Rollback-Free Stable Brick Structures Generation

• URL: http://arxiv.org/abs/2605.06947v1
• Date: Thu, 07 May 2026 21:06:44 GMT
• Title: Rollback-Free Stable Brick Structures Generation
• Abstract summary: Existing approaches rely on external physical simulators during inference to perform rejection sampling and brick-by-brick rollbacks.<n>We propose a reinforcement learning paradigm that shifts physical validity enforcement from test-time correction to training-time policy optimization.<n> Experimental results demonstrate that our approach achieves state-of-the-art generation quality while accelerating inference speed by orders of magnitude.
• Score: 51.856925926010184
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents [37.91666123749406]
  Co-Harness is a framework that jointly optimize the agent harness and model parameters during post-training.<n>An autonomous case study shows that Co-Harness can recover from system crashes, improve inference efficiency, and discover ensemble strategies without human intervention.
  arXiv  Detail & Related papers  (2026-07-17T02:39:57Z)
• Sample-Efficient Post-Training for LEGO Spatial-Physics Reasoning [17.416391606380827]
  LLM-based LEGO assembly generation requires both semantic grounding and physical feasibility.<n>We propose a model-based data selection approach that uses only a small fraction of the training data.<n>We introduce PVPO, a sample-efficient reinforcement learning method that couples physical feasibility with voxel-space geometric rewards.
  arXiv  Detail & Related papers  (2026-05-29T09:31:25Z)
• Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation [81.44955493339835]
  DeGO is a deformable Gaussian occupancy framework that unifies decoupled Gaussian deformation with factorized 4D foundation-model distillation.<n> Experiments on the Occ3D-NuScenes benchmark demonstrate that our method achieves state-of-the-art performance under weak supervision.
  arXiv  Detail & Related papers  (2026-05-27T15:09:55Z)
• PhyCo: Learning Controllable Physical Priors for Generative Motion [55.59209981836171]
  We present PhyCo, a framework that introduces continuous, interpretable, and physically grounded control into video generation.<n>Our approach integrates three key components: (i) a large-scale dataset of over 100K photorealistic simulation videos where friction, restitution, deformation, and force are systematically varied across diverse scenarios; (ii) physics-supervised fine-tuning of a pretrained diffusion model using a ControlNet conditioned on pixel-aligned physical property maps; and (iii) VLM-guided reward optimization, where a fine-tuned vision-language model evaluates generated videos with targeted physics queries and provides differentiable feedback.
  arXiv  Detail & Related papers  (2026-04-30T17:53:03Z)
• From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons [74.25767873168745]
  Diffusion models promise efficient parallel text generation but rely on bidirectional attention, creating a structural mismatch with pre-trained Autoregressive (AR) models.<n>We propose FLUID, a framework that efficiently adapts AR backbones to the diffusion paradigm.<n> Experiments demonstrate that FLUID achieves state-of-the-art performance while reducing training costs by orders of magnitude.
  arXiv  Detail & Related papers  (2026-04-11T13:18:27Z)
• PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models [100.65199317765608]
  Physical principles are fundamental to realistic visual simulation, but remain a significant oversight in transformer-based video generation.<n>We introduce a physics-aware reinforcement learning paradigm for video generation models that enforces physical collision rules directly in high-dimensional spaces.<n>We extend this paradigm to a unified framework, termed Mimicry-Discovery Cycle (MDcycle), which allows substantial fine-tuning.
  arXiv  Detail & Related papers  (2026-01-16T08:40:10Z)
• LEGATO: Good Identity Unlearning Is Continuous [30.78585550012454]
  LEGATO is a machine unlearning method for learning to forget identity of generative models.<n>It achieves state-of-the-art forgetting performance, avoids catastrophic collapse and reduces fine-tuned parameters.<n>Our experiments show that LEGATO achieves state-of-the-art forgetting performance, avoids catastrophic collapse and reduces fine-tuned parameters.
  arXiv  Detail & Related papers  (2026-01-07T13:15:25Z)
• Model-Less Feedback Control of Space-based Continuum Manipulators using Backbone Tension Optimization [0.0]
  Continuum manipulators offer dexterity and safe compliance for navigation within confined and obstacle-rich environments.<n>Their infinite-dimensional backbone deformation, unmodeled internal friction, and configuration-dependent stiffness limit the reliability of model-based kinematic formulations.<n>This work presents a complete model-less control framework that bypasses kinematic modeling by using an empirically intrinsic Jacobian refined online through differential convex updates.
  arXiv  Detail & Related papers  (2025-12-07T09:34:28Z)
• Dynamic Manipulation of Deformable Objects in 3D: Simulation, Benchmark and Learning Strategy [88.8665000676562]
  Prior methods often simplify the problem to low-speed or 2D settings, limiting their applicability to real-world 3D tasks.<n>To mitigate data scarcity, we introduce a novel simulation framework and benchmark grounded in reduced-order dynamics.<n>We propose Dynamics Informed Diffusion Policy (DIDP), a framework that integrates imitation pretraining with physics-informed test-time adaptation.
  arXiv  Detail & Related papers  (2025-05-23T03:28:25Z)
• Neural Internal Model Control: Learning a Robust Control Policy via Predictive Error Feedback [16.46487826869775]
  We propose a novel framework, Neural Internal Model Control, which integrates model-based control with RL-based control to enhance robustness.<n>Our framework streamlines the predictive model by applying Newton-Euler equations for rigid-body dynamics, eliminating the need to capture complex high-dimensional nonlinearities.<n>We demonstrate the effectiveness of our framework on both quadrotors and quadrupedal robots, achieving superior performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-11-20T07:07:42Z)
• Learn from the Past: A Proxy Guided Adversarial Defense Framework with Self Distillation Regularization [53.04697800214848]
  Adversarial Training (AT) is pivotal in fortifying the robustness of deep learning models. AT methods, relying on direct iterative updates for target model's defense, frequently encounter obstacles such as unstable training and catastrophic overfitting. We present a general proxy guided defense framework, LAST' (bf Learn from the Pbf ast)
  arXiv  Detail & Related papers  (2023-10-19T13:13:41Z)
• Benchmarking Model Predictive Control Algorithms in Building Optimization Testing Framework (BOPTEST) [40.17692290400862]
  We present a data-driven modeling and control framework for physics-based building emulators. Our approach consists of: (a) Offline training of differentiable surrogate models that accelerate model evaluations, provide cost-effective gradients, and maintain good predictive accuracy for the receding horizon in Model Predictive Control (MPC) We extensively evaluate the modeling and control performance using multiple surrogate models and optimization frameworks across various test cases available in the Building Optimization Testing Framework (BOPTEST)
  arXiv  Detail & Related papers  (2023-01-31T06:55:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.