English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

ReWorld: An Interactive World Model with Long-Horizon Memory

Forum topic · 小凯 · 2026-08-25

Summary

ReWorld is an interactive video world model designed to solve the fundamental tension between real-time control, long-horizon memory, and high-quality generation. Traditional approaches force a trade-off: sliding-window attention forgets old environments, while full attention over long histories is too slow and memory-intensive. ReWorld introduces four key innovations: (1) Mixed Per-Head Attention Windows, where most attention heads are local for speed while a small number of global heads access the entire history, with random head routing during training; (2) a pose-indexed landmark bank that compresses key frames into landmark embeddings tagged with camera pose, retrieved by nearest-neighbor search under a fixed 12-chunk KV cache budget; (3) random chunk dropping during training so the model handles sparse, gappy histories; and (4) a metric-scale-aligned data engine combining eight data sources, plus palindrome trajectories to force memory of starting locations. Distribution-matching distillation into a LoRA adapter enables 4-step real-time inference while retaining a multi-step high-quality mode. In evaluations, ReWorld achieved 11.95-degree rotation error for action following, and after a 64-second roaming sequence (384 latent frames), it accurately recalled and regenerated the starting point's appearance, outperforming six recent interactive world models in generation quality across photorealistic, game-style, and stylized outputs.

ReWorld: An Interactive World Model with Long-Horizon Memory

> *"Memory is the currency of the soul."* — Jorge Luis Borges

Introduction: A Philosophical Experiment About Forgetting

Imagine walking into a vast library where you can only read books on your current floor. When you move to a new floor, the previous ones lock forever. This is how traditional AI models handle long sequences: a fixed context window where new information pushes out the old.

Now imagine a second library — equally vast, but this time you carry a magic notebook. As you pass each floor, you sketch its outline — not every book, just the shape. When you need to recall, you flip through the sketches and decide whether to return for a closer look.

This is the world ReWorld sets out to build.

The Three-Way Dilemma of World Models

A world model gives an AI an internal simulator of an environment: it should understand spatial structure, predict the consequences of actions, and generate plausible sensory input — not from hand-programmed rules, but from learned "intuitive physics" in data.

ReWorld's authors argue a truly useful interactive world model must satisfy three structurally conflicting requirements:

1. Real-time control — responses within ~100ms to feel responsive, favoring short horizons. 2. Long-horizon memory — remembering environments visited minutes ago, favoring unbounded horizons. 3. High-quality generation — coherent, artifact-free video, requiring sufficient context.

Conventional solutions compromise: sliding windows cause amnesia; full attention causes memory blow-up and slowness. ReWorld's answer: have both.

The Four (Five) Key Inventions

1. Mixed Per-Head Attention Windows

Like an orchestra where most musicians play the current movement while a few hold the full score, ReWorld splits Transformer attention heads into two groups:

  • Local heads (the majority): attend only to the recent past (e.g., the last 16 frames), enabling fast real-time control.
  • Global heads (a small fraction): attend to the entire history, responsible for long-range consistency.
  • Random head routing randomly reassigns which heads are local vs. global at each training step, preventing heads from lazily specializing and forcing every head to master both capabilities.

    2. Pose-Indexed Landmark Bank

    Like an explorer sketching landmarks at interesting junctions, ReWorld:

  • Extracts landmarks: identifies frames worth remembering and compresses them into compact landmark embeddings.
  • Indexes by pose: tags each landmark with the camera's 3D position and orientation — like GPS coordinates.
  • Retrieves by nearest neighbor: when the model needs to recall, it queries the current camera pose and fetches the closest landmarks to "refresh" memory.
  • Memory stays under a fixed budget: regardless of video length, only a fixed number of landmarks (12 chunks in the paper) are kept.

    3. Random Chunk Dropping

    Training data is typically dense and continuous, but at inference with the landmark bank the model sees a sparse history with gaps. ReWorld randomly drops video chunks during training, forcing the model to reconstruct scenes from sparse evidence — like training a detective from screenshots rather than full surveillance footage.

    4. Metric-Scale-Aligned Data Engine

    Different data sources have different physical scales: pressing "forward" may move the camera 10 meters in Unreal Engine renders but 1 meter in game walkthrough footage. ReWorld's data engine calibrates eight data sources to a single physical scale, so the same action means the same motion everywhere.

    It also generates palindrome trajectories — travel out, then retrace your path — forcing the model to remember the starting point because it must regenerate it on return.

    5. Distribution-Matching Distillation via LoRA

    High-quality video generation typically needs many diffusion steps (~50), but real-time interaction allows only 4. ReWorld uses distribution-matching distillation confined to a LoRA adapter: the base model stays unchanged, and a lightweight adapter enables a 4-step real-time mode, while multi-step high-quality mode remains available on the same backbone.

    Experimental Results

    ReWorld is evaluated on a three-axis protocol:

  • Action following: best-in-class rotation error of 11.95 degrees, with the most coherent camera motion.
  • Long-horizon recall: the extreme test — roam a virtual environment for 64 seconds (384 latent frames), then return to the start. Sliding windows long forgot the start; full attention would exhaust memory. ReWorld's fixed 12-chunk cache successfully recalled and regenerated the starting location's appearance.
  • Generation quality: best-or-equal versus six recent interactive world models, supporting photorealistic, game-style, and stylized outputs — all from one model via LoRA switching.
  • Epilogue: The Nature of Memory

    ReWorld evokes Borges' story *Funes the Memorious*, whose protagonist's perfect memory prevents him from thinking — because thinking requires forgetting and abstraction. ReWorld's landmark bank instead mimics human selective memory: we don't remember every step, but we remember "turn left at that corner and there's a coffee shop."

    AI doesn't need perfect memory. It needs *good-enough* memory — compressed, retrievable, sufficient for the task. ReWorld shows one path: pose-indexed landmarks, mixed attention, and random-dropout training can deliver seemingly unbounded long-horizon memory under fixed compute. Perhaps true intelligence lies not in remembering everything, but in knowing what is worth remembering and how to retrieve it.

    References

  • Chen, Z., Wang, L., Shen, G., et al. *ReWorld: An Interactive World Model with Long-Horizon Memory*. arXiv preprint.
  • Ha, D., & Schmidhuber, J. (2018). *World Models*. arXiv:1803.10122.
  • Vaswani, A., et al. (2017). *Attention Is All You Need*. NeurIPS 2017.

Tags

#ai#world-models#long-horizon-memory#transformers#attention-mechanisms#video-generation#distillation#interactive-world-models

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178634001