The ELLIS Unit Stuttgart brings together an interdisciplinary team of outstanding researchers at the University of Stuttgart and the Stuttgart site of the Max Planck Institute for Intelligent Systems who advance research in learning and intelligent systems from four synergistic perspectives: Interactive Intelligent Systems, Natural and Programming Language Processing, Learning Theory, and Robot Learning.
Latest News
Spotlight
- ACL'24: Limits of Theory of Mind Modelling in Dialogue-Based Collaborative Plan Acquisition
- AAAI'24: Neural Reasoning About Agents’ Goals, Preferences, and Actions
- AAAI'24: HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric Subspaces
- AAAI'24: Navigating Open Set Scenarios for Skeleton-based Action Recognition
- AAAI'24: NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning
- ICLR'23: SIMPLE: A Gradient Estimator for k-Subset Sampling
- IJCAI'23: ReLiNet: Stable and Explainable Multistep Prediction with Recurrent Linear Parameter Varying Networks
- ICML'23: Learning Globally Smooth Functions on Manifolds
- CVPR'23: Reconstructing Signing Avatars from Video Using Linguistic Priors
- ICML'23: Automatic Data Augmentation via Invariance-Constrained Learning
- AAAI'23: Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models
- ICML'23: Learning Neural PDE Solvers with Parameter-Guided Channel Attention
- ASE'22: CrystalBLEU: Precisely and Efficiently Measuring the Similarity of Code
- ICML'22: Utilizing Expert Features for Contrastive Learning of Time-Series Representations
- ICLR'22: SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning
- NeurIPS'22: Ordered Subgraph Aggregation Networks
- NeurIPS'22: PDEBENCH: An Extensive Benchmark for Scientific Machine Learning
- NeurIPS'22: Hyperbolic Embedding Inference for Structured Multi-Label Prediction
- NeurIPS'22: Pseudo-Riemannian Graph Convolutional Networks