6 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…
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…
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…