publications

* denotes equal contribution and joint lead authorship.

2026

  1. kla_block.png
    Kalman Linear Attention: Parallel Bayesian Filters For Efficient Language Modelling (ICML 2026)
    Vaisakh Shaj, Cameron Barker, Aidan Scannell, and 3 more authors
    In International Conference on Machine Learning, 2026
    arXiv

2024

  1. multiFig.png
    Learning World Models With Hierarchical Temporal Abstractions: A Probabilistic Perspective
    Vaisakh Shaj
    PhD Thesis preprint arXiv:2404.16078, 2024

2023

  1. mts3.png
    Multi Time Scale World Models
    Vaisakh Shaj, Saleh Gholam Zadeh, Ozan Demir, and 2 more authors
    2023
    arXiv Code Long Talk

2021

  1. hiprssm4.png
    Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios
    Vaisakh Shaj, Dieter Büchler, Rohit Sonker, and 2 more authors
    In International Conference on Learning Representations, 2021
    arXiv Code

2020

  1. acrkn1.png
    Action-Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learning
    Vaisakh Shaj, Philipp Becker, Dieter Büchler, and 5 more authors
    In Conference on Robot Learning, 2020

2019

  1. icml2019.png
    Zero-shot knowledge distillation in deep networks (ICML 2019)
    Vaisakh Shaj*, Gaurav Kumar Nayak*, Konda Reddy Mopuri*, and 2 more authors
    In International Conference on Machine Learning, 2019

2016

  1. Edge-PSO: A recombination operator based PSO algorithm for solving TSP
    Vaisakh Shaj, PM Akhil, and S Asharaf
    In 2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2016