Jürgen Schmidhuber

Mixture of States: Routing Token-Level Dynamics for Multimodal Generation CVPR 2026 TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models CVPR 2026 Agent-as-a-Judge: Evaluate Agents with Agents ICML 2025 Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models EMNLP 2025 Directly Forecasting Belief for Reinforcement Learning with Delays ICML 2025 FACTS: A Factored State-Space Framework for World Modelling ICLR 2025 Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective ICML 2025 Measuring In-Context Computation Complexity via Hidden State Prediction ICML 2025 Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning ICML 2025 Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays ICML 2024 Exploring the Promise and Limits of Real-Time Recurrent Learning ICLR 2024 Goldfish: Vision-Language Understanding of Arbitrarily Long Videos ECCV 2024 GPTSwarm: Language Agents as Optimizable Graphs ICML 2024 Highway Value Iteration Networks ICML 2024 Learning Useful Representations of Recurrent Neural Network Weight Matrices ICML 2024 MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework ICLR 2024 MoEUT: Mixture-of-Experts Universal Transformers NeurIPS 2024 Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery NeurIPS 2024 Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning ICML 2024 SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention NeurIPS 2024 Tune-An-Ellipse: CLIP Has Potential to Find What You Want CVPR 2024 Approximating Two-Layer Feedforward Networks for Efficient Transformers EMNLP 2023 Contrastive Training of Complex-Valued Autoencoders for Object Discovery NeurIPS 2023 Goal-Conditioned Generators of Deep Policies AAAI 2023 Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules ICLR 2023 Learning to Identify Critical States for Reinforcement Learning from Videos ICCV 2023 Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions EMNLP 2023 The Benefits of Model-Based Generalization in Reinforcement Learning ICML 2023 A Modern Self-Referential Weight Matrix That Learns to Modify Itself ICML 2022 Exploring through Random Curiosity with General Value Functions NeurIPS 2022 Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules NeurIPS 2022 Reward-Weighted Regression Converges to a Global Optimum AAAI 2022 The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention ICML 2022 The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization ICLR 2022 Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks ICLR 2021 Going Beyond Linear Transformers with Recurrent Fast Weight Programmers NeurIPS 2021 Hierarchical Relational Inference AAAI 2021 Learning Associative Inference Using Fast Weight Memory ICLR 2021 Linear Transformers Are Secretly Fast Weight Programmers ICML 2021 Meta Learning Backpropagation And Improving It NeurIPS 2021 Parameter-Based Value Functions ICLR 2021 Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling ICLR 2021 Unsupervised Object Keypoint Learning using Local Spatial Predictability ICLR 2021 Fusion Architectures for Word-Based Audiovisual Speech Recognition Interspeech 2020 Are Disentangled Representations Helpful for Abstract Visual Reasoning? NeurIPS 2019 Hindsight policy gradients ICLR 2019 Domain-Adversarial Training for Session Independent EMG-based Speech Recognition Interspeech 2018 Learning to Reason with Third Order Tensor Products NeurIPS 2018 Recurrent World Models Facilitate Policy Evolution NeurIPS 2018 Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions ICLR 2018 Improving Speaker-Independent Lipreading with Domain-Adversarial Training Interspeech 2017 Neural Expectation Maximization NeurIPS 2017 Recurrent Highway Networks ICML 2017 Deep Neural Network Frontend for Continuous EMG-Based Speech Recognition Interspeech 2016 Tagger: Deep Unsupervised Perceptual Grouping NeurIPS 2016 Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation NeurIPS 2015 Training Very Deep Networks NeurIPS 2015 Deep Networks with Internal Selective Attention through Feedback Connections NeurIPS 2014 Natural Evolution Strategies JMLR 2014 Compete to Compute NeurIPS 2013 Upper Confidence Weighted Learning for Efficient Exploration in Multiclass Prediction with Binary Feedback IJCAI 2013 Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images NeurIPS 2012 Improving the Asymptotic Performance of Markov Chain Monte-Carlo by Inserting Vortices NeurIPS 2010 Accelerated Neural Evolution through Cooperatively Coevolved Synapses JMLR 2008 Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks NeurIPS 2008 Unconstrained On-line Handwriting Recognition with Recurrent Neural Networks NeurIPS 2007 Learning Precise Timing with LSTM Recurrent Networks JMLR 2002