CAST: Reconstruction-Coupled Acceleration of Interactive World Models

arXiv:2609.34144 · cs.CV · Submitted 2026-09-28 · Read on arXiv

cs.CV

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/lokiniuniu/CAST

Terminology

• Transformer — 21× in this paper · explained in 2 episodes
• Diffusion Model — 15× in this paper · explained in 8 episodes
• Diffusion Models — 13× in this paper · explained in 6 episodes
• Light Interaction — 13× in this paper
• World Model — 13× in this paper · explained in 7 episodes
• Sparsity — 9× in this paper · explained in 4 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Benchmark — 7× in this paper · explained in 2 episodes
• Phase-Aware Reconstruction — 7× in this paper
• Consistency — 6× in this paper · explained in 3 episodes
• Calibration — 4× in this paper · explained in 7 episodes
• Fidelity — 4× in this paper · explained in 2 episodes
• Quantization — 4× in this paper · explained in 12 episodes
• Sparse Attention — 4× in this paper · explained in 5 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Core — 3× in this paper · explained in 2 episodes
• Reconstruction Error — 3× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Distillation — 2× in this paper · explained in 2 episodes
• Provenance — 2× in this paper · explained in 4 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Decoupling — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Optical Flow — 1× in this paper · explained in 2 episodes

Sources

• Longformer: The Long-Document Transformer
• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
• WorldDynCache: Risk-Controlled Latent Dynamics Approximation for Diffusion World Model
• Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation
• Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models
• LongCat-Video Technical Report
• WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
• FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity
• Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
• FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing
• WorldMark: A Unified Benchmark Suite for Interactive Video World Models

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