OVOW reconstructs instance-level, simulation-ready 4D mesh scenes from monocular video via a four-stage training-free pipeline and introduces a new benchmark for structured Video-to-4D evaluation.
hub Canonical reference
3d and 4d world modeling: A survey
Canonical reference. 90% of citing Pith papers cite this work as background.
26
Pith papers citing it
Background
90% of classified citations
hub tools
citation-role summary
background 10
citation-polarity summary
roles
background 10representative citing papers
VSTAT benchmark shows state-of-the-art MLLMs perform far below humans and only modestly above answer-prior baselines on visual state tracking, failing at visual perception despite correct textual reasoning.
GTA generates 3D worlds from single images via a two-stage video diffusion process that prioritizes geometry before appearance to improve structural consistency.
WorldLens benchmark reveals no driving world model dominates across visual, geometric, behavioral, and perceptual fidelity, with contributions of a 26K human-annotated dataset and a distilled vision-language evaluator.
A kinematic-to-visual lifting paradigm combined with hierarchically routed control generates action-conditioned surgical videos with better faithfulness, fidelity, and efficiency.
Driver-WM is a driver-centric latent world model for causal rollout of in-cabin dynamics conditioned on out-cabin traffic, unifying kinematics forecasting with behavioral and emotional recognition via dual-stream architecture and gated injection.
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.
A single pixel-space diffusion model jointly performs 3D scene reconstruction and generation by supervising flow matching on rendered multi-view images, matching SOTA reconstruction and outperforming latent-space generation.
A new framework factorizes weather video synthesis into semantic appearance anchoring, physics-informed Gaussian particle simulation under gravity/wind/turbulence, and geometry-grounded alignment to produce diverse realistic weather effects.
Introduces BadDreamer, a backdoor attack that poisons the transition dynamics of video world models so that a trigger causes hallucination of obstacle-free futures, transferring to unsafe action predictions in autonomous driving.
U4D introduces an uncertainty-guided two-stage diffusion framework for 4D LiDAR scene synthesis that prioritizes high-entropy regions for geometry and uses a spatio-temporal block for consistency, reporting SOTA results on nuScenes and SemanticKITTI.
A unified text-conditioned diffusion model generates high-fidelity LiDAR scans across eight domains spanning weather, sensor, and platform shifts using cross-domain training and feature modeling.
GEM is a new LiDAR world model using deformable Mamba that disentangles dynamic and static features to generate high-fidelity simulations and achieve state-of-the-art results on autonomous driving benchmarks.
Embody4D generates novel-view videos from monocular robot videos via a 3D-aware synthesis pipeline, confidence-aware expert modulation, and interaction-aware attention for embodied 4D world modeling.
OneVL achieves superior accuracy to explicit chain-of-thought reasoning at answer-only latency by supervising latent tokens with a visual world model decoder that predicts future frames.
GaussianDWM uses 3D Gaussians with embedded linguistic features, language-guided sampling, and dual-condition generation for unified scene understanding and multi-modal output in driving world models.
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.
Synthesizing intermediate bridge views between sparse, non-overlapping urban cameras and jointly optimizing them stabilizes 4D reconstruction where dense-view methods collapse.
DynFlowDrive models action-conditioned scene transitions via rectified flow in latent space and adds stability-aware trajectory selection, showing gains on nuScenes and NavSim without added inference cost.
A sparse transformer predicts multi-frame 3D occupancy from images without BEV or VAE tokenization and reports SOTA results on nuScenes for 1-3s forecasting under arbitrary trajectories.
A survey proposing a three-level capability taxonomy (L1 Predictor, L2 Simulator, L3 Evolver) for world models across physical, digital, social, and scientific domains.
OpenWorldLib defines world models as perception-centered systems with interaction and long-term memory, and provides a modular inference codebase unifying interactive video, 3D, reasoning, and VLA tasks.
A survey of physical AI that distinguishes theoretical physics reasoning from applied understanding and synthesizes advances in symbolic reasoning, embodied systems, and generative models to advocate for physics-grounded world models.
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.
citing papers explorer
-
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
A survey proposing a three-level capability taxonomy (L1 Predictor, L2 Simulator, L3 Evolver) for world models across physical, digital, social, and scientific domains.
-
Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI
A survey of physical AI that distinguishes theoretical physics reasoning from applied understanding and synthesizes advances in symbolic reasoning, embodied systems, and generative models to advocate for physics-grounded world models.
-
A Tutorial on World Models and Physical AI
A tutorial that unifies explicit and implicit world models through shared predictive structure for applications in physical AI such as robotics.