Sepp Hochreiter

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks ICML 2025 Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences ICLR 2025 FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware ICLR 2025 Geometry-Informed Neural Networks ICML 2025 Improving Uncertainty Estimation through Semantically Diverse Language Generation ICLR 2025 MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Masked Image Modeling Representations ICLR 2025 On Information-Theoretic Measures of Predictive Uncertainty UAI 2025 Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics ICLR 2025 The Disparate Benefits of Deep Ensembles ICML 2025 Vision-LSTM: xLSTM as Generic Vision Backbone ICLR 2025 xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference ICML 2025 A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization ICML 2024 Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget AAAI 2024 Energy-based Hopfield Boosting for Out-of-Distribution Detection NeurIPS 2024 Overcoming Saturation in Density Ratio Estimation by Iterated Regularization ICML 2024 xLSTM: Extended Long Short-Term Memory NeurIPS 2024 Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation ICLR 2023 Boundary Graph Neural Networks for 3D Simulations AAAI 2023 Conformal Prediction for Time Series with Modern Hopfield Networks NeurIPS 2023 Context-enriched molecule representations improve few-shot drug discovery ICLR 2023 Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language ICML 2023 Learning to Modulate pre-trained Models in RL NeurIPS 2023 Quantification of Uncertainty with Adversarial Models NeurIPS 2023 Semantic HELM: A Human-Readable Memory for Reinforcement Learning NeurIPS 2023 Variational Annealing on Graphs for Combinatorial Optimization NeurIPS 2023 Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution ICML 2022 CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP NeurIPS 2022 History Compression via Language Models in Reinforcement Learning ICML 2022 Hopfield Networks is All You Need ICLR 2021 MC-LSTM: Mass-Conserving LSTM ICML 2021 Modern Hopfield Networks and Attention for Immune Repertoire Classification NeurIPS 2020 Human-level Protein Localization with Convolutional Neural Networks ICLR 2019 RUDDER: Return Decomposition for Delayed Rewards NeurIPS 2019 Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields ICLR 2018 First Order Generative Adversarial Networks ICML 2018 GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium NeurIPS 2017 Self-Normalizing Neural Networks NeurIPS 2017 Rectified Factor Networks NeurIPS 2015