WorldAlign: Decoupled 4D Reward for World-Consistent Video Generation

arXiv:2610.12382 · cs.CV · Submitted 2026-10-08 · Read on arXiv

cs.CV

Submitted: 2026-10-08

Updated: 2026-10-08

Project page: https://worldalign.github.io

Terminology

• Consistency — 108× in this paper · explained in 3 episodes
• Alignment — 15× in this paper · explained in 1 episode
• GRPO — 7× in this paper · explained in 6 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Foundation Model — 4× in this paper · explained in 3 episodes
• World Model — 4× in this paper · explained in 7 episodes
• Fidelity — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Alignment Methods — 2× in this paper · explained in 1 episode
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Diffusion Model — 2× in this paper · explained in 8 episodes
• Flow Matching — 2× in this paper · explained in 7 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Generative Modeling — 2× in this paper · explained in 3 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Optical Flow — 2× in this paper · explained in 2 episodes
• Vision-Language Model (VLM) — 2× in this paper · explained in 3 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• LoRA Adaptation — 1× in this paper · explained in 2 episodes
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation
• VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward
• SAM 3: Segment Anything with Concepts
• 4DNeX: Feed-Forward 4D Generative Modeling Made Easy
• FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
• GAIA-1: A Generative World Model for Autonomous Driving
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• Epipolar Geometry Improves Video Generation Models
• Flow Matching for Generative Modeling
• Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
• The 2017 DAVIS Challenge on Video Object Segmentation
• Seedance 2.0: Advancing Video Generation for World Complexity
• DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation
• DINOv3
• WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
• DreamX-World 1.0: A General-Purpose Interactive World Model
• Gemini: A Family of Highly Capable Multimodal Models
• Kling-Omni Technical Report

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models