publications

My publications in reversed chronological order.

2025

  1. tfla_fig1_icon.png
    Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
    Maximilian Beck, Korbinian Pöppel , Phillip Lippe , and 1 more author
    In Arxiv , 2025
  2. ICML25
    xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference
    Maximilian Beck*, Korbinian Pöppel* , Phillip Lippe* , and 5 more authors
    In International Conference on Machine Learning (ICML) , 2025
  3. flashrnn_fig1_cropped.png
    FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware
    Korbinian Pöppel , Maximilian Beck, and Sepp Hochreiter
    In The International Conference on Learning Representations (ICLR) , 2025
  4. ICLR25
    Vision-LSTM: xLSTM as Generic Vision Backbone
    Benedikt Alkin , Maximilian Beck, Korbinian Pöppel , and 2 more authors
    In The International Conference on Learning Representations (ICLR) , 2025

2024

  1. xlstm_figure1_cropped.png
    xLSTM: Extended Long Short-Term Memory
    Maximilian Beck*, Korbinian Pöppel* , Markus Spanring , and 6 more authors
    In Advances in Neural Information Processing Systems (NeurIPS) , 2024
  2. arXiv
    A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
    Thomas Schmied , Thomas Adler , Vihang Patil , and 6 more authors
    In arXiv , 2024

2023

  1. Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation
    Marius-Constantin Dinu , Markus Holzleitner , Maximilian Beck, and 7 more authors
    In The International Conference on Learning Representations (ICLR) , 2023

2022

  1. subgd-pca.png
    Few-Shot Learning by Dimensionality Reduction in Gradient Space
    Martin Gauch , Maximilian Beck, Thomas Adler , and 10 more authors
    In The Conference on Lifelong Learning Agents , 2022