An audio-conditioned STEVE-1 agent, built with a new Minecraft audio-video CLIP model and a learned prior, matches or beats text- and video-conditioned versions on most short-horizon collection tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
STEVE-Audio: Expanding the Goal Conditioning Modalities of Embodied Agents in Minecraft
An audio-conditioned STEVE-1 agent, built with a new Minecraft audio-video CLIP model and a learned prior, matches or beats text- and video-conditioned versions on most short-horizon collection tasks.