Bio

👋 I’m Pascal Jutras‑Dubé, a PhD student in Computer Science at Purdue University (advised by Ruqi Zhang). I study sampling and generative modeling through learned stochastic processes, like diffusions and jump processes, and their applications.

Outside the lab, I co-founded Almost Surely, a fashion brand for the geek community. And when I need a reset, I make fresh pasta: flour, eggs, a little patience: an experiment you can taste.

Now seeking: Summer 2026 research / applied scientist PhD internships (ML, generative modeling, sampling, planning, statistics).

Publications

P. Jutras-Dubé, P. Pynadath, R. Zhang. (2025) Single-step consistent diffusion samplers [Frontiers in Probabilistic Inference Workshop at ICLR].

P. Jutras-Dubé, J. Zhang, Z. Wang, R. Zhang. (2025) One-step diffusion samplers via self-distillation and deterministic flow [Under review].

P. Mesana, P. Jutras-Dubé, J. Crowe, et al. (2025) Measuring privacy/utility tradeoffs of format-preserving strategies for data release. Journal of Business Analytics.

P. Punyamoorty, P. Jutras-Dubé, R. Zhang, et al. (2025) Dynamic obstacle avoidance through uncertainty-based adaptive planning with diffusion. International conference on intelligent robots and systems (IROS) [Co-first authors].

P. Jutras-Dubé, M. B. Al-Khasawneh, Z. Yang, et al. (2024) Copula-based transferable models for synthetic population generation. Transportation Research Part C.

P. Jutras-Dubé, R. Zhang, A. Bera. (2024) Adaptive planning with generative models under uncertainty. International conference on intelligent robots and systems (IROS).

P. Mesana, P. Jutras-Dubé, J. Crowe, G. Vial, G. Caporossi. (2024) Evaluating the risk of re-identification in data release strategies: An attacker-centric approach. Hawaii international conference on system sciences (HICSS).