UWM-JEPA uses a density-matrix latent and unitary predictor in JEPA to preserve joint-state spectrum during blind rollouts, achieving 0.77 accuracy on a five-step hidden-velocity task versus 0.53 for an LSTM baseline.
Action-Conditional Video Prediction using Deep Networks in Atari Games
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
Motivated by vision-based reinforcement learning (RL) problems, in particular Atari games from the recent benchmark Aracade Learning Environment (ALE), we consider spatio-temporal prediction problems where future (image-)frames are dependent on control variables or actions as well as previous frames. While not composed of natural scenes, frames in Atari games are high-dimensional in size, can involve tens of objects with one or more objects being controlled by the actions directly and many other objects being influenced indirectly, can involve entry and departure of objects, and can involve deep partial observability. We propose and evaluate two deep neural network architectures that consist of encoding, action-conditional transformation, and decoding layers based on convolutional neural networks and recurrent neural networks. Experimental results show that the proposed architectures are able to generate visually-realistic frames that are also useful for control over approximately 100-step action-conditional futures in some games. To the best of our knowledge, this paper is the first to make and evaluate long-term predictions on high-dimensional video conditioned by control inputs.
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
unclear 1representative citing papers
mimic-video combines internet video pretraining with a flow-matching decoder to achieve state-of-the-art robotic manipulation performance with 10x better sample efficiency than vision-language-action models.
Generative model with normalized pairwise distance constraint discovers output space topologies from sparse data and outperforms GANs and VAEs by avoiding mode collapse.
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.
citing papers explorer
-
mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs
mimic-video combines internet video pretraining with a flow-matching decoder to achieve state-of-the-art robotic manipulation performance with 10x better sample efficiency than vision-language-action models.
-
World Action Models: The Next Frontier in Embodied AI
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.