Publications

Denoising diffusion models trained at web-scale have revolutionized image generation. The application of these tools to engineering design is an intriguing possibility, but is currently limited by their inability to parse and enforce concrete engineering constraints. In this paper, we take a step towards this goal by proposing physics-based guidance, which enables optimization of a performance metric (as predicted by a surrogate model) during the generation process. As a proof-of-concept, we add drag guidance to Stable Diffusion, which allows this tool to generate images of novel vehicles while simultaneously minimizing their predicted drag coefficients. READ MORE

Denoising is intuitively related to projection. Indeed, under the manifold hypothesis, adding random noise is approximately equivalent to orthogonal perturbation. Hence, learning to denoise is approximately learning to project. In this paper, we use this observation to interpret denoising diffusion models as approximate gradient descent applied to the Euclidean distance function. We then provide straight-forward convergence analysis of the DDIM sampler under simple assumptions on the projection error of the denoiser. Finally, we propose a new gradient-estimation sampler, generalizing DDIM using insights from our theoretical results. In as few as 5-10 function evaluations, our sampler achieves state-of-the-art FID scores on pretrained CIFAR-10 and CelebA models and can generate high quality samples on latent diffusion models. READ MORE

Denoising is intuitively related to projection. Indeed, under the manifold hypothesis, adding random noise is approximately equivalent to orthogonal perturbation. Hence, learning to denoise is approximately learning to project. In this paper, we use this observation to reinterpret denoising diffusion models as approximate gradient descent applied to the Euclidean distance function. We then provide straight-forward convergence analysis of the DDIM sampler under simple assumptions on the projection-error of the denoiser. Finally, we propose a new sampler based on two simple modifications to DDIM using insights from our theoretical results. In as few as 5-10 function evaluations, our sampler achieves state-of-the-art FID scores on pretrained CIFAR-10 and CelebA models and can generate high quality samples on latent diffusion models. READ MORE

Machine learning (ML) is gaining popularity as a tool for materials scientists to accelerate computation, automate data analysis, and predict materials properties. The representation of input material features is critical to the accuracy, interpretability, and generalizability of data-driven models for scientific research. In this Perspective, we discuss a few central challenges faced by ML practitioners in developing meaningful representations, including handling the complexity of real-world industry-relevant materials, combining theory and experimental data sources, and describing scientific phenomena across timescales and length scales. We present several promising directions for future research: devising representations of varied experimental conditions and observations, the need to find ways to integrate machine learning into laboratory practices, and making multi-scale informatics toolkits to bridge the gaps between atoms, materials, and devices. READ MORE

This paper introduces Diffusion Policy, a new way of generating robot behavior by representing a robot's visuomotor policy as a conditional denoising diffusion process. We benchmark Diffusion Policy across 12 different tasks from 4 different robot manipulation benchmarks and find that it consistently outperforms existing state-of-the-art robot learning methods with an average improvement of 46.9%. Diffusion Policy learns the gradient of the action-distribution score function and iteratively optimizes with respect to this gradient field during inference via a series of stochastic Langevin dynamics steps. We find that the diffusion formulation yields powerful advantages when used for robot policies, including gracefully handling multimodal action distributions, being suitable for high-dimensional action spaces, and exhibiting impressive training stability. To fully unlock the potential of diffusion models for visuomotor policy learning on physical robots, this paper presents a set of key technical contributions including the incorporation of receding horizon control, visual conditioning, and the time-series diffusion transformer. We hope this work will help motivate a new generation of policy learning techniques that are able to leverage the powerful generative modeling capabilities of diffusion models. Code, data, and training details will be publicly available. READ MORE

Generative AI models have made significant progress in automating the creation of 3D shapes, which has the potential to transform car design. In engineering design and optimization, evaluating engineering metrics is crucial. To make generative models performance-aware and enable them to create high-performing designs, surrogate modeling of these metrics is necessary. However, the currently used representations of three-dimensional (3D) shapes either require extensive computational resources to learn or suffer from significant information loss, which impairs their effectiveness in surrogate modeling. To address this issue, we propose a new two-dimensional (2D) representation of 3D shapes. We develop a surrogate drag model based on this representation to verify its effectiveness in predicting 3D car drag. We construct a diverse dataset of 9,070 high-quality 3D car meshes labeled by drag coefficients computed from computational fluid dynamics (CFD) simulations to train our model. Our experiments demonstrate that our model can accurately and efficiently evaluate drag coefficients with an R2 value above 0.84 for various car categories. Moreover, the proposed representation method can be generalized to many other product categories beyond cars. Our model is implemented using deep neural networks, making it compatible with recent AI image generation tools (such as Stable Diffusion) and a significant step towards the automatic generation of drag-optimized car designs. We have made the dataset and code publicly available at this https URL. READ MORE

A practical benefit of implicit visual representations like Neural Radiance Fields (NeRFs) is their memory efficiency: large scenes can be efficiently stored and shared as small neural nets instead of collections of images. However, operating on these implicit visual data structures requires extending classical image-based vision techniques (e.g., registration, blending) from image sets to neural fields. Towards this goal, we propose NeRFuser, a novel architecture for NeRF registration and blending that assumes only access to pre-generated NeRFs, and not the potentially large sets of images used to generate them. We propose registration from re-rendering, a technique to infer the transformation between NeRFs based on images synthesized from individual NeRFs. For blending, we propose sample-based inverse distance weighting to blend visual information at the ray-sample level. We evaluate NeRFuser on public benchmarks and a self-collected object-centric indoor dataset, showing the robustness of our method, including to views that are challenging to render from the individual source NeRFs. READ MORE

To reliably deploy lithium-ion batteries, a fundamental understanding of cycling and aging behavior is critical. Battery aging, however, consists of complex and highly coupled phenomena, making it challenging to develop a holistic interpretation. In this work, we generate a diverse battery cycling dataset with a broad range of degradation trajectories, consisting of 363 high energy density commercial Li(Ni,Co,Al)O$_2$/Graphite + SiO$_x$ cylindrical 21700 cells cycled under 218 unique cycling protocols. We consolidate aging via 16 mechanistic state-of-health (SOH) metrics, including cell-level performance metrics, electrode-specific capacities/state-of-charges (SOCs), and aging trajectory descriptors. Through the use of interpretable machine learning and explainable features, we deconvolute the underlying factors that contribute to battery degradation. This generalizable data-driven framework reveals the complex interplay between cycling conditions, degradation modes, and SOH, representing a holistic approach towards understanding battery aging. READ MORE

The burgeoning field of materials informatics necessitates a focus on educating the next generation of materials scientists in the concepts of data science, artificial intelligence (AI), and machine learning (ML). In addition to incorporating these topics in undergraduate and graduate curricula, regular hands-on workshops present the most effective medium to initiate researchers to informatics and have them start applying the best AI/ML tools to their own research. With the help of the Materials Research Society (MRS), members of the MRS AI Staging Committee, and a dedicated team of instructors, we successfully conducted workshops covering the essential concepts of AI/ML as applied to materials data, at both the Spring and Fall Meetings in 2022, with plans to make this a regular feature in future meetings. In this article, we discuss the importance of materials informatics education via the lens of these workshops, including details such as learning and implementing specific algorithms, the crucial nuts and bolts of ML, and using competitions to increase interest and participation. READ MORE

Exploratory synthesis has been the main generator of new inorganic materials for decades. However, our Edisonian and bias-prone processes of synthetic exploration alone are no longer sufficient in an age that demands rapid advances in materials development. In this work, we demonstrate one of the first end-to-end attempts towards systematic, computer-aided discovery and laboratory synthesis of inorganic crystalline compounds as a modern alternative to purely exploratory synthesis. Our approach initializes materials discovery campaigns by autonomously mapping the synthetic feasibility of a chemical system using density functional theory with AI feedback. Following expert-driven down-selection of newly generated phases, we use solid-state synthesis and in situ characterization via hot-stage X-ray diffraction in order to realize new ternary oxide phases experimentally. We applied this strategy in six ternary transition-metal oxide chemistries previously considered well-explored, one of which culminated in the discovery of two novel phases of calcium ruthenates. Detailed characterization using room temperature X-ray powder diffraction, 4D-STEM and SQUID measurements identify the structure, composition and confirm distinct properties, including distinct defect concentrations, of one of the new phases formed in our experimental campaigns. While the discovery of a new material guided by AI and DFT theory represents a milestone, our procedure and results also highlight a number of critical gaps in the process that can inform future efforts towards the improvement of AI-coupled methodologies, which are discussed. READ MORE