Saeid Naderiparizi

I am a third year Ph.D. student in Computer Science at the University of British Columbia. I am a member of the PLAI lab led by Frank Wood.
My research interests are generative models, constrained generation, and Bayesian inference.

Email / Google Scholar / GitHub / LinkedIn

Publications

	Constrained Generative Modeling with Manually Bridged Diffusion Models Saeid Naderiparizi, , , AAAI, 2025 (Oral Presentation) Diffusion models on constrained domains. The constraints are specified by differentiable distance functions.
	Don't be so negative! Score-based Generative Modeling with Oracle-assisted Guidance Saeid Naderiparizi, , , , ICML, 2024 Diffusion models under constraints specified by a given binary oracle that determines whether a sampled data point is valid or not.
	RangeAugment: Efficient Online Augmentation with Range Learning , Saeid Naderiparizi, , , , , , arXiv preprint, 2022 An automatic augmentation method that efficiently learns the range of augmentations together with training the downstream model. On multiple large-scale computer vision tasks, it achieves competitive performance with state-of-the-art augmentation methods, with 4-5 times fewer augmentation operations. Work was done during my summer internship at Apple. [Code (as a part of CVNets repository)]
	Flexible Diffusion Modeling of Long Videos , Saeid Naderiparizi, , , NeurIPS, 2022 Video generative models based on Denoising Diffusion Probabilistic Models (DDPMs). This model can generate videos of more than an hour in length. [Project page] [Code] [Videos] [arXiv]
	Amortized Rejection Sampling in Universal Probabilistic Programming Saeid Naderiparizi, , , , , , , , , , , AISTATS, 2022 (Oral Presentation) [Top-9%] Identifying and addressing the problems caused by rejection sampling loops in inference in universal probabilistic programs. [Code] [arXiv]
	Conditional Image Generation by Conditioning Variational Auto-Encoders , Saeid Naderiparizi, ICLR, 2022 Conditional image completion using amortized inference in image generative models, particularly, variational auto-encoders. We demonstrate that it leads to diverse and realistic generated images. [Code] [arXiv]
	Uncertainty in Neural Processes Saeid Naderiparizi, , , arXiv preprint, 2020 Achieving calibrated uncertainty in Neural Processes, especially in low data regime, via different architectures and training objectives.
	Planning as Inference in Epidemiological Dynamics Models , , Saeid Naderiparizi, , , , , , Frontiers in Artificial Intelligence, 2022 Automating parts of infectious disease-control policy-making via performing inference in existing epidemiological dynamics models. [Code] [Frontiers]
	Coping With Simulators That Don't Always Return , Saeid Naderiparizi, AISTATS, 2020 Model learning in models partially defined through "brittle" deterministic simulators. A "brittle" simulator is one which would fail to produce results for invalid inputs that might occur over the course of training. An ODE solver not converging to the required tolerance in the allocated time or solid bodies intersecting in robot simulators are examples of simulator failure. [Code] [arXiv]
	Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model , , , , Saeid Naderiparizi, , , , , , , , , , Neural Information Processing Systems (NeurIPS), 2019 A novel probabilistic programming framework that couples to the existing large-scale simulators via a cross-platform protocol, allowing automatic inference in such simulators.
	Etalumis: bringing probabilistic programming to scientific simulators at scale , , , , , , , Saeid Naderiparizi, , , , , , , , , Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, 2019

Education

	University of British Columbia Ph.D. in Computer Science Supervisor: Frank Wood
	University of British Columbia M.Sc. in Computer Science Supervisor: Frank Wood
	Sharif University of Technology B.Sc. in Computer Engineering Minor degree in Mathematics

Website source forked from Jon Barron.