MosaiChunk: Compositing Spatio-Temporal Memory for Autoregressive Video Generation

arXiv:2610.02153 · cs.CV, cs.GR · Submitted 2026-10-01 · Read on arXiv

cs.CV, cs.GR

Submitted: 2026-10-01

Updated: 2026-10-01

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

Terminology

• Consistency — 23× in this paper · explained in 3 episodes
• Benchmark — 18× in this paper · explained in 2 episodes
• Distillation — 12× in this paper · explained in 2 episodes
• Self-Distillation — 11× in this paper · explained in 7 episodes
• KV cache — 10× in this paper · explained in 3 episodes
• World Model — 6× in this paper · explained in 7 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Diffusion Model — 4× in this paper · explained in 8 episodes
• Diffusion Models — 4× in this paper · explained in 6 episodes
• Clustering — 3× in this paper · explained in 2 episodes
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Mixture of Contexts — 2× in this paper
• Quantization — 2× in this paper · explained in 12 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• GRPO — 1× in this paper · explained in 6 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Optical Flow — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Qwen2.5-VL Technical Report
• Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
• Past- and Future-Informed KV Cache Policy with Salience Estimation in Autoregressive Video Diffusion
• MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing
• Infinite Worlds with Versatile Interactions
• Can 4D Foundation Models Remember?
• RELIC: Interactive Video World Model with Long-Horizon Memory
• Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
• Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models
• PackCache: A Training-Free Acceleration Method for Unified Autoregressive Video Generation via Compact KV-Cache
• Sekai: A Video Dataset towards World Exploration
• Depth Anything 3: Recovering the Visual Space from Any Views
• RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO
• Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation
• $\pi^3$: Permutation-Equivariant Visual Geometry Learning
• Video World Models with Long-term Spatial Memory
• Addressable Memory for Video World Models
• Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
• WorldMem: Long-term Consistent World Simulation with Memory
• 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