The Design Computation and Digital Engineering (DeCoDE) Lab at MIT Mechanical Engineering advances the science of AI-driven design. We envision a future where humans and AI design together to tackle the world's most pressing challenges. To realize this vision, we build engineering-native AI — models, datasets, and solvers that work the way engineering actually works, through CAD, geometry, simulation, and optimization, under real physical and manufacturing constraints — to enhance the design of complex systems and support human teams in creating better products.
Our goal is to build versatile approaches that automate and augment engineering design across scales, levels of complexity, and disciplines, framing design problems as generalizable machine learning and optimization tasks. Much of our current research is organized around three pillars of engineering-native AI: workflow-native models and agents that operate directly on CAD programs, geometry, and topology; transferable foundation-model priors that keep prediction and optimization reliable when data are scarce and evaluations expensive; and open infrastructure — large datasets, objective-aware benchmarks, and fast solvers — that helps the whole field explore, evaluate, and generate solutions cumulatively. Together, these threads build toward our long-term goal: a General Artificial Designer — a dependable AI collaborator for engineering.
September 2026
Ghadi Nehme and Dr. Ahmed's paper "StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search" was accepted to NeurIPS 2026. In addition, a collaborative paper on failure-driven inference-time scaling, led by DeCoDE alumnus Giorgio Giannone and colleagues at Red Hat and IBM, was also accepted.
September 2026
Dr. Ahmed was named a recipient of IIT Kanpur's 2026 Young Alumni Award.
September 2026
DeCoDE Lab welcomed several new members this fall and celebrated the start of the semester with a kayaking outing.
August 2026
Kristen Edwards successfully defended her Ph.D. thesis, "Multimodal Artificial Intelligence for Design Exploration and Evaluation at Scale." Congratulations, Dr. Edwards!
August 2026
The lab had a great IDETC-CIE 2026 in Houston, presenting three papers and seven additional talks. Our FLARE paper with GE Vernova received both the CIE Best Conference Paper Award and the AI/ML Technical Committee Best Paper Award. We also concluded a successful fourth "From Data to Design" workshop and a student hackathon with nTop and MIT Lincoln Laboratory.
July 2026
Dr. Ahmed received the Air Force Office of Scientific Research (AFOSR) Young Investigator Program award (selected in 2025, with the grant effective 2026).
July 2026
Dr. Ahmed was appointed to the Esther and Harold E. Edgerton Career Development Professorship at MIT.
July 2026
The lab presented four papers at ICML 2026, with FIRE selected as a Spotlight (top 2.2% of submissions). Earlier in April, GIT-BO was presented at ICLR 2026.
July 2026
Congratulations to Ghadi Nehme on receiving the GE Vernova Fellowship and to Rosen Yu on receiving the MathWorks Fellowship!
CIE Best Conference Paper & AI/ML TC Best Paper, IDETC 2026
In IDETC 2026 (Accepted)
Directed energy deposition (DED) produces complex thermo-mechanical responses that can lead to distortion and reduced dimensional accuracy of a manufactured part. Thermo-mechanical finite element simulations are widely used to estimate these effects, but their computational cost and the complexity of accurately capturing DED physics limit their use in design iteration and process optimization. This paper introduces FLARE (Field Prediction via Linear Affine Reconstruction in wEight-space), a data-efficient surrogate modeling framework for predicting post-cooling displacement fields in DED from geometric and process parameters. We develop a predefined-geometry DED simulation workflow using an open-source finite element framework and generate a dataset of simulations with varying geometry, laser power, and deposition velocity. Each simulation provides full-field displacement, stress, strain, and temperature data throughout the manufacturing process. FLARE encodes each simulation as an implicit neural field and regularizes the corresponding neural-network weights so that they follow the affine structure of the input parameter space. This enables prediction of unseen parameter combinations by reconstructing network weights through affine mixing of training examples. On this DED benchmark, the method shows improved accuracy compared to baseline methods in both in-distribution and extrapolation settings. Although the present study focuses on DED displacement prediction, the proposed affine weight-space reconstruction framework offers a promising approach for data-efficient surrogate modeling of physical fields.
In Structural and Multidisciplinary Optimization (in press)
Projected Gradient Descent (PGD) methods offer a simple and scalable approach to topology optimization (TO), yet they often struggle with nonlinear and multi-constraint problems due to the complexity of active-set detection. This paper introduces PGD-TO, a framework that reformulates the projection step into a regularized convex quadratic problem, eliminating the need for active-set search and ensuring well-posedness even when constraints are infeasible. The framework employs a semismooth Newton solver for general multi-constraint cases and a binary search projection for single or independent constraints, achieving fast and reliable convergence. It further integrates spectral step-size adaptation and nonlinear conjugate-gradient directions for improved stability and efficiency. We evaluate PGD-TO on four benchmark families representing the breadth of TO problems: (i) minimum compliance with a linear volume constraint, (ii) minimum volume under a nonlinear compliance constraint, (iii) multi-material minimum compliance with four independent volume constraints, and (iv) minimum compliance with coupled volume and center-of-mass constraints. Across these single- and multi-constraint, linear and nonlinear cases, PGD-TO achieves convergence and final compliance comparable to the Method of Moving Asymptotes (MMA) and Optimality Criteria (OC), while reducing per-iteration computation time by 10–43x on general problems and 115–312x when constraints are independent. Overall, PGD-TO establishes a fast, robust, and scalable alternative to MMA, advancing topology optimization toward practical large-scale, multi-constraint, and nonlinear design problems. Public code available at: https://github.com/ahnobari/pyFANTOM.
In Journal of Mechanical Design 2026
The subjective evaluation of early-stage engineering designs, such as concept sketches, traditionally relies on human experts. However, expert evaluations are time-consuming, expensive, and sometimes inconsistent. Recent advances in vision-language models (VLMs) offer the potential to automate design assessments, but it is crucial to ensure that these artificial intelligence (AI) “judges” perform on par with human experts. This work introduces in-context learning (ICL)-enhanced VLM judges and a comprehensive statistical framework (including agreement, error, correlation, statistical difference checks, equivalence testing, and top-set overlap) to rigorously assess AI–expert equivalence. Across two case studies, we show that reasoning-enabled VLMs are the strongest-performing AI judges. They consistently outperform two-third trained novices across all metrics, and for measures such as uniqueness, creativity, and drawing quality, they approach expert-equivalent performance. In specific cases, they even exceed expert–expert agreement, attaining lower mean absolute error and higher rank correlations than the expert baseline. These findings suggest that, on certain statistical tests, AI judges are not only approaching expert–expert equivalence but in some cases surpassing it.
In ICML 2026
Despite recent progress, recovering parametric CAD construction sequences from geometric input, such as meshes or point clouds, is a key challenge for design and manufacturing, as existing CAD reconstruction and generation methods are largely restricted to difficult-to-edit formats like meshes or Breps or editable simple sketch-and-extrude pipelines and low-complexity datasets. We introduce CADFit, a hybrid optimization-based CAD reconstruction framework that recovers complex, editable CAD construction sequences from meshes by incrementally fitting and validating parametric operations using geometric feedback. Our approach is distinguished by formulating reconstruction as an IoU-driven optimization over structured CAD programs and supporting a rich set of operations, including extrusions, revolutions, fillets, and chamfers. Experiments on multiple CAD benchmarks show that CADFit outperforms state-of-the-art mesh-to-CAD methods in volumetric Intersection-over-Union and Chamfer Distance, while substantially reducing the Invalid Ratio of reconstructed CAD programs, particularly for complex designs. We further present a multimodal pipeline that enables end-to-end reconstruction of CAD construction sequences from images by combining image-based geometry reconstruction with CADFit. By enabling accurate reconstruction of higher-complexity CAD models, CADFit provides a practical foundation for generating richer datasets and advancing future learning-based approaches to CAD reverse engineering. The code is available at: https://github.com/ghadinehme/CADFit
Spotlight Paper: Top 2.2% of 23,918 Submissions
In ICML 2026
Multi-fidelity (MF) regression often operates in regimes of extreme data imbalance, where the commonly-used Gaussian-process (GP) surrogates struggle with cubic scaling costs and overfit to sparse high-fidelity observations, limiting efficiency and generalization in real-world applications. We introduce FIRE, a training-free MF framework that couples tabular foundation models (TFMs) to perform zero-shot in-context Bayesian inference via a high-fidelity correction model conditioned on the low-fidelity model's posterior predictive distributions. This cross-fidelity information transfer via distributional summaries captures heteroscedastic errors, enabling robust residual learning without model retraining. Across 31 benchmark problems spanning synthetic and real-world tasks (e.g., DrivAerNet, LCBench), FIRE delivers a stronger performance-time trade-off than seven state-of-the-art GP-based or deep learning MF regression methods, ranking highest in accuracy and uncertainty quantification with runtime advantages. Limitations include context window constraints and dependence on the quality of the pre-trained TFM's.
In ICLR 2026
Bayesian optimization (BO) struggles in high dimensions, where Gaussian-process surrogates demand heavy retraining and brittle assumptions, slowing progress on real engineering and design problems. We introduce GIT-BO, a Gradient-Informed BO framework that couples TabPFN v2, a tabular foundation model (TFM) that performs zero-shot Bayesian inference in context, with an active-subspace mechanism computed from the model's own predictive-mean gradients. This aligns exploration to an intrinsic low-dimensional subspace via a Fisher-information estimate and selects queries with a UCB acquisition, requiring no online retraining. Across 60 problem variants spanning 20 benchmarks — nine scalable synthetic families and eleven real-world tasks (e.g., power systems, Rover, MOPTA08, Mazda) — up to 500 dimensions, GIT-BO delivers a better performance-time trade-off than state-of-the-art GP-based methods (SAASBO, TuRBO, Vanilla BO, BAxUS), ranking highest in performance and with runtime advantages that grow with dimensionality. Limitations include memory footprint and dependence on the capacity of the underlying TFM.
MIT Initiative for New Manufacturing
This work examines how AI, especially agentic systems, is being adopted in engineering and manufacturing workflows, what value it provides today, and what is needed for broader deployment. This is an exploratory and qualitative state-of-practice study grounded in over 30 interviews across four stakeholder groups (large enterprises, small/medium firms, AI developers, and CAD/CAM/CAE vendors). We find that near-term AI gains cluster around structured, repetitive work and data-intensive synthesis, while higher-value agentic gains come from orchestrating multi-step workflows across tools. Adoption is constrained less by model capability than by fragmented and machine-unfriendly data, stringent security and regulatory requirements, and limited API-accessible legacy toolchains. Reliability, verification, and auditability are central requirements for adoption, driving human-in-the-loop frameworks and governance aligned with existing engineering reviews. Beyond technical barriers there are also organizational ones: a persistent AI literacy gap, cultural heterogeneity, and governance structures that have not yet caught up with agentic capabilities. Together, the findings point to a staged progression of AI utility from low-consequence assistance toward higher-order automation, as trust, infrastructure, and verification mature. This highlights key breakthroughs needed, including integration with traditional engineering tools and data types, robust verification frameworks, and improved spatial and physical reasoning.
In NeurIPS 2025
Structural topology optimization (TO) is central to engineering design but remains computationally intensive due to complex physics and hard constraints. Existing deep-learning methods are limited to fixed square grids, a few hand-coded boundary conditions, and post-hoc optimization, preventing general deployment. We introduce Optimize Any Topology (OAT), a foundation-model framework that directly predicts minimum-compliance layouts for arbitrary aspect ratios, resolutions, volume fractions, loads, and fixtures. OAT combines a resolution- and shape-agnostic autoencoder with an implicit neural-field decoder and a conditional latent-diffusion model trained on OpenTO, a new corpus of 2.2 million optimized structures covering 2 million unique boundary-condition configurations. On four public benchmarks and two challenging unseen tests, OAT lowers mean compliance up to 90% relative to the best prior models and delivers sub-1 second inference on a single GPU across resolutions from 64 x 64 to 256 x 256 and aspect ratios as high as 10:1. These results establish OAT as a general, fast, and resolution-free framework for physics-aware topology optimization and provide a large-scale dataset to spur further research in generative modeling for inverse design.
In Applied Energy 2025
Offshore wind energy leverages the high intensity and consistency of oceanic winds, playing a key role in the transition to renewable energy. As energy demands grow, larger turbines are required to optimize power generation and reduce the Levelized Cost of Energy (LCoE), which represents the average cost of electricity over a project’s lifetime. However, upscaling turbines introduces engineering challenges, particularly in the design of supporting structures, especially towers. These towers must support increased loads while maintaining structural integrity, cost-efficiency, and transportability, making them essential to offshore wind projects’ success. This paper presents a comprehensive review of the latest advancements, challenges, and future directions driven by Artificial Intelligence (AI) in the design optimization of Offshore Wind Turbine (OWT) structures, with a focus on towers. It provides an in-depth background on key areas such as design types, load types, analysis methods, design processes, monitoring systems, Digital Twin (DT), software, standards, reference turbines, economic factors, and optimization techniques. Additionally, it includes a state-of-the-art review of optimization studies related to tower design optimization, presenting a detailed examination of turbine, software, loads, optimization method, design variables and constraints, analysis, and findings, motivating future research to refine design approaches for effective turbine upscaling and improved efficiency. Lastly, the paper explores future directions where AI can revolutionize tower design optimization, enabling the development of efficient, scalable, and sustainable structures. By addressing the upscaling challenges and supporting the growth of renewable energy, this work contributes to shaping the future of offshore wind turbine towers and others supporting structures.
In IDETC 2025
BlendedNet is a publicly available aerodynamic dataset of 999 blended wing body (BWB) geometries. Each geometry is simulated across about nine flight conditions, yielding 8830 converged RANS cases with the Spalart-Allmaras model and 9 to 14 million cells per case. The dataset is generated by sampling geometric design parameters and flight conditions, and includes detailed pointwise surface quantities needed to study lift and drag. We also introduce an end-to-end surrogate framework for pointwise aerodynamic prediction. The pipeline first uses a permutation-invariant PointNet regressor to predict geometric parameters from sampled surface point clouds, then conditions a Feature-wise Linear Modulation (FiLM) network on the predicted parameters and flight conditions to predict pointwise coefficients Cp, Cfx, and Cfz. Experiments show low errors in surface predictions across diverse BWBs. BlendedNet addresses data scarcity for unconventional configurations and enables research on data-driven surrogate modeling for aerodynamic design.
MIT Open Data Prize, 2024
In NeurIPS 2024
We present DrivAerNet++, the largest and most comprehensive multimodal dataset for aerodynamic car design. DrivAerNet++ comprises 8,000 diverse car designs modeled with high-fidelity computational fluid dynamics (CFD) simulations. The dataset includes diverse car configurations such as fastback, notchback, and es- tateback, with different underbody and wheel designs to represent both internal combustion engines and electric vehicles. Each entry in the dataset features detailed 3D meshes, parametric models, aerodynamic coefficients, and extensive flow and surface field data, along with segmented parts for car classification and point cloud data. This dataset supports a wide array of machine learning applications including data-driven design optimization, generative modeling, surrogate model training, CFD simulation acceleration, and geometric classification. With more than 39 TB of publicly available engineering data, DrivAerNet++ fills a significant gap in available resources, providing high-quality, diverse data to enhance model training, promote generalization, and accelerate automotive design processes. Along with rigorous dataset validation, we also provide ML benchmarking results on the task of aerodynamic drag prediction, showcasing the breadth of applications supported by our dataset. This dataset is set to significantly impact automotive design and broader engineering disciplines by fostering innovation and improving the fidelity of aerodynamic evaluations.
Prospective Ph.D. students - If you are interested in joining the DeCoDE lab, you can apply to the Computational Science and Engineering Program or to the Mechanical Engineering department at MIT.
If you are interested in joining the DeCoDE lab, drop me an email with the following text in your subject line "Join DeCoDE:" followed by the position you are interested in (for example, a postdoc, intern, visiting student, etc.).
Engineering design datasets from the DeCoDE lab. Please cite the corresponding paper when using a dataset.
Interactive project pages for our publications.
Prof. Faez Ahmed is an Associate Professor in the Department of Mechanical Engineering at MIT, where he directs the Design Computation and Digital Engineering Lab. His research interests lie at the intersection of Artificial Intelligence and engineering design, focusing particularly on first‑principle generative AI and optimization algorithms, multi‑modal representation learning, and engineering design methodology with human–AI design co‑pilots. Before joining MIT, Prof. Ahmed was a postdoctoral fellow at Northwestern University and earned his Ph.D. in Mechanical Engineering from the University of Maryland. He also spent several years in Australia’s railway and mining sector, leading data‑driven predictive‑maintenance initiatives. Prof. Ahmed has received the NSF CAREER Award, the AFOSR Young Investigator Award, the ASME DAC and DTM Young Investigator Awards, the Google Research Scholar and Amazon Research Awards, and MIT's Keenan Award for Innovation in Undergraduate Education. He holds the Esther and Harold E. Edgerton Career Development Professorship, having previously held the Doherty, ABS, and d'Arbeloff chairs, and serves as Associate Editor of Design Science and on the editorial boards of Computer-Aided Design and Machine Learning: Engineering.
Fun fact: According to the Mathematics Genealogy Project, our academic ancestors include: Poisson, Laplace, Lagrange, Euler, Bernoulli, Leibniz, Copernicus, Nasir al-Din al-Tusi, and many more. Check out our academic family tree.
No Math AI
MIT Open Learning
MIT Mechanical Engineering
We gratefully acknowledge the organizations that support and collaborate on our research.
