JEDI is the first online end-to-end latent diffusion world model that trains latents from denoising loss rather than reconstruction, achieving competitive Atari100k results with 43% less VRAM and over 3x faster sampling than pixel diffusion baselines.
Temporal difference learning for model predictive control.arXiv preprint arXiv:2203.04955
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
RLA-WM predicts residual latent actions via flow matching to create visual feature world models that outperform prior feature-based and diffusion approaches while enabling offline video-based robot RL.
TRAP is a tail-aware ranking attack that plants a backdoor in world models so that a trigger causes the model to reorder a few critical imagined trajectories and redirect planning while preserving normal behavior on clean inputs.
RAY-TOLD combines ray-based latent dynamics from LiDAR with MPPI control and a learned policy prior via mixture sampling to lower collision rates in high-density dynamic obstacle environments compared to standard MPPI.
Single-stage fine-tuning of a video model to generate actions as latent frames plus future states and values yields state-of-the-art robot policy performance on LIBERO, RoboCasa, and bimanual tasks.
V-JEPA 2 pre-trained on massive unlabeled video achieves strong results on motion understanding and action anticipation, SOTA video QA at 8B scale, and enables zero-shot robotic planning on Franka arms using only 62 hours of unlabeled robot video.
citing papers explorer
-
Learning Visual Feature-Based World Models via Residual Latent Action
RLA-WM predicts residual latent actions via flow matching to create visual feature world models that outperform prior feature-based and diffusion approaches while enabling offline video-based robot RL.