ACWM-Phys is a controllable simulator benchmark with in- and out-of-distribution protocols for evaluating action-conditioned world models across rigid, kinematic, deformable, and particle dynamics.
Mixed citations
Vid2World: Crafting video diffusion models to interactive world models.arXiv preprint arXiv:2505.14357, 2025
Mixed citation behavior. Most common role is background (67%).
13
Pith papers citing it
Background
67% of classified citations
citation-role summary
background 5
baseline 1
citation-polarity summary
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.
MultiWorld is a scalable framework for multi-agent multi-view video world models that improves controllability and consistency over single-agent baselines in game and robot tasks.
DreamDojo is a foundation world model pretrained on the largest human video dataset to date that uses continuous latent actions to transfer interaction knowledge and achieves controllable physics simulation after robot post-training.
PanoWorld adds depth consistency and trajectory consistency losses plus spherical adaptations to a pre-trained video model, plus a new PanoGeo dataset, to produce geometry-consistent 360 video.
DiGSeg repurposes diffusion U-Nets as generalist segmentation learners by conditioning on image-mask latents and multi-scale CLIP text features, achieving strong cross-domain performance.
PhyEdit improves physical accuracy in image object manipulation by using explicit geometric simulation as 3D-aware guidance combined with joint 2D-3D supervision.
CoLA-World jointly trains latent action models and world models with a warm-up phase to achieve co-evolution, matching or exceeding prior two-stage methods in video simulation quality and visual planning performance.
Embodied AI requires query-conditioned world models that select the simplest physical abstraction sufficient to answer intervention queries.
OrbiSim builds a differentiable physics engine from world models to support gradient-based policy optimization and contact modeling in robotics.
Semantic latent spaces from pretrained encoders outperform reconstruction-based spaces for robotic world models on planning and downstream policy performance.
Proposes WorldString, a differentiable neural model for the state manifold of actionable physical objects learned directly from 3D or video data as a building block for world models.
citing papers explorer
-
ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models
ACWM-Phys is a controllable simulator benchmark with in- and out-of-distribution protocols for evaluating action-conditioned world models across rigid, kinematic, deformable, and particle dynamics.
-
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.
-
MultiWorld: Scalable Multi-Agent Multi-View Video World Models
MultiWorld is a scalable framework for multi-agent multi-view video world models that improves controllability and consistency over single-agent baselines in game and robot tasks.
-
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
DreamDojo is a foundation world model pretrained on the largest human video dataset to date that uses continuous latent actions to transfer interaction knowledge and achieves controllable physics simulation after robot post-training.
-
PanoWorld: Geometry-Consistent Panoramic Video World Modeling
PanoWorld adds depth consistency and trajectory consistency losses plus spherical adaptations to a pre-trained video model, plus a new PanoGeo dataset, to produce geometry-consistent 360 video.
-
Diffusion Model as a Generalist Segmentation Learner
DiGSeg repurposes diffusion U-Nets as generalist segmentation learners by conditioning on image-mask latents and multi-scale CLIP text features, achieving strong cross-domain performance.
-
PhyEdit: Towards Real-World Object Manipulation via Physically-Grounded Image Editing
PhyEdit improves physical accuracy in image object manipulation by using explicit geometric simulation as 3D-aware guidance combined with joint 2D-3D supervision.
-
Co-Evolving Latent Action World Models
CoLA-World jointly trains latent action models and world models with a warm-up phase to achieve co-evolution, matching or exceeding prior two-stage methods in video simulation quality and visual planning performance.
-
Physically Viable World Models: A Case for Query-Conditioned Embodied AI
Embodied AI requires query-conditioned world models that select the simplest physical abstraction sufficient to answer intervention queries.
-
OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence
OrbiSim builds a differentiable physics engine from world models to support gradient-based policy optimization and contact modeling in robotics.
-
Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
Semantic latent spaces from pretrained encoders outperform reconstruction-based spaces for robotic world models on planning and downstream policy performance.
-
WorldString: Actionable World Representation
Proposes WorldString, a differentiable neural model for the state manifold of actionable physical objects learned directly from 3D or video data as a building block for world models.
- FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization