publications

Research publications in reverse chronological order.

2026

  1. Are Learned Vascular Tree Generators Better Than Conditional Resampling?
    Reza Akbarian Bafghi, Sukirt Thakur, and Maziar Raissi
    arXiv preprint arXiv:2610.30449, Oct 2026
    HTML
  2. CARS: A Centerline-Anchored Attention Surrogate for Coronary Blood Flow on Skeleton-Generated Lumen Geometries
    Reza Akbarian Bafghi, Sukirt Thakur, and Maziar Raissi
    arXiv preprint arXiv:2610.30498, Oct 2026
    HTML
  3. Self-Supervised Coarse Spaces for Structured Multigrid Failure Modes
    Reza Akbarian Bafghi, Rahul Sharma, John L. Davenport, and Maziar Raissi
    In Representations for the Physical Sciences Workshop @ NeurIPS 2026, Oct 2026
    HTML PDF
  4. centerlines.webp
    From Centerlines to Hemodynamics: Anisotropic RBF Decoders for Coronary Arteries
    Reza Akbarian Bafghi*, Sukirt Thakur*, and Maziar Raissi
    Transactions on Machine Learning Research, Aug 2026
    HTML PDF Website
  5. punch.webp
    PUNCH: Physics-informed Uncertainty-aware Network for Coronary Hemodynamics
    Sukirt Thakur, Marcus Roper, Yang Zhou, Dmitry Yu. Isaev, and 7 more authors
    Medical Image Analysis, Sep 2026
    DOI HTML
  6. PINN-Sed: An Interconnected Physics-Informed Machine Learning Model for High Resolution Suspended Sediment Transport in River Network
    Arman Haddadchi, Neshat Movahedi, Reza Akbarian Bafghi, and Maziar Raissi
    Journal of Hydraulic Engineering, 2026
    DOI HTML
  7. Test-Driven Agentic Framework for Reliable Robot Controller Synthesis
    Shivanshu Tripathi, Reza Akbarian Bafghi, and Maziar Raissi
    In International Conference on Control, Automation and Systems (ICCAS), 2026
    HTML

2025

  1. Predictions and Corrections: Neural Predictors with Solver-based Correction for ODEs and PDEs
    Reza Akbarian Bafghi, Hasitha De Silva, Joseph G. Kocheemoolayil, John L. Davenport, and 6 more authors
    In ML4PS Workshop, NeurIPS, 2025
    HTML PDF
  2. Geometry-Aware Hemodynamics via a Transformer Encoder and Anisotropic RBF Decoder
    Reza Akbarian Bafghi*, Sukirt Thakur*, and Maziar Raissi
    In ML4PS Workshop, NeurIPS, 2025
    HTML PDF
  3. aligning.webp
    Aligning to What? Limits to RLHF Based Alignment
    Logan Barnhart, Reza Akbarian Bafghi, Stephen Becker, and Maziar Raissi
    In Findings of the Association for Computational Linguistics: NAACL, 2025
    DOI HTML Code
  4. Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation
    Reza Akbarian Bafghi, Carden Bagwell, Avinash Ravichandran, Ashish Shrivastava, and 1 more author
    arXiv preprint arXiv:2501.15377, 2025
    HTML
  5. mixdiff.webp
    MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations
    Reza Akbarian Bafghi*, Nidhin Harilal*, Claire Monteleoni, and Maziar Raissi
    In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
    DOI HTML Code

2024

  1. peft.webp
    Parameter Efficient Fine-tuning of Self-supervised ViTs without Catastrophic Forgetting
    Reza Akbarian Bafghi*, Nidhin Harilal*, Claire Monteleoni, and Maziar Raissi
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshop, 2024
    DOI HTML Code
  2. Comparing PINNs Across Frameworks: JAX, TensorFlow, and PyTorch
    Reza Akbarian Bafghi and Maziar Raissi
    In AI4DifferentialEquations Workshop, ICLR, 2024
    HTML Code Website
  3. Influence Estimation in Self-Supervised Learning
    Nidhin Harilal*, Reza Akbarian Bafghi*, Amit Kiran Rege*, Maziar Raissi, and 1 more author
    In SSL Workshop, NeurIPS, 2024
    HTML Website
  4. Where Did Your Model Learn That? Label-free Influence for Self-supervised Learning
    Nidhin Harilal, Amit Kiran Rege, Reza Akbarian Bafghi, Maziar Raissi, and 1 more author
    2024
    HTML Code

2023

  1. vizwiz.webp
    A New Dataset Based on Images Taken by Blind People for Testing the Robustness of Image Classification Models Trained for ImageNet Categories
    Reza Akbarian Bafghi and Danna Gurari
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
    DOI HTML Code
  2. PINNs-Torch: Enhancing Speed and Usability of Physics-Informed Neural Networks with PyTorch
    Reza Akbarian Bafghi and Maziar Raissi
    In The Symbiosis of Deep Learning and Differential Equations III, NeurIPS, 2023
    HTML Code
  3. PINNs-TF2: Fast and User-Friendly Physics-Informed Neural Networks in TensorFlow V2
    Reza Akbarian Bafghi and Maziar Raissi
    In Machine Learning and the Physical Sciences Workshop, NeurIPS, 2023
    PDF Code