Formalizes video world models as group actions on states and uses latent regularization with synthesized supervision to enforce consistency, introducing GAC and GAR metrics that improve structural correctness in SOTA models.
Dreamerad: Efficient re- inforcement learning via latent world model for autonomous driving
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Discrete-WAM unifies world modeling and policy learning for autonomous driving by representing observations, states, decisions, and actions as tokens in one space and using hierarchical token editing for planning.
RAD-2 uses a diffusion generator and RL discriminator to cut collision rates by 56% in closed-loop autonomous driving planning.
citing papers explorer
-
World Models as Group Actions
Formalizes video world models as group actions on states and uses latent regularization with synthesized supervision to enforce consistency, introducing GAC and GAR metrics that improve structural correctness in SOTA models.
-
Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning
Discrete-WAM unifies world modeling and policy learning for autonomous driving by representing observations, states, decisions, and actions as tokens in one space and using hierarchical token editing for planning.
-
RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
RAD-2 uses a diffusion generator and RL discriminator to cut collision rates by 56% in closed-loop autonomous driving planning.