Scholar
Shree Singhi
Google Scholar ID: xCMGlgwAAAAJ
Student, Indian Institute of Technology Roorkee
Citations & Impact
Citations
5
H-index
2
i10-index
0
Publications
5
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- 1. DINOHash: Learning Adversarially Robust Perceptual Hashes from Self-Supervised Features, ICML 2025 — CODEML Workshop.
- 2. Riemann Sum Optimization for Accurate Integrated Gradients Computation, NeurIPS 2024 — IAI Workshop.
- 3. Strengthening Interpretability: An Investigative Study of Integrated Gradient Methods, TMLR 2024.
Research Experience
- 1. Research Fellow - SGI, Massachusetts Institute of Technology, Jul 2025 - Aug 2025. Mentor: Prof. Justin Solomon. Worked on solvers for heat diffusion on discrete meshes, latent-space optimization for DeepSDFs, etc.
- 2. Summer Intern, KLA, May 2025 - Jul 2025. Optimized YOLO training pipeline for semiconductor defect detection.
- 3. ML Researcher (funded by Zellic), Proteus, Jun 2024 - Feb 2024. Worked on robust perceptual hashing, adversarial training, etc.
- 4. Software Engineering Intern, Uber, May 2024 - Jun 2024. Built Go backend services and Kafka-based event streams.
Education
- Degree: Bachelor's in Data Science and AI; School: IIT Roorkee; Time: Currently enrolled
Background
- Research Interests: Geometry Processing, XAI, Adversarial ML, and Generative Models. Field: Computer Vision and Data Science & AI. Bio: Undergraduate at IIT Roorkee, serving as the Secretary of the student-run ML community, Data Science Group.
Miscellany
- Personal Interests: Squash, running, scouting for ice cream or boba.
