Vaibhav Rathore
Ph.D. Scholar, IIT Bombay · Senior AI Data Scientist, MOFSL
I am a Ph.D. scholar at IIT Bombay and a Senior AI Data Scientist at Motilal Oswal Financial Services. I completed my M.S. by Research in AI and Data Science at C-MInDS, IIT Bombay, after studying Mechanical Engineering at MNNIT Allahabad.
My research focuses on learning systems that generalize across domains and discover new categories. I also work on multilingual models, multimodal learning, and financial AI.

News
- Three AI4F papers accepted for poster presentation.
- HElIOS accepted at WACV 2027.
- Award for Excellence in Research.
Publications
Published and accepted work. See also Google Scholar.
-
HElIOS: Hyperbolic Generalized Category Discovery for Remote Sensing
WACV 2027 · Accepted
-
Align Before You Quantize: Making Leech Lattice Tokenization Work for Time Series
AI4F Workshop at ACM ICAIF 2026 · Accepted poster · Non-archival workshop
-
CandleDiff: Contextual Diffusion for Structurally Valid OHLC Generation
AI4F Workshop at ACM ICAIF 2026 · Accepted poster · Non-archival workshop
-
Position: Many Agents, Few Minds — Model Concentration as a Governance Metric for Agent-Native Financial Markets
AI4F Workshop at ACM ICAIF 2026 · Accepted poster · Non-archival workshop
-
Beyond Accuracy: What Language-Subspace Interventions Capture, Remove, and Improve
Multi-LLL Workshop at AACL-IJCNLP 2026 · Published
-
SuTRA: Structurally-Unified Tokenization with Root Awareness
Interspeech 2026 · Accepted
-
M³ QuestionIng: Multi-modal Multi-span Medical Question Answering
ACM Transactions on Computing for Healthcare · Published
-
HiDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery
NeurIPS 2025 · Published
-
When Domain Generalization Meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach
CVPR 2025 · Published
-
Towards Unconstrained Pedestrian Attribute Recognition: Evaluating Domain Shift and Open-World Constraints
NewInML Workshop at NeurIPS 2026 · Poster
Blog
- Understanding Satellite Image Processing: From Pixels to Intelligence
A course-wide GNR607 reference with key equations, worked numericals, practical interpretation, and exam pitfalls.
- Optimization in Machine Learning: The Course Revision Guide
A course-wide CS769 revision reference, with definitions, convergence rates, expandable proofs, worked examples, and self-check questions.
- Optimization, Connected: A Revision Guide
A connected guide to gradients, convexity, subgradients, and proximal methods—and what they tell us about optimization and expert routing.
- The Blame Game: How Neural Networks Learn via Backpropagation
How the chain rule assigns responsibility across millions of parameters.
- The Machine That Learns from Mistakes: A Gentle Introduction to Perceptrons and Gradients
An intuitive introduction to learning, decision boundaries, and gradient descent.
- The Evolution of Audio-Driven Lip Synchronization
From adversarial networks to diffusion-based approaches.
- From Linear Algebra to Deep Learning: A Unified Guide
Connecting mathematical foundations to modern neural networks.
Experience
Senior AI Data Scientist
Motilal Oswal Financial Services Ltd. (MOFSL)
Research Intern, Vehant Fellow Track
Vehant Technologies
Research Intern
Motilal Oswal Financial Services Ltd. (MOFSL)
Research Intern
Sony Research India
Research & Development Intern
Clinical AI Assistance
Graduate Engineer Trainee
Reliance Industries Ltd.
Education
Ph.D. · IIT Bombay
Centre of Studies in Resources Engineering (CSRE)
M.S. by Research · C-MInDS, IIT Bombay
Artificial Intelligence and Data Science
B.Tech. · MNNIT Allahabad
Mechanical Engineering
Awards
2026 · Award for Excellence in Research, C-MInDS, IIT Bombay.