Schmied, Thomas

13 publications

ICML 2025 A Large Recurrent Action Model: xLSTM Enables Fast Inference for Robotics Tasks Thomas Schmied, Thomas Adler, Vihang Prakash Patil, Maximilian Beck, Korbinian Pöppel, Johannes Brandstetter, Günter Klambauer, Razvan Pascanu, Sepp Hochreiter

NeurIPS 2025 Parameter Efficient Fine-Tuning via Explained Variance Adaptation Fabian Paischer, Lukas Hauzenberger, Thomas Schmied, Benedikt Alkin, Marc Peter Deisenroth, Sepp Hochreiter

NeurIPS 2025 pLSTM: Parallelizable Linear Source Transition Mark Networks Korbinian Pöppel, Richard Freinschlag, Thomas Schmied, Wei Lin, Sepp Hochreiter

NeurIPSW 2024 A Large Recurrent Action Model: xLSTM Enables Fast Inference for Robotics Tasks Thomas Schmied, Thomas Adler, Vihang Prakash Patil, Maximilian Beck, Korbinian Pöppel, Johannes Brandstetter, Günter Klambauer, Razvan Pascanu, Sepp Hochreiter

NeurIPSW 2024 One Initialization to Rule Them All: Fine-Tuning via Explained Variance Adaptation Fabian Paischer, Lukas Hauzenberger, Thomas Schmied, Benedikt Alkin, Marc Peter Deisenroth, Sepp Hochreiter

NeurIPSW 2024 One Initialization to Rule Them All: Fine-Tuning via Explained Variance Adaptation Fabian Paischer, Lukas Hauzenberger, Thomas Schmied, Benedikt Alkin, Marc Peter Deisenroth, Sepp Hochreiter

NeurIPS 2023 Learning to Modulate Pre-Trained Models in RL Thomas Schmied, Markus Hofmarcher, Fabian Paischer, Razvan Pascanu, Sepp Hochreiter

ICLRW 2023 Learning to Modulate Pre-Trained Models in RL Thomas Schmied, Markus Hofmarcher, Fabian Paischer, Razvan Pascanu, Sepp Hochreiter

NeurIPSW 2022 InfODist: Online Distillation with Informative Rewards Improves Generalization in Curriculum Learning Rahul Siripurapu, Vihang Prakash Patil, Kajetan Schweighofer, Marius-Constantin Dinu, Thomas Schmied, Luis Eduardo Ferro Diez, Markus Holzleitner, Hamid Eghbal-zadeh, Michael K. Kopp, Sepp Hochreiter

NeurIPSW 2022 InfODist: Online Distillation with Informative Rewards Improves Generalization in Curriculum Learning Rahul Siripurapu, Vihang Prakash Patil, Kajetan Schweighofer, Marius-Constantin Dinu, Thomas Schmied, Luis Eduardo Ferro Diez, Markus Holzleitner, Hamid Eghbal-zadeh, Michael K Kopp, Sepp Hochreiter

CoLLAs 2022 Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning Christian Alexander Steinparz, Thomas Schmied, Fabian Paischer, Marius-constantin Dinu, Vihang Prakash Patil, Angela Bitto-nemling, Hamid Eghbal-zadeh, Sepp Hochreiter

NeurIPSW 2021 Controllable Network Data Balancing with GANs Fares Meghdouri, Thomas Schmied, Thomas Gärtner, Tanja Zseby

NeurIPSW 2021 Fast and Data-Efficient Training of Rainbow: An Experimental Study on Atari Dominik Schmidt, Thomas Schmied