# Rollback-Free Stable Brick Structures Generation

arXiv: https://arxiv.org/abs/2605.06947 · HTML: https://mlsanity.com/paper/2605.06947/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 24 of 24)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Neural 3D Mesh Renderer](https://mlsanity.com/paper/1711.07566/) (2017)
- [OctNet: Learning Deep 3D Representations at High Resolutions](https://mlsanity.com/paper/1611.05009/) (2016)
- [PolyGen: An Autoregressive Generative Model of 3D Meshes](https://mlsanity.com/paper/2002.10880/) (2020)
- [3DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations](https://mlsanity.com/paper/2108.12958/) (2021)
- [StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions](https://mlsanity.com/paper/2112.01530/) (2021)
- [ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Model](https://mlsanity.com/paper/2311.17618/) (2023)
- [Autoregressive 3D Shape Generation via Canonical Mapping](https://mlsanity.com/paper/2204.01955/) (2022)
- [Generating Physically Stable and Buildable Brick Structures from Text](https://mlsanity.com/paper/2505.05469/) (2025)
- [Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning](https://mlsanity.com/paper/2110.15481/) (2021)
- [Planning Assembly Sequence with Graph Transformer](https://mlsanity.com/paper/2210.05236/) (2022)
- [StableLego: Stability Analysis of Block Stacking Assembly](https://mlsanity.com/paper/2402.10711/) (2024)
- [BrickSim: A Physics-Based Simulator for Manipulating Interlocking Brick Assemblies](https://mlsanity.com/paper/2603.16853/) (2026)
- [AssemblyComplete: 3D Combinatorial Construction with Deep Reinforcement Learning](https://mlsanity.com/paper/2410.15469/) (2024)

## Built on by (most cited first, 2 of 2)

- [ResemBrick: Brick Reconstruction from Photographs with Perceptual Fidelity and Buildability](https://mlsanity.com/paper/2608.09597/) (2026)
- [ScaffoldM3C: A Multimodal Sequential Monte Carlo Framework for Generative Stable Construction Planning](https://mlsanity.com/paper/2610.00487/) (2026)

## Abstract (arXiv)

While autoregressive models have advanced 3D generation, creating physically stable brick structures remains a challenge due to the strict requirements of gravity and interconnectivity. Existing approaches rely on external physical simulators during inference to perform rejection sampling and brick-by-brick rollbacks, which severely bottlenecks efficiency. To address this, we propose a reinforcement learning paradigm that shifts physical validity enforcement from test-time correction to training-time policy optimization. By utilizing assembly-level rewards, the model optimizes for collision avoidance, global connectivity, structural interlocking, and shape conformity. This paradigm allows the model to internalize physical priors, enabling the first rollback-free generation of stable brick structures. Experimental results demonstrate that our approach achieves state-of-the-art generation quality while accelerating inference speed by orders of magnitude. Our code and dataset are available at https://github.com/miniHuiHui/STABLE. Our models are available at https://huggingface.co/miniHui/STABLE.