Maximilian Beck

22 papers A* 6Journal 15Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Effective Distillation to Hybrid xLSTM Architectures. CoRR Lukas Hauzenberger, Niklas Schmidinger, Thomas Schmied, Anamaria-Roberta Hartl, David Stap, Pieter-Jan Hoedt, Maximilian Beck, Sebastian Böck, Günter Klambauer, Sepp Hochreiter
2026	J	`jnl`	Towards a Neural Debugger for Python. CoRR Maximilian Beck, Jonas Gehring, Jannik Kossen, Gabriel Synnaeve
2025	A*	`conf`	A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks. ICML Thomas Schmied, Thomas Adler, Vihang Prakash Patil, Maximilian Beck, Korbinian Pöppel, Johannes Brandstetter, Günter Klambauer, Razvan Pascanu, Sepp Hochreiter
2025	J	`jnl`	CWM: An Open-Weights LLM for Research on Code Generation with World Models. CoRR FAIR CodeGen team, Jade Copet, Quentin Carbonneaux, Gal Cohen, Jonas Gehring, Jacob Kahn, Jannik Kossen, Felix Kreuk, Emily McMilin, Michel Meyer, Yuxiang Wei, David Zhang, Kunhao Zheng, Jordi Armengol-Estapé, Pedram Bashiri, Maximilian Beck, Pierre Chambon, Abhishek Charnalia, Chris Cummins, Juliette Decugis, Zacharias V. Fisches, François Fleuret, Fabian Gloeckle, Alex Gu, Michael Hassid, Daniel Haziza, Badr Youbi Idrissi, Christian Keller, Rahul Kindi, Hugh Leather, Gallil Maimon, Aram H. Markosyan, Francisco Massa, Pierre-Emmanuel Mazaré, Vegard Mella, Naila Murray, Keyur Muzumdar, Peter W. O'Hearn, Matteo Pagliardini, Dmitrii Pedchenko, Tal Remez, Volker Seeker, Marco Selvi, Oren Sultan, Sida Wang, Luca Wehrstedt, Ori Yoran, Lingming Zhang, Taco Cohen, Yossi Adi, Gabriel Synnaeve
2025	A*	`conf`	FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware. ICLR Korbinian Pöppel, Maximilian Beck, Sepp Hochreiter
2025	J	`jnl`	PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning. CoRR Xiaogang Jia, Qian Wang, Anrui Wang, Han A. Wang, Balázs Gyenes, Emiliyan Gospodinov, Xinkai Jiang, Ge Li, Hongyi Zhou, Weiran Liao, Xi Huang, Maximilian Beck, Moritz Reuss, Rudolf Lioutikov, Gerhard Neumann
2025	J	`jnl`	Short window attention enables long-term memorization. CoRR Loïc Cabannes, Maximilian Beck, Gergely Szilvasy, Matthijs Douze, Maria Lomeli, Jade Copet, Pierre-Emmanuel Mazaré, Gabriel Synnaeve, Hervé Jégou
2025	J	`jnl`	Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels. CoRR Maximilian Beck, Korbinian Pöppel, Phillip Lippe, Sepp Hochreiter
2025	A*	`conf`	Vision-LSTM: xLSTM as Generic Vision Backbone. ICLR Benedikt Alkin, Maximilian Beck, Korbinian Pöppel, Sepp Hochreiter, Johannes Brandstetter
2025	A*	`conf`	xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference. ICML Maximilian Beck, Korbinian Pöppel, Phillip Lippe, Richard Kurle, Patrick M. Blies, Günter Klambauer, Sebastian Böck, Sepp Hochreiter
2025	J	`jnl`	xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference. CoRR Maximilian Beck, Korbinian Pöppel, Phillip Lippe, Richard Kurle, Patrick M. Blies, Günter Klambauer, Sebastian Böck, Sepp Hochreiter
2025	J	`jnl`	xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity. CoRR Maximilian Beck, Kajetan Schweighofer, Sebastian Böck, Sebastian Lehner, Sepp Hochreiter
2024	J	`jnl`	A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks. CoRR Thomas Schmied, Thomas Adler, Vihang Patil, Maximilian Beck, Korbinian Pöppel, Johannes Brandstetter, Günter Klambauer, Razvan Pascanu, Sepp Hochreiter
2024	J	`jnl`	FlashRNN: Optimizing Traditional RNNs on Modern Hardware. CoRR Korbinian Pöppel, Maximilian Beck, Sepp Hochreiter
2024	J	`jnl`	Vision-LSTM: xLSTM as Generic Vision Backbone. CoRR Benedikt Alkin, Maximilian Beck, Korbinian Pöppel, Sepp Hochreiter, Johannes Brandstetter
2024	A*	`conf`	xLSTM: Extended Long Short-Term Memory. NeurIPS Maximilian Beck, Korbinian Pöppel, Markus Spanring, Andreas Auer, Oleksandra Prudnikova, Michael Kopp, Günter Klambauer, Johannes Brandstetter, Sepp Hochreiter
2024	J	`jnl`	xLSTM: Extended Long Short-Term Memory. CoRR Maximilian Beck, Korbinian Pöppel, Markus Spanring, Andreas Auer, Oleksandra Prudnikova, Michael Kopp, Günter Klambauer, Johannes Brandstetter, Sepp Hochreiter
2023	A*	`conf`	Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation. ICLR Marius-Constantin Dinu, Markus Holzleitner, Maximilian Beck, Hoan Duc Nguyen, Andrea Huber, Hamid Eghbal-zadeh, Bernhard Alois Moser, Sergei V. Pereverzyev, Sepp Hochreiter, Werner Zellinger
2023	J	`jnl`	Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation. CoRR Marius-Constantin Dinu, Markus Holzleitner, Maximilian Beck, Hoan Duc Nguyen, Andrea Huber, Hamid Eghbal-zadeh, Bernhard Alois Moser, Sergei V. Pereverzyev, Sepp Hochreiter, Werner Zellinger
2023	J	`jnl`	Artificial Intelligence for Cybersecurity. IEEE Softw. Christof Ebert, Maximilian Beck
2022	—	`conf`	Few-Shot Learning by Dimensionality Reduction in Gradient Space. CoLLAs Martin Gauch, Maximilian Beck, Thomas Adler, Dmytro Kotsur, Stefan Fiel, Hamid Eghbal-zadeh, Johannes Brandstetter, Johannes Kofler, Markus Holzleitner, Werner Zellinger, Daniel Klotz, Sepp Hochreiter, Sebastian Lehner
2022	J	`jnl`	Few-Shot Learning by Dimensionality Reduction in Gradient Space. CoRR Martin Gauch, Maximilian Beck, Thomas Adler, Dmytro Kotsur, Stefan Fiel, Hamid Eghbal-zadeh, Johannes Brandstetter, Johannes Kofler, Markus Holzleitner, Werner Zellinger, Daniel Klotz, Sepp Hochreiter, Sebastian Lehner