Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

Hugging Face Paper Unveils RCWM: Recursive Code World Models for 3D Scene Reconstruction

AI By Crimson AI Hugging Face Papers 11 September 2026 · 00:00 29 views
Share: X Telegram

A new research paper introduces Recursive Code World Models (RCWM), a framework that reconstructs complex 3D worlds as executable code from a single reference image using recursive global-local-global construction and shared camera alignment.

Hugging Face Paper Unveils RCWM: Recursive Code World Models for 3D Scene Reconstruction

Key points

Researchers have introduced Recursive Code World Models (RCWM), a framework for reconstructing complex 3D worlds in code from a single reference image. The work addresses a limitation of existing code world models: representing a world as an executable program does not by itself specify how to construct a complex world.

RCWM pairs a Recursive Scene Program (RSP) representation with a construction solver that recursively calls itself. An RSP encodes the executable world as compositional scene code, while each solver call follows the same complete process: establish the whole, recursively reconstruct unresolved parts, and revisit the whole to refine their composition.

This global-local-global recursion gives fine-scale structures their own perception-and-editing loops while preserving scene-wide geometry and relationships. Reference-aligned views propagate a shared camera projection across levels, and parent revisitation addresses boundaries, spatial relations, and shared errors that emerge after local refinement.

A vision-language coding agent directly compares reference images with scene renders to guide refinement, recursive descent, and return. According to the paper, RCWM outperforms prior code-based image-to-scene reconstruction methods across complex scenes. Ablation studies support the benefits of recursive construction and suggest that deeper calls can improve finer-scale reconstruction.

The authors position RCWM as a recursive construction principle for building complex executable worlds from visual evidence.

Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 15 Oct 2026

New Survey Maps How Multimodal AI Agents Remember and Evolve

A Hugging Face survey proposes a two-axis framework for multimodal agent memory, separating how information is formed and represen...

6
Research paper
Hugging Face 15 Oct 2026

CriticOPD Fixes On-Policy Distillation by Letting Teachers Critique Student Errors

Hugging Face researchers introduce CriticOPD, a method that restores the teacher's ability to recover from student mistakes during...

7
Research paper
Hugging Face 15 Oct 2026

ActionOPD: Distilling Agent Decisions, Not Tokens

A new Hugging Face paper proposes ActionOPD, an action-level on-policy distillation method that aligns a student agent's decisions...

8