9 papers
From Synthetic Priors to Model Behavior: Structural Coverage in Tabular Foundation Models
He Zhao, Ryan Thompson, Daniel M. Steinberg +3
Tabular foundation models (TFMs) are commonly pretrained on large collections of procedurally generated synthetic tasks, yet it remains unclear how well these synthetic pretraining…
Can Tabular In-Context Learners Generalize to Biomolecular Property Prediction?
Davy Guan, Lu Zhang, Asiri Wijesinghe +7
Predicting biomolecular properties from limited labeled data is a central bottleneck in protein engineering and small-molecule design. As strong pretrained encoders now supply rich…
Arrow: A Foundation Model for Causal Discovery
Ryan Thompson, He Zhao, Daniel M. Steinberg +1
We introduce Arrow, a foundation model for zero-shot causal discovery on observational tabular data. Arrow factorizes a directed acyclic graph into an undirected skeleton and a top…
Active Flow Matching
Yashvir S. Grewal, Daniel M. Steinberg, Thang D. Bui +2
Discrete diffusion and flow matching models capture complex, non-additive and non-autoregressive structure in high-dimensional objective landscapes through parallel, iterative refi…
Flowette: Flow Matching with Graphette Priors for Graph Generation
Asiri Wijesinghe, Sevvandi Kandanaarachchi, Daniel M. Steinberg +1
We study generative modeling of graphs with recurring subgraph motifs. We propose Flowette, a continuous flow matching framework that employs a graph neural network-based transform…
Causal Preference Elicitation
Edwin V. Bonilla, He Zhao, Daniel M. Steinberg
We propose causal preference elicitation, a Bayesian framework for expert-in-the-loop causal discovery that actively queries local edge relations to concentrate a posterior over di…
Generative Bayesian Optimization: Generative Models as Acquisition Functions
Rafael Oliveira, Daniel M. Steinberg, Edwin V. Bonilla
We present a general strategy for turning generative models into candidate solution samplers for batch Bayesian optimization (BO). The use of generative models for BO enables large…
Amortized Active Generation of Pareto Sets
Daniel M. Steinberg, Asiri Wijesinghe, Rafael Oliveira +3
We introduce active generation of Pareto sets (A-GPS), a new framework for online discrete black-box multi-objective optimization (MOO). A-GPS learns a generative model of the Pare…
Variational Search Distributions
Daniel M. Steinberg, Rafael Oliveira, Cheng Soon Ong +1
We develop VSD, a method for conditioning a generative model of discrete, combinatorial designs on a rare desired class by efficiently evaluating a black-box (e.g. experiment, simu…