From the 1 of 6 linked papers with an AI index.
6 papers
Context-Informed Ship Trajectory Prediction via Conditional Attention
Yuan Guan, Chandler Squires, Timothy Hu +1
The paper introduces the Conditional Informer, a Transformer-based model that predicts ship trajectories by explicitly conditioning vessel states on environmental contexts using a…
Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolate
Duncan Soiffer, Chandler Squires, Yuan Guan +2
The task of compositional generation involves using a conditional generative model, trained only on a subset of the possible conditions, to produce samples from compositionally-def…
Concept Modulation Models: A Unified Framework for Identifiability and Extrapolation
Soheun Yi, Yizhou Lu, Chandler Squires +1
Reliable generalization in conditional latent variable models requires understanding both identifiability and extrapolation: how observed variation across attributes determines lat…
A Unifying Framework for Unsupervised Concept Extraction
Chandler Squires, Pradeep Ravikumar
Techniques for concept extraction, such as sparse autoencoders and transcoders, aim to extract high-level symbolic concepts from low-level nonsymbolic representations. When these e…
The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications
Philippe Brouillard, Chandler Squires, Jonas Wahl +4
Causal discovery aims to automatically uncover causal relationships from data, a capability with significant potential across many scientific disciplines. However, its real-world a…
Synthetic Potential Outcomes and Causal Mixture Identifiability
Bijan Mazaheri, Chandler Squires, Caroline Uhler
Heterogeneous data from multiple populations, sub-groups, or sources is often represented as a ``mixture model'' with a single latent class influencing all of the observed covariat…