WorldAgen: Unified State-Action Prediction with Test-Time World Model Training
WorldAgen is presented, a unified framework that jointly learns world modeling and action prediction while enabling test-time training (TTT) to adapt to new environments, and surpasses existing state-of-the-art models at inference time.
Chi Wan, Kang-Rui Wang, Yuan Si et al.
· AAAI Conference on Artificia... · 5 citations