Search Results for author:
Found 4 papers, 1 papers with code
Symbolic Autoencoding for Self-Supervised Sequence Learning
Traditional language models, adept at next-token prediction in text sequences, often struggle with transduction tasks between distinct symbolic systems, particularly when parallel data is scarce.
On Provable Length and Compositional Generalization
Length generalization -- the ability to generalize to longer sequences than ones seen during training, and compositional generalization -- the ability to generalize to token combinations not seen during training, are crucial forms of out-of-distribution generalization in sequence-to-sequence models.
Object-centric architectures enable efficient causal representation learning
Causal representation learning has showed a variety of settings in which we can disentangle latent variables with identifiability guarantees (up to some reasonable equivalence class).
Multi-Domain Causal Representation Learning via Weak Distributional Invariances
Causal representation learning has emerged as the center of action in causal machine learning research.
