., Johnson, J., & Desai, K. (2024). Benchmarking Object Detectors with COCO: A New Path Forward. ECCV 2024.

  • Kumar, A.*, Singla, P.*, & Yadav, A. (2025). StegaVision: Enhancing Steganography with Attention Mechanism (Student Abstract). AAAI 2025.

  • Singhi, S.*, Yadav, A.*, Gupta, A., Ebrahimi, S., & Hassanizadeh, P. Provenance Detection for AI-Generated Images: Combining Perceptual Hashing, Homomorphic Encryption, and AI Detection Models. Under Review

  • Puniani, C., Sinha, A., Singhi, S., Yadav, A. Impact of Language Guidance: A Reproducibility Study Under Review


Projects

  • Sirius
    An agentic RAG system using SoTA techniques like AdaRAG, PlanRAG, HyDE, SPLADE, MetRAG, RRF etc.
  • 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.
  • 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.

Follow

GitHub | LinkedIn | Portfolio


Updated: