Publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. arXiv
    GEM: GPU-Variability-Aware Expert to GPU Mapping for MoE Systems
    Sourish Wawdhane, Avinash Kumar, and Poulami Das
    arXiv preprint arXiv:2605.19945, 2026
    HTML
  2. arXiv
    Test-Time Speculation
    Avinash Kumar, Sujay Sanghavi, and Poulami Das
    arXiv preprint arXiv:2605.09329, 2026
    HTML
  3. MLSys
    HELIOS: Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving
    Avinash Kumar, Shashank Nag, Jason Clemons, and 2 more authors
    Proceedings of Machine Learning and Systems, 2026
    HTML
  4. ICML
    Quarch: A benchmark for evaluating llm reasoning in computer architecture
    Shvetank Prakash, Andrew Cheng, Arya Tschand, and 24 more authors
    In Forty-third International Conference on Machine Learning, 2026
    HTML

2025

  1. arXiv
    HiSpec: Hierarchical Speculative Decoding for LLMs
    Avinash Kumar, Sujay Sanghavi, and Poulami Das
    arXiv preprint arXiv:2510.01336, 2025
    HTML
  2. ICML
    Dialogue Without Limits: Constant-Sized KV Caches for Extended Response in LLMs
    Ravi Ghadia, Avinash Kumar, Gaurav Jain, and 2 more authors
    In Forty-second International Conference on Machine Learning, 2025
    HTML

2024

  1. MICRO
    Understanding Real Time Decoding for Photonic Quantum Computers
    Avinash Kumar, Eneet Kaur, and Poulami Das
    In 57th IEEE/ACM International Symposium on Microarchitecture, 2024
    HTML

2019

  1. ICASSP
    An improved air tissue boundary segmentation technique for real time magnetic resonance imaging video using segnet
    CA Valliappan, Avinash Kumar, Renuka Mannem, and 1 more author
    In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019
    HTML