Publications

Peer-reviewed publications across AI systems, computer vision, continual learning, physics informed AI and biophysics, neuroscience and applied mathematics. For citations and the most current list, see Google Scholar.

Google ScholarPatentsDownload CV

Coding and Reasoning LLMs

  1. Wang, S., Cai, N., Hong, C., Walker, J., Kroiz, G., Vanica, G., Patil, D., Gavrilescu, A., Sipra, H. and Sankaran, S. MaxKernel: Agentic Kernel Generation for TPUs. Neurips Spotlight ML4Sys Track. [arXiv]
  2. Tschand, A., Hong, C., Walker, J., Cai, N., Wang, S., Subramanian, S., Dev, S., Reddi, V.J., Yazdanbakhsh, A. and Sankaran, S. JAXBench: Benchmarking Autonomous TPU Kernel Optimization. ICML Workshop on Deep Learning for Code (DL4Code), 2026. [arXiv]
  3. Liang, Q., Ingram, S., Vanica, G., Gavrilescu, A., Harrat, N., Sipra, H. and Sankaran, S. Agentic Framework for Deep Learning Workload Migration via In-Context Learning. ML ArchSys 2026. [arXiv]
  4. Cai, S., Nie, S., Chen, Z., Gulalkari, N., Vanica, G., Jain, C. and Sankaran, S. Forecasting machine degradation of GPU clusters. Neurips 2025 ML4Sys track. [OpenReview]

Computer Vision and Continual Learning

  1. Sankaran, S., Yang, D. and Lim, S.N. Refining multimodal representations using a modality-centric self-supervised module, 2022. [OpenReview]
  2. Sankaran, S., Yang, D. and Lim, S.-N. Multimodal Fusion Refiner Networks. arXiv:2104.03435, 2021. [arXiv]
  3. Nakanishi, R., Sankaran, S.*, et al. Automated estimation of image quality for coronary computed tomographic angiography using machine learning. European Radiology 28(9), 4018–4026, 2018. (*equal contribution) [PDF]
  4. Sankaran, S., et al. HALE: Healthy area of lumen estimation for vessel stenosis quantification. MICCAI, LNCS 9902, 380–387, 2016. [PDF]
  5. Sankaran, S., Grady, L.J. and Taylor, C.A. Real-time sensitivity analysis of blood flow simulations to lumen segmentation uncertainty. MICCAI 1, 1–8, 2014.

Neuroscience

  1. Rajasethupathy, P.*, Sankaran, S.*, Marshel, J.H.*, Kim, C.K., Ferenczi, E., Lee, S.Y., Berndt, A., Ramakrishnan, C., Jaffe, A., Lo, M., Liston, C. and Deisseroth, K. Projections from neocortex mediate top-down control of memory retrieval. Nature 526, 653–659, 2015. (*equal contribution) [paper] [PDF]
  2. Tomer, R., Lovett-Barron, M., Kauvar, I., Andalman, A., Burns, V.M., Sankaran, S., Grosenick, L., Broxton, M., Yang, S. and Deisseroth, K. SPED light sheet microscopy: fast mapping of biological system structure and function. Cell 163(7), 1796–1806, 2015.

Computational BioPhysics and Physics Informed AI

  1. Sankaran, S., Lesage, D., Tombropoulos, R., Xiao, N., Kim, H.J., Spain, D., Schaap, M. and Taylor, C.A. Physics driven real-time blood flow simulations. Computer Methods in Applied Mechanics and Engineering 364, 112963, 2020. [paper]
  2. Sankaran, S., et al. Physics driven reduced order model for real time blood flow simulations. arXiv preprint, 2019. [arXiv]
  3. Modi, B.N., Sankaran, S., et al. Predicting the physiological effect of revascularization in serially diseased coronary arteries: clinical validation of a novel CT coronary angiography based technique. Circulation: Cardiovascular Interventions 12(2), 2019. [PDF]
  4. Sankaran, S., Kim, H-J., Choi, G. and Taylor, C. Uncertainty quantification in coronary flow simulations: impact of geometry, boundary conditions and blood viscosity. Journal of Biomechanics 49(12), 2540–2547, 2016. [PDF]
  5. Sankaran, S., Grady, L. and Taylor, C. Fast computation of hemodynamic sensitivity to lumen segmentation uncertainty. IEEE Transactions on Medical Imaging 34(12), 2562–2571, 2015. [PDF]
  6. Sankaran, S., Grady, L. and Taylor, C. Impact of geometric uncertainty on hemodynamic simulations using machine learning. Computer Methods in Applied Mechanics and Engineering 297(1), 167–190, 2015. [PDF]
  7. Ramachandra, A.B., Sankaran, S., Humphrey, J.D. and Marsden, A.L. Computational simulation of the adaptive capacity of vein grafts in response to increased pressure. Journal of Biomechanical Engineering 137(3), 031009, 2015.
  8. Choi, G., Lee, J.M., Kim, H-J., Park, J-B., Sankaran, S., et al. Coronary artery axial plaque stress and its relationship with lesion geometry. JACC: Cardiovascular Imaging 8(10), 1156–1166, 2015.
  9. Choi, G., Kim, H.J., Park, J.B., Lee, J.M., Sankaran, S., et al. Characterization of lesion shape and hemodynamic forces acting on coronary artery atherosclerotic plaques using computational flow dynamics and computed tomography data. Journal of the American College of Cardiology 64(11_S), 2014.
  10. Sankaran, S., Humphrey, J.D. and Marsden, A.L. An efficient framework for optimization and parameter sensitivity analysis in arterial growth and remodeling computations. Computer Methods in Applied Mechanics and Engineering 256, 200–210, 2013.
  11. Sankaran, S., Moghadam, M.E., Kahn, A.M., Tseng, E.E., Guccione, J.M. and Marsden, A.L. Patient-specific multiscale modeling of blood flow for coronary artery bypass graft surgery. Annals of Biomedical Engineering 40(10), 2228–2242, 2012. [paper]
  12. Sengupta, D., Kahn, A.M., Burns, J.C., Sankaran, S., Shadden, S.C. and Marsden, A.L. Image-based modeling of hemodynamics in coronary artery aneurysms caused by Kawasaki disease. Biomechanics and Modeling in Mechanobiology 11(6), 915–932, 2012.
  13. Schriefl, A.J., Reinisch, A.J., Sankaran, S., Pierce, D.M. and Holzapfel, G.A. Quantitative assessment of collagen fibre orientations from two-dimensional images of soft biological tissues. Journal of the Royal Society Interface 9(76), 3081–3093, 2012.
  14. Sankaran, S. and Marsden, A.L. A stochastic collocation method for uncertainty quantification in cardiovascular simulations. Journal of Biomechanical Engineering 133(3), 031001, 2011. [PDF]
  15. Sankaran, S. and Marsden, A.L. The impact of uncertainty on shape optimization of idealized bypass graft models in unsteady flow. Physics of Fluids 22, 121902, 2010.
  16. Bazilevs, Y., Hsu, M.-C., Benson, D.J., Sankaran, S. and Marsden, A.L. Computational fluid-structure interaction: methods and application to a total cavopulmonary connection. Computational Mechanics 45(1), 77–89, 2009.

Uncertainty Quantification, Optimization and Materials

  1. Sankaran, S., Audet, C. and Marsden, A.L. A method for stochastic constrained optimization using derivative-free surrogate pattern search and collocation. Journal of Computational Physics 229(12), 4664–4682, 2010. [PDF]
  2. Sankaran, S. Stochastic optimization using a sparse grid collocation scheme. Probabilistic Engineering Mechanics 24(3), 382–396, 2009. [PDF]
  3. Zabaras, N. and Sankaran, S. An information-theoretic approach to stochastic materials modeling. IEEE Computing in Science and Engineering, 50–59, 2007.
  4. Sankaran, S. and Zabaras, N. Computing property variability of polycrystals induced by grain size and orientation uncertainties. Acta Materialia 55, 2279–2290, 2007.
  5. Sankaran, S. and Zabaras, N. A maximum entropy approach for property prediction of random microstructures. Acta Materialia 54, 2265–2276, 2006.
  6. Zabaras, N., Sundararaghavan, V. and Sankaran, S. An information-theoretic approach for obtaining property PDFs from macro specifications of microstructural variability. TMS Letters 3(1), 1–2, 2006.
  7. Balasubramaniam, K. and Sankaran, S. Ultrasonic interferometric sensor for rheological changes of fluids. Review of Scientific Instruments 77, 084902, 2006.