Levent Burak Kara
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Levent Burak Kara has a total of 153 co-authors. Here are the top co-authors by number of shared publications:
Kenji Shimada
Department of Mechanical Engineering Carnegie Mellon University 15213 Pittsburgh PA USA
9 shared publicationsHongrui Chen
Department of Mechanical Engineering Carnegie Mellon University Pittsburgh 15213 PA USA
8 shared publicationsGünay Orbay
6 shared publicationsLuoting Fu
6 shared publicationsAditya Joglekar
5 shared publicationsGunay Orbay
Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213
5 shared publications
Latest Publications
- Open Access
- 10 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
Design for Machinability: Topology Optimization for Subtractive Machining Using Trimmed Neural Fields
Topology optimization has found significant utility in additive manufacturing, but the resulting geometries are often difficult to realize using subtractive methods. The complex, curved surfaces of optimized designs typically require time-consuming point milling operations. In contrast, geometries composed of developable surfaces are well suited to flank milling, enabling substantial improvements in machining efficiency and surface quality. However, globally minimizing Gaussian curvature leads to overly simplistic designs. We address this challenge with a novel method that represents geometry using three implicit neural fields, optimized to produce machinable components. The resulting designs consist of regions of developable surfaces separated by seamlines where curvature is concentrated. Seamlines are efficiently computed as intersections of the implicit fields, while the geometry emerges through their product. By constraining surfaces to align with the cutter’s normal or tangential direction, our approach further accommodates practical constraints of 3-axis machining. We demonstrate concurrent optimization of topology and Gaussian curvature, enabling control over seamline feature scale. Compared to methods that enforce subtractive machinability without considering milling efficiency, our approach consistently reduces machining time while maintaining competitive structural performance.
- 10 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
Open AccessDesign for Machinability: Topology Optimization for Subtractive Machining Using Trimmed Neural Fields
Topology optimization has found significant utility in additive manufacturing, but the resulting geometries are often difficult to realize using subtractive methods. The complex, curved surfaces of optimized designs typically require time-consuming point milling operations. In contrast, geometries composed of developable surfaces are well suited to flank milling, enabling substantial improvements in machining efficiency and surface quality. However, globally minimizing Gaussian curvature leads to overly simplistic designs. We address this challenge with a novel method that represents geometry using three implicit neural fields, optimized to produce machinable components. The resulting designs consist of regions of developable surfaces separated by seamlines where curvature is concentrated. Seamlines are efficiently computed as intersections of the implicit fields, while the geometry emerges through their product. By constraining surfaces to align with the cutter’s normal or tangential direction, our approach further accommodates practical constraints of 3-axis machining. We demonstrate concurrent optimization of topology and Gaussian curvature, enabling control over seamline feature scale. Compared to methods that enforce subtractive machinability without considering milling efficiency, our approach consistently reduces machining time while maintaining competitive structural performance.
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (6) , 7524-7531
FlowSSC: Universal Generative Monocular Semantic Scene Completion via One-Step Latent Diffusion
Semantic Scene Completion (SSC) from monocular RGB images is a fundamental yet challenging task due to the inherent ambiguity of inferring occluded 3D geometry from a single view. While feed-forward methods have made progress, they often struggle to generate plausible details in occluded regions and preserve the fundamental spatial relationships of objects. Such accurate generative reasoning capability for the entire 3D space is critical in real-world applications. In this paper, we present FlowSSC, the first generative framework applied directly to monocular semantic scene completion. FlowSSC treats the SSC task as a conditional generation problem and can seamlessly integrate with existing feed-forward SSC methods to significantly boost their performance. To achieve real-time inference without compromising quality, we introduce Shortcut Flow-matching that operates in a compact triplane latent space. Unlike standard diffusion models that require hundreds of steps, our method utilizes a shortcut mechanism to achieve high-fidelity generation in a single step, enabling practical deployment in autonomous systems. Extensive experiments on SemanticKITTI demonstrate that FlowSSC achieves state-of-the-art performance, significantly outperforming existing baselines.
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (6) , 7524-7531
FlowSSC: Universal Generative Monocular Semantic Scene Completion via One-Step Latent Diffusion
Semantic Scene Completion (SSC) from monocular RGB images is a fundamental yet challenging task due to the inherent ambiguity of inferring occluded 3D geometry from a single view. While feed-forward methods have made progress, they often struggle to generate plausible details in occluded regions and preserve the fundamental spatial relationships of objects. Such accurate generative reasoning capability for the entire 3D space is critical in real-world applications. In this paper, we present FlowSSC, the first generative framework applied directly to monocular semantic scene completion. FlowSSC treats the SSC task as a conditional generation problem and can seamlessly integrate with existing feed-forward SSC methods to significantly boost their performance. To achieve real-time inference without compromising quality, we introduce Shortcut Flow-matching that operates in a compact triplane latent space. Unlike standard diffusion models that require hundreds of steps, our method utilizes a shortcut mechanism to achieve high-fidelity generation in a single step, enabling practical deployment in autonomous systems. Extensive experiments on SemanticKITTI demonstrate that FlowSSC achieves state-of-the-art performance, significantly outperforming existing baselines.
- Open Access
- 23 February 2026
- Published by Elsevier in SSRN Electronic Journal
Surrogate model for rapid laser powder bed fusion distortion prediction with adjustable material property input
The design process for metal additive manufacturing is limited by the computational cost of simulating a full build at every design iteration. We develop a data-driven machine-learned surrogate model that can predict output fields of Laser Powder Bed Fusion (LPBF) simulations. The model is trained on a dataset of 456 unique 3D parts and is capable of predicting displacement along the build direction for five different materials. Specifically, we train a set of models to predict part distortion during LPBF, capable of working across a range of shapes and materials. Further, we determine that a graph-convolution-based approach is less prone to overfitting and better suited for fine-tuning than an attention-based model. By fine-tuning, we are able to rapidly update an existing LPBF prediction model for better performance on a new set of parts. We present a thorough investigation into the use of fine-tuning with Low-Rank Adaptation (LoRA) to improve model performance on a previously unseen material. We conclude that only a few new simulations are required in order to optimally fine-tune a model for a new set of material properties. The proposed model can be used to rapidly estimate whether there will be excessive deformation along the build direction for arbitrary input shapes and materials.
- 23 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessSurrogate model for rapid laser powder bed fusion distortion prediction with adjustable material property input
The design process for metal additive manufacturing is limited by the computational cost of simulating a full build at every design iteration. We develop a data-driven machine-learned surrogate model that can predict output fields of Laser Powder Bed Fusion (LPBF) simulations. The model is trained on a dataset of 456 unique 3D parts and is capable of predicting displacement along the build direction for five different materials. Specifically, we train a set of models to predict part distortion during LPBF, capable of working across a range of shapes and materials. Further, we determine that a graph-convolution-based approach is less prone to overfitting and better suited for fine-tuning than an attention-based model. By fine-tuning, we are able to rapidly update an existing LPBF prediction model for better performance on a new set of parts. We present a thorough investigation into the use of fine-tuning with Low-Rank Adaptation (LoRA) to improve model performance on a previously unseen material. We conclude that only a few new simulations are required in order to optimally fine-tune a model for a new set of material properties. The proposed model can be used to rapidly estimate whether there will be excessive deformation along the build direction for arbitrary input shapes and materials.
- Open Access
Heterogeneous Metamaterials Design via Multiscale Neural Implicit Representation
Metamaterials are engineered materials composed of specially designed unit cells that exhibit extraordinary properties beyond those of natural materials. Complex engineering tasks often require heterogeneous unit cells to accommodate spatially varying property requirements. However, designing heterogeneous metamaterials poses significant challenges due to the enormous design space and strict compatibility requirements between neighboring cells. Traditional concurrent multiscale design methods require solving an expensive optimization problem for each unit cell and often suffer from discontinuities at cell boundaries. On the other hand, data-driven approaches that assemble structures from a fixed library of microstructures are limited by the dataset and require additional post-processing to ensure seamless connections. In this work, we propose a neural network-based metamaterial design framework that learns a continuous two-scale representation of the structure, thereby jointly addressing these challenges. Central to our framework is a multiscale neural representation in which the neural network takes both global (macroscale) and local (microscale) coordinates as inputs, outputting an implicit field that represents multiscale structures with compatible unit cell geometries across the domain, without the need for a predefined dataset. We use a compatibility loss term during training to enforce connectivity between adjacent unit cells. Once trained, the network can produce metamaterial designs at arbitrarily high resolution, hence enabling infinite upsampling for fabrication or simulation. We demonstrate the effectiveness of the proposed approach on mechanical metamaterial design, negative Poisson's ratio, and mechanical cloaking problems with potential applications in robotics, bioengineering, and aerospace.
Open AccessHeterogeneous Metamaterials Design via Multiscale Neural Implicit Representation
Metamaterials are engineered materials composed of specially designed unit cells that exhibit extraordinary properties beyond those of natural materials. Complex engineering tasks often require heterogeneous unit cells to accommodate spatially varying property requirements. However, designing heterogeneous metamaterials poses significant challenges due to the enormous design space and strict compatibility requirements between neighboring cells. Traditional concurrent multiscale design methods require solving an expensive optimization problem for each unit cell and often suffer from discontinuities at cell boundaries. On the other hand, data-driven approaches that assemble structures from a fixed library of microstructures are limited by the dataset and require additional post-processing to ensure seamless connections. In this work, we propose a neural network-based metamaterial design framework that learns a continuous two-scale representation of the structure, thereby jointly addressing these challenges. Central to our framework is a multiscale neural representation in which the neural network takes both global (macroscale) and local (microscale) coordinates as inputs, outputting an implicit field that represents multiscale structures with compatible unit cell geometries across the domain, without the need for a predefined dataset. We use a compatibility loss term during training to enforce connectivity between adjacent unit cells. Once trained, the network can produce metamaterial designs at arbitrarily high resolution, hence enabling infinite upsampling for fabrication or simulation. We demonstrate the effectiveness of the proposed approach on mechanical metamaterial design, negative Poisson's ratio, and mechanical cloaking problems with potential applications in robotics, bioengineering, and aerospace.
- Open Access
- 10 June 2025
- Published by Springer Nature in Engineering with Computers
- Vol. 41 (5) , 3313-3327
Multi-scale topology optimization using neural networks
A long-standing challenge in multi-scale structural design is ensuring proper connectivity between the constituent cells as each cell is being optimized toward its theoretical performance limit. We propose a new method for multi-scale topology optimization that seamlessly ensures compatibility across neighboring microstructure cells without the need for a catalog of unit cells and associated connectivity rules. Our approach consists of a topology neural network that encodes each cell’s microstructure as well as the distribution of the optimized cells within the design domain as a continuous and differentiable density field. Each cell is optimized based on a prescribed elasticity tensor. The neural network takes as input the local coordinates within a cell to represent the density distribution within a cell, as well as the global coordinates of each cell to generate spatially varying microstructure cells. As such, our approach models an n-dimensional multi-scale optimization problem as a 2n-dimensional inverse homogenization problem using neural networks. During the inverse homogenization of each unit cell, we extend the boundary of each cell by scaling the input coordinates such that the boundaries of neighboring cells are blended and, thus, jointly optimized. This enables inverse homogenization of the cells to be consistently connected without introducing discontinuities at the cell boundaries. We demonstrate our method through the design and optimization of several graded multi-scale structures.
- 10 June 2025
- Published by Springer Nature in Engineering with Computers
- Vol. 41 (5) , 3313-3327
Open AccessMulti-scale topology optimization using neural networks
A long-standing challenge in multi-scale structural design is ensuring proper connectivity between the constituent cells as each cell is being optimized toward its theoretical performance limit. We propose a new method for multi-scale topology optimization that seamlessly ensures compatibility across neighboring microstructure cells without the need for a catalog of unit cells and associated connectivity rules. Our approach consists of a topology neural network that encodes each cell’s microstructure as well as the distribution of the optimized cells within the design domain as a continuous and differentiable density field. Each cell is optimized based on a prescribed elasticity tensor. The neural network takes as input the local coordinates within a cell to represent the density distribution within a cell, as well as the global coordinates of each cell to generate spatially varying microstructure cells. As such, our approach models an n-dimensional multi-scale optimization problem as a 2n-dimensional inverse homogenization problem using neural networks. During the inverse homogenization of each unit cell, we extend the boundary of each cell by scaling the input coordinates such that the boundaries of neighboring cells are blended and, thus, jointly optimized. This enables inverse homogenization of the cells to be consistently connected without introducing discontinuities at the cell boundaries. We demonstrate our method through the design and optimization of several graded multi-scale structures.
- Open Access
- 14 April 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (4) , e0319196
A data-driven approach for real-time soft tissue deformation prediction using nonlinear presurgical simulations
A method that allows a fast and accurate registration of digital tissue models obtained during preoperative, diagnostic imaging with those captured intraoperatively using lower-fidelity ultrasound imaging techniques is presented. Minimally invasive surgeries are often planned using preoperative, high-fidelity medical imaging techniques such as MRI and CT imaging. While these techniques allow clinicians to obtain detailed 3D models of the surgical region of interest (ROI), various factors such as physical changes to the tissue, changes in the body’s configuration, or apparatus used during the surgery may cause large, non-linear deformations of the ROI. Such deformations of the tissue can result in a severe mismatch between the preoperatively obtained 3D model and the real-time image data acquired during surgery, potentially compromising surgical success. To overcome this challenge, this work presents a new approach for predicting intraoperative soft tissue deformations. The approach works by simply tracking the displacements of a handful of fiducial markers or analogous biological features embedded in the tissue, and produces a 3D deformed version of the high-fidelity ROI model that registers accurately with the intraoperative data. In an offline setting, we use the finite element method to generate deformation fields given various boundary conditions that mimic the realistic environment of soft tissues during a surgery. To reduce the dimensionality of the 3D deformation field involving thousands of degrees of freedom, we use an autoencoder neural network to encode each computed deformation field into a short latent space representation, such that a neural network can accurately map the fiducial marker displacements to the latent space. Our computational tests on a head and neck tumor, a kidney, and an aorta model show prediction errors as small as 0.5 mm. Considering that the typical resolution of interventional ultrasound is around 1 mm and each prediction takes less than 0.5 s, the proposed approach has the potential to be clinically relevant for an accurate tracking of soft tissue deformations during image-guided surgeries.
- 14 April 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (4) , e0319196
Open AccessA data-driven approach for real-time soft tissue deformation prediction using nonlinear presurgical simulations
A method that allows a fast and accurate registration of digital tissue models obtained during preoperative, diagnostic imaging with those captured intraoperatively using lower-fidelity ultrasound imaging techniques is presented. Minimally invasive surgeries are often planned using preoperative, high-fidelity medical imaging techniques such as MRI and CT imaging. While these techniques allow clinicians to obtain detailed 3D models of the surgical region of interest (ROI), various factors such as physical changes to the tissue, changes in the body’s configuration, or apparatus used during the surgery may cause large, non-linear deformations of the ROI. Such deformations of the tissue can result in a severe mismatch between the preoperatively obtained 3D model and the real-time image data acquired during surgery, potentially compromising surgical success. To overcome this challenge, this work presents a new approach for predicting intraoperative soft tissue deformations. The approach works by simply tracking the displacements of a handful of fiducial markers or analogous biological features embedded in the tissue, and produces a 3D deformed version of the high-fidelity ROI model that registers accurately with the intraoperative data. In an offline setting, we use the finite element method to generate deformation fields given various boundary conditions that mimic the realistic environment of soft tissues during a surgery. To reduce the dimensionality of the 3D deformation field involving thousands of degrees of freedom, we use an autoencoder neural network to encode each computed deformation field into a short latent space representation, such that a neural network can accurately map the fiducial marker displacements to the latent space. Our computational tests on a head and neck tumor, a kidney, and an aorta model show prediction errors as small as 0.5 mm. Considering that the typical resolution of interventional ultrasound is around 1 mm and each prediction takes less than 0.5 s, the proposed approach has the potential to be clinically relevant for an accurate tracking of soft tissue deformations during image-guided surgeries.
- Open Access
- 3 April 2025
- Published by Elsevier in Computers in Industry
- Vol. 168
Generative Manufacturing: A requirements and resource-driven approach to part making
- 3 April 2025
- Published by Elsevier in Computers in Industry
- Vol. 168
Open AccessGenerative Manufacturing: A requirements and resource-driven approach to part making
- Open Access
- 28 March 2025
- Published by Elsevier in Journal of Computational Physics
- Vol. 532
SNF-ROM: Projection-based nonlinear reduced order modeling with smooth neural fields
- 28 March 2025
- Published by Elsevier in Journal of Computational Physics
- Vol. 532
Open AccessSNF-ROM: Projection-based nonlinear reduced order modeling with smooth neural fields
- Open Access
- 19 February 2025
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 37 (2) , 887-907
VIRL: Volume-Informed Representation Learning towards few-shot manufacturability estimation
Designing for manufacturing poses significant challenges in part due to the computation bottleneck of Computer-Aided Manufacturing (CAM) simulations. Although deep learning as an alternative offers fast inference, its performance is dependently bounded by the need for abundant training data. Representation learning, particularly through pre-training, offers promise for few-shot learning, aiding in manufacturability tasks where data can be limited. This work introduces VIRL, a Volume-Informed Representation Learning approach to pre-train a 3D geometric encoder. The pretrained model is evaluated across four manufacturability indicators obtained from CAM simulations: subtractive machining (SM) time, additive manufacturing (AM) time, residual von Mises stress, and blade collisions during Laser Power Bed Fusion process. Across all case studies, the model pre-trained by VIRL shows substantial enhancements in generalizability, as measured by R2 regression results, with improved performance on limited data and superior predictive accuracy with larger datasets. Regarding deployment strategy, case-specific phenomenon exists where finetuning VIRL-pretrained models adversely affects AM tasks with limited data but benefits SM time prediction. Moreover, the efficacy of Low-rank adaptation (LoRA), which balances between probing and finetuning, is explored. LoRA shows stable performance akin to probing with limited data, while achieving a higher upper bound than probing as data size increases, without the computational costs of finetuning. Furthermore, static normalization of manufacturing indicators consistently performs well across tasks, while dynamic normalization enhances performance when a reliable task dependent input is available.
- 19 February 2025
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 37 (2) , 887-907
Open AccessVIRL: Volume-Informed Representation Learning towards few-shot manufacturability estimation
Designing for manufacturing poses significant challenges in part due to the computation bottleneck of Computer-Aided Manufacturing (CAM) simulations. Although deep learning as an alternative offers fast inference, its performance is dependently bounded by the need for abundant training data. Representation learning, particularly through pre-training, offers promise for few-shot learning, aiding in manufacturability tasks where data can be limited. This work introduces VIRL, a Volume-Informed Representation Learning approach to pre-train a 3D geometric encoder. The pretrained model is evaluated across four manufacturability indicators obtained from CAM simulations: subtractive machining (SM) time, additive manufacturing (AM) time, residual von Mises stress, and blade collisions during Laser Power Bed Fusion process. Across all case studies, the model pre-trained by VIRL shows substantial enhancements in generalizability, as measured by R2 regression results, with improved performance on limited data and superior predictive accuracy with larger datasets. Regarding deployment strategy, case-specific phenomenon exists where finetuning VIRL-pretrained models adversely affects AM tasks with limited data but benefits SM time prediction. Moreover, the efficacy of Low-rank adaptation (LoRA), which balances between probing and finetuning, is explored. LoRA shows stable performance akin to probing with limited data, while achieving a higher upper bound than probing as data size increases, without the computational costs of finetuning. Furthermore, static normalization of manufacturing indicators consistently performs well across tasks, while dynamic normalization enhances performance when a reliable task dependent input is available.
- Open Access
- 16 January 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-17
A simplified computational liver perfusion model, with applications to organ preservation
Advanced liver preservation strategies could revolutionize liver transplantation by extending preservation time, thereby allowing for broader availability and better matching of transplants. However, developing new cryopreservation protocols requires exploration of a complex design space, further complicated by the scarcity of real human livers to experiment upon. We aim to create computational models of the liver to aid in the development of new cryopreservation protocols. Towards this goal, we present an approach for generating 3D models of the liver vasculature by building upon the space colonization algorithm. Additionally, we introduce the concept of a super lobule which enables a computational abstraction of biological liver lobules. User-tunable parameters allow for vasculatures of varying depth and topology to be generated. In each model, we solve for a common lumped resistance value assigned to the super lobules, allowing the overall physiological blood pressure and flow rate through the liver to be preserved. We demonstrate our approach’s ability to maintain consistency between models of varying depth. Finally, we simulate steady state machine perfusion of the generated models and demonstrate how they can be used to quickly test the effect of different boundary conditions when designing organ preservation protocols.
- 16 January 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-17
Open AccessA simplified computational liver perfusion model, with applications to organ preservation
Advanced liver preservation strategies could revolutionize liver transplantation by extending preservation time, thereby allowing for broader availability and better matching of transplants. However, developing new cryopreservation protocols requires exploration of a complex design space, further complicated by the scarcity of real human livers to experiment upon. We aim to create computational models of the liver to aid in the development of new cryopreservation protocols. Towards this goal, we present an approach for generating 3D models of the liver vasculature by building upon the space colonization algorithm. Additionally, we introduce the concept of a super lobule which enables a computational abstraction of biological liver lobules. User-tunable parameters allow for vasculatures of varying depth and topology to be generated. In each model, we solve for a common lumped resistance value assigned to the super lobules, allowing the overall physiological blood pressure and flow rate through the liver to be preserved. We demonstrate our approach’s ability to maintain consistency between models of varying depth. Finally, we simulate steady state machine perfusion of the generated models and demonstrate how they can be used to quickly test the effect of different boundary conditions when designing organ preservation protocols.