STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling
Paper • 2610.00907 • Published
steer-rt-checkpoints
RT-12 leave-one-database-out checkpoints (one directory per held-out RelBench database), trained by the STEER authors with the Relational Transformer training pipeline on the eight RelBench databases used in the paper. Cite RelBench and the Relational Transformer.
Part of STEER: STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling (Mohamed and Aboulnaga, arXiv:2610.00907).
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support