GTA generates 3D worlds from single images via a two-stage video diffusion process that prioritizes geometry before appearance to improve structural consistency.
hub Canonical reference
3D and 4D world modeling: A survey
Canonical reference. 100% of citing Pith papers cite this work as background.
14
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 6
citation-polarity summary
roles
background 6polarities
background 6representative citing papers
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.
Proposes a levels x laws taxonomy for world models in AI agents, defining L1-L3 capabilities across physical, digital, social, and scientific regimes while reviewing over 400 works to outline a roadmap for advanced agentic modeling.
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 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.
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.
Stitch4D reconstructs coherent 4D urban scenes from sparse non-overlapping camera placements by synthesizing bridge views and enforcing inter-location spatio-temporal consistency.
Driver-WM rolls out in-cabin driver states in a compact latent space from frozen vision-language features, using traffic-conditioned dual streams and gated causal injection for long-horizon geometric and semantic forecasting.
Embody4D generates high-fidelity, view-consistent novel views from monocular videos for embodied scenarios via 3D-aware data synthesis, adaptive noise injection, and interaction-aware attention.
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.
OpenWorldLib offers a standardized codebase and definition for world models that combine perception, interaction, and memory to understand and predict the world.
citing papers explorer
-
GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video Diffusion
GTA generates 3D worlds from single images via a two-stage video diffusion process that prioritizes geometry before appearance to improve structural consistency.
-
Is Your Driving World Model an All-Around Player?
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.
-
From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation
A kinematic-to-visual lifting paradigm combined with hierarchically routed control generates action-conditioned surgical videos with better faithfulness, fidelity, and efficiency.
-
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
Proposes a levels x laws taxonomy for world models in AI agents, defining L1-L3 capabilities across physical, digital, social, and scientific regimes while reviewing over 400 works to outline a roadmap for advanced agentic modeling.
-
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.
-
OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation
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: Generating LiDAR World Model via Deformable Mamba
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.
-
Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
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.
-
Stitch4D: Sparse Multi-Location 4D Urban Reconstruction via Spatio-Temporal Interpolation
Stitch4D reconstructs coherent 4D urban scenes from sparse non-overlapping camera placements by synthesizing bridge views and enforcing inter-location spatio-temporal consistency.
-
Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout
Driver-WM rolls out in-cabin driver states in a compact latent space from frozen vision-language features, using traffic-conditioned dual streams and gated causal injection for long-horizon geometric and semantic forecasting.
-
Embody4D: A Generalist 4D World Model for Embodied AI
Embody4D generates high-fidelity, view-consistent novel views from monocular videos for embodied scenarios via 3D-aware data synthesis, adaptive noise injection, and interaction-aware attention.
-
DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving
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.
-
SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model
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.
-
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
OpenWorldLib offers a standardized codebase and definition for world models that combine perception, interaction, and memory to understand and predict the world.