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.
hub
arXiv preprint arXiv:2402.03570 , year=
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3representative citing papers
CODA augments offline multi-agent RL with on-policy diffusion trajectories that evolve with the joint policy to enable coordination.
Multimodal Diffusion Forcing trains a diffusion model on partially masked multimodal robot trajectories to learn temporal and cross-modal dependencies for forceful manipulation.
BiTrajDiff augments offline RL datasets by running independent forward and backward diffusion processes from intermediate states, yielding higher performance than prior one-directional data-augmentation baselines on D4RL.
Ada-Diffuser is a causal diffusion model that jointly learns observed interaction structure and underlying latent dynamics from minimal observations for adaptive planning and policy learning.
DAWM introduces a modular diffusion world model with an inverse dynamics model to produce complete synthetic transitions that improve conservative offline RL algorithms like TD3BC and IQL on D4RL tasks.
DINO-WM builds world models on pre-trained DINOv2 features to enable zero-shot planning from offline data without rewards or demonstrations.
Embodied AI requires query-conditioned world models that select the simplest physical abstraction sufficient to answer intervention queries.
Transformer world models on Atari exhibit game-specific scaling regimes, but joint training on 26 environments produces consistent monotonic gains that improve downstream control policies to a median normalized score of 0.770.
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.
The paper delivers a multi-axis taxonomy for world models that maps architectures, training families, reasoning strategies, and domains from early cognitive foundations through systems such as Dreamer, MuZero, and Sora while noting evaluation gaps.
The Cosmos platform supplies open-source pre-trained world models and supporting tools for building fine-tunable digital world simulations to train Physical AI.
citing papers explorer
-
BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement Learning
BiTrajDiff augments offline RL datasets by running independent forward and backward diffusion processes from intermediate states, yielding higher performance than prior one-directional data-augmentation baselines on D4RL.