DyMD: Preserving Interaction Dynamics through Distribution Matching Distillation in Few-Step Video World Models

arXiv:2609.31349 · cs.CV, cs.AI · Submitted 2026-09-25 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• Distillation — 21× in this paper · explained in 2 episodes
• Fidelity — 15× in this paper · explained in 2 episodes
• Distribution Matching — 14× in this paper · explained in 2 episodes
• Consistency — 13× in this paper · explained in 3 episodes
• World Model — 10× in this paper · explained in 7 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Distribution Matching Distillation — 8× in this paper
• Ablation — 4× in this paper · explained in 1 episode
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Flow Matching — 3× in this paper · explained in 8 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Active Learning — 1× in this paper · explained in 6 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Adaptive Sampling — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Copula — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Fisher Information — 1× in this paper · explained in 3 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• International Conference on Computer Vision — 1× in this paper
• Latent Dynamics — 1× in this paper · explained in 2 episodes
• Pseudo-labeling — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Selection Bias — 1× in this paper · explained in 4 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Optimizing Few-Step Generation with Adaptive Matching Distillation
• VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models
• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment
• Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations
• Reinforcing Few-step Generators via Reward-Tilted Distribution Matching
• DreamGen: Unlocking Generalization in Robot Learning through Video World Models
• Distribution Matching Distillation Meets Reinforcement Learning
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• Flow Matching for Generative Modeling
• Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
• Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
• V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
• Cosmos World Foundation Model Platform for Physical AI
• DINOv2: Learning Robust Visual Features without Supervision
• WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models
• Wan: Open and Advanced Large-Scale Video Generative Models
• Generative Video Compression with Adaptive Score Distillation
• PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation
• CoDMD: Copula-aware Distribution Matching Distillation for Fast Video Generation

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