Scholar
Jithendaraa Subramanian
Google Scholar ID: s0BzYvYAAAAJ
Toyota Research Institute, McGill University, Mila
Citations & Impact
Citations
176
H-index
5
i10-index
4
Publications
10
Co-authors
14
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network' accepted at NeurIPS 2023; 'Bayesian Learning of Causal Structure and Mechanisms with GFlowNets and Variational Bayes' accepted at the 3rd Workshop on Graphs and more Complex structures for Learning and Reasoning (GCLR) at AAAI 2023; 'Latent Variable Models for Bayesian Causal Discovery' accepted at the ICML 2022 Workshop on Spurious Correlations, Invariance, and Stability.
Research Experience
- Currently an AI resident at the Toyota Research Institute, working on developing multimodal models for applications in material science. In 2024, was a visiting researcher at ServiceNow Research, working on change point detection in temporal causal models and benchmarking text-conditioned forecasting capabilities of LLMs. Spent summer 2023 as a research scientist intern at Amazon training large-scale models for long-term revenue forecasting. During master’s, worked on problems at the intersection of causal discovery and representation learning, some involving GFlowNets. Also had research internships at Carnegie Mellon University and UC Berkeley.
Education
- Completed M.Sc. at McGill University and Mila, supervised by Derek Nowrouzezahrai and Samira Ebrahimi Kahou; completed Bachelors in Production Engineering from NIT, Trichy, India.
Background
- Research interests span probabilistic inference, multimodal generative models, Large Language Models (LLMs), and causality. Passionate about writing GPU-efficient code.
Miscellany
- No personal interests mentioned.
