 Towards Understanding Extrapolation: a Causal LensNeural Information Processing Systems (NeurIPS), 2025 |
 Compositional Audio Representation LearningIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024 |
 Object-centric architectures enable efficient causal representation
learningInternational Conference on Learning Representations (ICLR), 2023 |
 On the Identifiability of Quantized FactorsCLEaR (CLEaR), 2023 |
 Nonparametric Identifiability of Causal Representations from Unknown
InterventionsNeural Information Processing Systems (NeurIPS), 2023 |
 Reusable Slotwise MechanismsNeural Information Processing Systems (NeurIPS), 2023 |
 Learning Efficient Abstract Planning Models that Choose What to PredictConference on Robot Learning (CoRL), 2022 |
