paper-with-me

Papers

Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation

2023-05-29 · NeurIPS 2023 11

Generative models have had a profound impact on vision and language, paving the way for a new era of multimodal generative applications. While these successes have inspired researchers to explore using generative models in science and engineering to accelerate the design process and reduce the reliance on iterative optimization, challenges remain. Specifically, engineering optimization methods based on physics still outperform generative models when dealing with constrained environments where data is scarce and precision is paramount. To address these challenges, we introduce Diffusion Optimization Models (DOM) and Trajectory Alignment (TA), a learning framework that demonstrates the efficacy of aligning the sampling trajectory of diffusion models with the optimization trajectory derived from traditional physics-based methods. This alignment ensures that the sampling process remains grounded in the underlying physical principles. Our method allows for generating feasible and high-performance designs in as few as two steps without the need for expensive preprocessing, external surrogate models, or additional labeled data. We apply our framework to structural topology optimization, a fundamental problem in mechanical design, evaluating its performance on in- and out-of-distribution configurations. Our results demonstrate that TA outperforms state-of-the-art deep generative models on in-distribution configurations and halves the inference computational cost. When coupled with a few steps of optimization, it also improves manufacturability for out-of-distribution conditions. By significantly improving performance and inference efficiency, DOM enables us to generate high-quality designs in just a few steps and guide them toward regions of high performance and manufacturability, paving the way for the widespread application of generative models in large-scale data-driven design.

📄 PDF Abstract BibTeX arXiv:2305.18470

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples

2025-05-28 · Zijing Hu, Fengda Zhang, Kun Kuang

The practical applications of diffusion models have been limited by the misalignment between generated images and corresponding text prompts. Recent studies have introduced direct preference optimization (DPO) to enhance…

Denoising

Explicit Critic Guidance for Aligning Diffusion Models

2026-05-26 · Zhengyang Liang, Qihang Zhang, Ceyuan Yang arxiv

Online reinforcement learning is becoming increasingly important for aligning diffusion models with non-differentiable objectives. However, existing methods still face limitations in assigning fine-grained credit along d…

Reinforcement Learning

Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF

2026-07-08 · Eric Zhu, Abhinav Shrivastava, Soumik Mukhopadhyay arxiv

Reinforcement learning from human feedback (RLHF) has emerged as a powerful paradigm for aligning generative models with human preferences. However, applying RLHF to diffusion models remains highly feedback inefficient, …

Reinforcement Learning

Model-Based Diffusion Sampling for Predictive Control in Offline Decision Making

2025-12-09 · Haldun Balim, Na Li, Yilun Du arxiv

Offline decision-making via diffusion models often produces trajectories that are misaligned with system dynamics, limiting their reliability for control. We propose Model Predictive Diffuser (MPDiffuser), a compositiona…

Decision Making

Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models

2026-06-07 · Yawen Shao, Jie Xiao, Kai Zhu, Yu Liu 외 arxiv

Reinforcement learning (RL) holds immense promise for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, progress is fundamentally constrained by a dual misalignment between authent…

Reinforcement Learning