Optimistic Task Inference for Behavior Foundation Models

ICLROral2026

Authors: Thomas Rupf, Marco Bagatella, Marin Vlastelica, Andreas Krause
Affiliation: ETHZ - ETH Zurich
Venue: ICLR 2026
Track: Oral

TL;DR

We propose an algorithm for fast online task inference in behavior foundation models.

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

← All ICLR 2026 Oral papers · Browse the whole archive