publications

Research articles in reverse chronological order. Updated August 2026.

Conference and journal articles

  1. DCC: A Tensor Compiler for Processing-in-Memory Architectures
    P. Yang, S. Durvasula, I. Fernandez, M. Sadrosadati, O. Mutlu, G. Pekhimenko, and C. Giannoula
    ISCA, 2026
  2. Contra-GS: Codebook Condensed Gaussian Splatting Training
    S. Durvasula, S. Muhunthan, Z. Mostafa, R. Chen, R. Liang, Y. Guan, N. Ahuja, N. Jain, P. Selvakumar, and N. Vijaykumar
    ICCV, 2025
  3. ARC: Warp-Level Adaptive Atomic Reduction in GPUs to Accelerate Differentiable Rendering
    S. Durvasula, A. Zhao, P. Sanjaya, G. Guan, R. Liang, and N. Vijaykumar
    ASPLOS, 2025
  4. PyGim: An Efficient Graph Neural Network Library for Real Processing-in-Memory Architectures
    C. Giannoula, P. Yang, I. Fernandez, J. Yang, S. Durvasula, Y. Li, M. Sadrosadati, J. Luna, O. Mutlu, and G. Pekhimenko
    SIGMETRICS, 2025
  5. ACE: Efficient GPU Kernel Concurrency for Input-Dependent Irregular Computational Graphs
    S. Durvasula, A. Zhao, R. Kiguru, Y. Guan, Z. Chen, and N. Vijaykumar
    PACT, 2024
  6. DISORF: A Distributed Online NeRF Training and Rendering Framework for Mobile Robots
    C. Li, H. Fan, X. Huang, R. Liang, S. Durvasula, and N. Vijaykumar
    IEEE RA-L; presented at ICRA 2025, 2024
  7. Distributed Training of Neural Radiance Fields: A Performance Characterization
    J. Zhao, L. Zhang, S. Durvasula, F. Chen, N. Jain, S. Panneer, and N. Vijaykumar
    ISPASS, 2024
  8. Ev-Conv: Fast CNN Inference on Event Camera Inputs for High-Speed Robot Perception
    S. Durvasula, Y. Guan, and N. Vijaykumar
    IEEE RA-L; presented at IROS, 2023
  9. VoxelCache: Accelerating Online Mapping in Robotics and 3D Reconstruction Tasks
    S. Durvasula, R. Kiguru, S. Mathur, J. Xu, J. Lin, and N. Vijaykumar
    PACT, 2022

Under review

  1. Squeeze3D: Your 3D Generation Model Is Secretly an Extreme Neural Compressor
    R. Dagli, Y. Guan, S. Durvasula, M. Mofayezi, and N. Vijaykumar
    Under review at TMLR, 2026
  2. FG-Attn: Leveraging Fine-Grain Sparsity in Diffusion Transformers
    S. Durvasula, K. Sreedhar, Z. Moustafa, S. Kothawade, T. Pang, A. Gondimalla, S. Subramanian, N. Shahidi, and N. Vijaykumar
    Under review at TMLR, 2026