pith. sign in

VIP: Towards universal visual reward and representation via value-implicit pre-training

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.RO 2

years

2024 1 2023 1

verdicts

CONDITIONAL 2

representative citing papers

Any-point Trajectory Modeling for Policy Learning

cs.RO · 2023-12-28 · conditional · novelty 7.0

ATM pre-trains models to predict trajectories of any points in videos, then uses those predictions to learn strong visuomotor policies from minimal action labels, beating baselines by 80% on 130+ tasks.

citing papers explorer

Showing 2 of 2 citing papers.