# 3D modeling

3D modeling is the computer-based process of creating mathematical, three-dimensional representations of physical objects using CAD software.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## DrawScore: Evaluating Generated CAD Models against Engineering Drawings

DevFeed: [DrawScore: Evaluating Generated CAD Models against Engineering Drawings](<https://devfeed.tech/articles/drawscore-evaluating-generated-cad-models-against-engineering-drawings-142216.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24681>)

Author: Haorui Chen, Shiteng Lu, Zhanyu Guo, Zaixi Li, Yunhe Ni, Yaosong Du, Yichen Xiang, Xiande Huang, Rui Huang

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [3D](<https://devfeed.tech/topics/3d.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [cad](<https://devfeed.tech/tags/cad.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [error](<https://devfeed.tech/tags/error.md>), [generation](<https://devfeed.tech/tags/generation.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [models](<https://devfeed.tech/tags/models.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [reward](<https://devfeed.tech/tags/reward.md>)

### AI overview

DrawScore targets a weakness in common CAD evaluation metrics: IoU, Chamfer Distance, and surface F-score can overlook small but manufacturing-critical errors such as a misplaced hole. It projects generated and reference models into three orthographic views with visible and hidden lines, then applies a saturating penalty to projected curves; the authors say this makes the influence of local errors decay linearly with their size, compared with higher-power decay for the conventional metrics. Controlled experiments reportedly confirm the predicted decay, and DrawScore exposes errors in agent outputs that IoU scores as nearly perfect. The authors also report using it as a reinforcement-learning reward and as a test-time verifier for drawing-to-CAD generation without 3D ground truth or an additional reward model.

### Source excerpt

arXiv:2611.24681v1 Announce Type: cross Abstract: Automatic CAD generation is commonly evaluated with volumetric IoU, Chamfer Distance, and surface F-score, which barely penalize local errors that occupy only a small fraction of a part's volume or surface area, such as a misplaced hole or a slot on the wrong face, even though such errors are critical to manufacturing. We formalize these metrics in a unified integral form and show that the weight of a local error decays as the $(k+q)$-th power of its size, where $k$ is the dimension of the integration domain and $q$ is determined by the penalty function. Guided by this analysis, we propose DrawScore, which projects both models into three orthographic views with visible and hidden lines, as in engineering drawings, and applies a saturating penalty along the projected curves, so that the weight of a local error decays only linearly. Controlled experiments confirm the predicted decay orders, and on outputs of existing CAD generation agents, DrawScore exposes errors in outputs that IoU rates as nearly perfect. DrawScore further improves generation as a reinforcement learning reward and, for CAD generation from engineering drawings, serves as a test-time verifier without 3D ground truth or an additional reward model. Our code is available at https://github.com/UESTC-Simon/DrawScore.

## CADMAGEDDON: High-Fidelity CAD Reconstruction with Local Inference

DevFeed: [CADMAGEDDON: High-Fidelity CAD Reconstruction with Local Inference](<https://devfeed.tech/articles/cadmageddon-high-fidelity-cad-reconstruction-with-local-inference-140049.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22563>)

Author: Oleg Pavlov, Nikita Gavrilov, Soslan Kabisov, Gennadii Savrasov, Andrey Kuznetsov, Anton Konushin, Dmitrii Zhemchuzhnikov

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Local AI](<https://devfeed.tech/topics/local-ai.md>), [3D](<https://devfeed.tech/topics/3d.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cad](<https://devfeed.tech/tags/cad.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [freecad](<https://devfeed.tech/tags/freecad.md>), [frontier](<https://devfeed.tech/tags/frontier.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [laptops](<https://devfeed.tech/tags/laptops.md>), [local-inference](<https://devfeed.tech/tags/local-inference.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [open-source-agent](<https://devfeed.tech/tags/open-source-agent.md>), [qwen3-8-27b](<https://devfeed.tech/tags/qwen3-8-27b.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

CADMAGEDDON reconstructs editable CAD from meshes by breaking the work into visual decisions about what to build and correct, while geometric tools handle precise construction. The open-source agent is designed for local use on single-GPU systems and current-generation laptops, addressing practitioners' reluctance to send proprietary parts to external services and limited compute budgets. With Qwen3.8-27B, it reportedly outperforms prior approaches, including frontier-model systems, on all main reconstruction benchmarks. It integrates with FreeCAD. The supplied text does not give benchmark details or specify hardware requirements beyond the stated local-use scope.

### Source excerpt

arXiv:2611.22563v1 Announce Type: new Abstract: CAD practitioners often work with proprietary parts that they are unwilling to share with external services. For individuals and small companies, bringing this work in-house also requires computational resources they can afford. We introduce CADMAGEDDON, an open-source agent that reconstructs editable CAD from meshes and can run locally on single-GPU systems and current-generation laptops. The method decomposes this complex task into a chain of simple visual decisions about what to construct and what to correct. Geometric tools support precise construction, allowing the agent to focus on visual reasoning. Using the mid-sized Qwen3.8-27B model, CADMAGEDDON outperforms prior approaches, including systems based on frontier models, in reconstruction quality on all the main benchmarks. CADMAGEDDON integrates with FreeCAD, bringing its reconstructions into practitioners' existing CAD workflows. Code: https://github.com/kulibinai/cadmageddon

## Topology-Aware Reinforcement Learning for CAD Decomposition toward All-Hexahedral Meshing

DevFeed: [Topology-Aware Reinforcement Learning for CAD Decomposition toward All-Hexahedral Meshing](<https://devfeed.tech/articles/topology-aware-reinforcement-learning-for-cad-decomposition-toward-all-hexahedral-meshing-128629.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.12930>)

Author: Jiaming Peng, Zhihao Zheng, Rui Wang, Qinglin Wang, Jing Xiao, Jie Liu, Na Lei, Xinhai Chen

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [cad](<https://devfeed.tech/tags/cad.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-gr](<https://devfeed.tech/tags/cs-gr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [deep-reinforcement-learning](<https://devfeed.tech/tags/deep-reinforcement-learning.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [topology](<https://devfeed.tech/tags/topology.md>)

### AI overview

DecompRL uses deep reinforcement learning to decompose complex CAD models for all-hexahedral meshing. Its topology-aware internal-splitting actions use global topology and local geometry to separate misaligned features; geometric rewards and meshability feedback guide the agent toward valid decompositions and quality meshes. Across ABC, Fusion360, NIST, and DeepCAD, it reports the highest success rate among evaluated learning-based methods on three benchmarks, with competitive mesh quality. The largest reported success-rate improvement is on Fusion360, where DecompRL reaches 59.6%. A reported runtime ratio of up to 100x compares the full LMFF procedure with DecompRL decomposition alone, excluding later mesh generation.

### Source excerpt

arXiv:2611.12930v1 Announce Type: cross Abstract: Automatic hexahedral meshing for complex CAD models has long been regarded as the "holy grail" of mesh generation. The fundamental challenge arises from feature misalignment, where orthogonal or interacting features coexist, making direct hexahedral meshing infeasible and requiring decomposition into simpler, meshable blocks. While existing decomposition methods, including frame-field pipelines and learning-based techniques, have reduced manual intervention, they can remain sensitive to geometric and topological complexity and may fail to produce valid decompositions for challenging feature configurations. Specifically, their action spaces are typically restricted to surface-based splitting, which often yields invalid or unmeshable decompositions. To address these limitations, we propose DecompRL, a deep reinforcement learning framework for CAD decomposition toward hexahedral meshing. We design a set of topology-aware internal-splitting actions that leverage both global topological structure and local geometric property to effectively separate misaligned features. Furthermore, we introduce geometric rewards together with meshability feedback to guide the learning process toward valid decompositions and high-quality meshes. Extensive experiments on ABC, Fusion360, NIST, and DeepCAD show that DecompRL achieves the highest success rate among the evaluated learning-based methods on three of the four benchmarks, while maintaining competitive mesh quality. The measured LMFF-to-DecompRL runtime ratio reaches up to two orders of magnitude; this compares the full LMFF procedure with DecompRL decomposition alone, excluding subsequent mesh generation. The largest SR improvement is observed on Fusion360, where DecompRL reaches a success rate of 59.6%.

## GOPR-CAD: Graph-of-Operations Progressive Reasoning for CAD Generation

DevFeed: [GOPR-CAD: Graph-of-Operations Progressive Reasoning for CAD Generation](<https://devfeed.tech/articles/gopr-cad-graph-of-operations-progressive-reasoning-for-cad-generation-126120.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.11470>)

Author: Yitian Pang, Yifan Li, Xiaowei Yue, Li Zheng

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [appearance](<https://devfeed.tech/tags/appearance.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [but](<https://devfeed.tech/tags/but.md>), [cad](<https://devfeed.tech/tags/cad.md>), [code](<https://devfeed.tech/tags/code.md>), [compiler](<https://devfeed.tech/tags/compiler.md>), [control](<https://devfeed.tech/tags/control.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [decision](<https://devfeed.tech/tags/decision.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [execution](<https://devfeed.tech/tags/execution.md>), [generation](<https://devfeed.tech/tags/generation.md>), [graph](<https://devfeed.tech/tags/graph.md>), [operations](<https://devfeed.tech/tags/operations.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>)

### AI overview

GOPR-CAD generates CAD models by having a language model progressively build an executable graph from encapsulated CAD operations; a deterministic compiler then converts that graph into the model. This separates planning from code generation, requires no additional training, and supports different language models. The paper introduces MHCAD, a benchmark of 300 mechanical-part requirements derived from Machinery's Handbook, with explicit structures that enable reference-free STEP/B-rep evaluation. GOPR-CAD reports 82.7% Structural Yield on MHCAD and 87.2% on an external CADPrompt subset. The abstract motivates this approach by noting that executable code and rendered appearance may fail to reveal structural errors.

### Source excerpt

arXiv:2611.11470v1 Announce Type: new Abstract: Generating accurate CAD models requires substantial engineering expertise and careful control of geometry, topology, and mechanical constraints. Text-to-CAD aims to simplify this process, but current LLM-based methods often generate CAD programs directly. Language models remain unreliable when producing long code while coordinating coupled geometric, topological, and dimensional constraints. Consequently, executable programs may still produce structurally incorrect models, which execution rate and rendered appearance may fail to reveal. To address these limitations, we propose GOPR-CAD, an agentic Text-to-CAD pipeline based on Graph-of-Operations Progressive Reasoning. A language model acts as a decision agent over encapsulated CAD operations and progressively constructs an executable operation graph, which a deterministic compiler converts into the final CAD model. This separation requires no additional training and supports different language models. To evaluate structural fidelity, we construct MHCAD, a benchmark of 300 standard mechanical part requirements derived from Machinery's Handbook. Their explicit structures enable reference-free STEP/B-rep evaluation. GOPR-CAD achieves 82.7% Structural Yield on MHCAD, and 87.2% Structural Yield on an external CADPrompt subset.

## PhyCAD: Physics-Aware Text-to-CAD Generation via Hierarchical Reinforcement Learning

DevFeed: [PhyCAD: Physics-Aware Text-to-CAD Generation via Hierarchical Reinforcement Learning](<https://devfeed.tech/articles/phycad-physics-aware-text-to-cad-generation-via-hierarchical-reinforcement-learning-124674.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09401>)

Author: Yuxin Cui, Weijie Zheng, Zhengyang Li, Han Wang, Wenjie Feng, Qiyu Kang

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [grpo](<https://devfeed.tech/topics/grpo.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [CadQuery](<https://devfeed.tech/topics/cadquery.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [rlvr](<https://devfeed.tech/topics/rlvr.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [automated](<https://devfeed.tech/tags/automated.md>), [cad](<https://devfeed.tech/tags/cad.md>), [cadquery](<https://devfeed.tech/tags/cadquery.md>), [cae](<https://devfeed.tech/tags/cae.md>), [computer-aided-design](<https://devfeed.tech/tags/computer-aided-design.md>), [constraint-satisfaction](<https://devfeed.tech/tags/constraint-satisfaction.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [group-relative-policy-optimization](<https://devfeed.tech/tags/group-relative-policy-optimization.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [learning](<https://devfeed.tech/tags/learning.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [physics](<https://devfeed.tech/tags/physics.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [text](<https://devfeed.tech/tags/text.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

PhyCAD trains language models to generate executable CadQuery programs that satisfy geometric and physical constraints, addressing the fact that geometric correctness alone does not ensure physical feasibility. Its dataset links parametric models with geometric specifications, loading conditions, and physical constraints; an automated CAD-CAE verifier combines program execution, geometric checks, and finite element analysis to provide training feedback. To keep unmet requirements from being offset by gains on other criteria, its Hierarchical Balanced Advantage for Group Relative Policy Optimization ranks candidates by verification status, then provides objective-wise peer feedback within each level. Experiments across multiple language models report improved joint geometric and physical constraint satisfaction. The supplied text is an abstract and does not provide quantitative results or implementation details.

### Source excerpt

arXiv:2611.09401v1 Announce Type: new Abstract: Language-driven computer-aided design (CAD) generation enables the creation of editable parametric models from text, yet geometric correctness alone does not ensure physical feasibility. We present PhyCAD, a framework for physics-aware Text-to-CAD generation that trains language models to produce executable CadQuery programs under geometric and physical constraints. To support this setting, we construct a Text-to-CAD dataset that links parametric CAD models with geometric specifications, loading conditions, and physical constraints. We further develop an automated CAD--CAE verifier that combines program execution, geometric checks, and finite element analysis to provide feedback for model training. A key learning challenge is to prioritize joint satisfaction of geometric and physical constraints while retaining informative feedback on partial progress. A flat aggregation of heterogeneous rewards can obscure this priority, allowing improvements in individual criteria to compensate for unmet design requirements. We therefore introduce a Hierarchical Balanced Advantage for Group Relative Policy Optimization, grouping candidates into levels according to their verification status and combining between-level progress with objective-wise peer ranking within each level. This formulation preserves cross-level priority in the training signal while providing fine-grained feedback for satisfying constraints and improving feasible designs. Experiments across multiple language models show that PhyCAD consistently improves joint geometric and physical constraint satisfaction. These results demonstrate the value of verifiable engineering feedback for advancing language-driven CAD generation beyond geometric reconstruction toward physics-aware design.

## TraceCAD: Trace-Guided Repair for Agentic CAD Generation

DevFeed: [TraceCAD: Trace-Guided Repair for Agentic CAD Generation](<https://devfeed.tech/articles/tracecad-trace-guided-repair-for-agentic-cad-generation-118041.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.03062>)

Author: Fengxiao Fan, Jingzhe Ni, Fan Sang, Xiaolong Yin, Yu Liu, Ruofeng Tong, Min Tang, Peng Du

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [CadQuery](<https://devfeed.tech/topics/cadquery.md>), [Software](<https://devfeed.tech/topics/software.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [cad](<https://devfeed.tech/tags/cad.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-gr](<https://devfeed.tech/tags/cs-gr.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [dependency](<https://devfeed.tech/tags/dependency.md>), [edits](<https://devfeed.tech/tags/edits.md>), [execution](<https://devfeed.tech/tags/execution.md>), [failed](<https://devfeed.tech/tags/failed.md>), [generation](<https://devfeed.tech/tags/generation.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llm](<https://devfeed.tech/tags/llm.md>), [memory](<https://devfeed.tech/tags/memory.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [regression](<https://devfeed.tech/tags/regression.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [repair](<https://devfeed.tech/tags/repair.md>), [results](<https://devfeed.tech/tags/results.md>), [retries](<https://devfeed.tech/tags/retries.md>), [store](<https://devfeed.tech/tags/store.md>)

### AI overview

TraceCAD improves CAD-agent repair by preserving links between requested features, modeling steps, failures, and repair outcomes. It diagnoses likely faulty operations, searches bounded edits in their dependency regions, checks candidates by execution and preservation, and stores successful and failed repairs in reusable skill memory. On DeepCAD-derived benchmarks, it reports competitive IoU, Chamfer, and Hausdorff results. Ablations show that removing persistent state nearly halves recovery score, while removing localized search more than doubles geometric regression and doubles code-agent invocations. A skill store initialized on disjoint training models also reduces retries, token cost, and latency.

### Source excerpt

arXiv:2608.03062v2 Announce Type: replace-cross Abstract: LLM-based CAD agents produce executable parametric programs, but their correction loops may lose evidence about satisfied requirements, faulty operations, and prior repairs. We introduce TraceCAD, a recovery layer that links requested features, modeling steps, failure evidence, and candidate outcomes as persistent state. TraceCAD diagnoses likely faulty operations, searches bounded edits in their dependency regions, validates candidates through execution and preservation checks, and retains successful and failed repair outcomes in reusable skill memory. On DeepCAD-derived benchmarks with 200-model ablations and a 1K-model comparison, TraceCAD achieves competitive geometric quality in terms of IoU, Chamfer distance, and Hausdorff distance. Removing persistent state nearly halves recovery score; removing localized search more than doubles geometric regression and doubles code-agent invocations. Initializing the skill store on disjoint training models further reduces retries, token cost, and latency. These results demonstrate that persistent, localized, and reusable recovery improves final CAD quality and repair reliability.

## Accelerating engineering for the physical world

DevFeed: [Accelerating engineering for the physical world](<https://devfeed.tech/articles/accelerating-engineering-for-the-physical-world-115907.md>)

Original publisher: [Read original article](<https://openai.com/index/accelerating-engineering-for-the-physical-world>)

Published: 2026-11-03T12:00:00Z

Content type: news

Language: en

Sources: [OpenAI News](<https://devfeed.tech/sources/openai-news.md>)

Topics: [AI-enhanced product development](<https://devfeed.tech/topics/ai-enhanced-product-development.md>), [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [3D](<https://devfeed.tech/topics/3d.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [Hardware](<https://devfeed.tech/topics/hardware.md>), [Chip design](<https://devfeed.tech/topics/chip-design.md>), [Electrical engineering and computer science (EECS)](<https://devfeed.tech/topics/electrical-engineering-and-computer-science-eecs.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>), [Robotics](<https://devfeed.tech/topics/robotics.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [accelerate](<https://devfeed.tech/tags/accelerate.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [assembly](<https://devfeed.tech/tags/assembly.md>), [astra](<https://devfeed.tech/tags/astra.md>), [build](<https://devfeed.tech/tags/build.md>), [cad](<https://devfeed.tech/tags/cad.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [changes](<https://devfeed.tech/tags/changes.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [codex](<https://devfeed.tech/tags/codex.md>), [design](<https://devfeed.tech/tags/design.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineers](<https://devfeed.tech/tags/engineers.md>), [pcb](<https://devfeed.tech/tags/pcb.md>), [pcb-design](<https://devfeed.tech/tags/pcb-design.md>), [research](<https://devfeed.tech/tags/research.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

OpenAI reports early use of its models to speed work across mechanical, electrical, and software design, while noting gaps in manufacturing readiness. In a side project, two team members used Astra to design a Codex-connected device spanning enclosure, PCB, interface, firmware, and integrations; prototypes were built in under a month, but several review rounds were needed because Astra did not consistently account for production limits, tolerances, or assembly details. Internal teams use Codex and ChatGPT for CAD revisions, manufacturing drawings, simulations, and design reviews. On BenchCAD 2.0, a newer internal model scored 0.875 on average versus 0.594 for GPT-6 Astra at its highest reasoning setting. Collaborations are testing practical workflows: Chip Ganassi Racing is evaluating conversion of 3D scans into editable CAD and drawings, with engineers checking accuracy and manufacturability; Mazda is exploring airflow and crash simulations while accounting for styling and cost. The text presents these as early evidence and says engineering review remains important for accuracy and safe, reliable use.

### Source excerpt

Discover how ChatGPT and Codex are helping engineers accelerate CAD, PCB design, simulation, and other workflows across the physical world.

## NEW GUIDE: Computer Graphics Turbo Demos #CircuitPython #AdafruitLearningSystem @Adafruit

DevFeed: [NEW GUIDE: Computer Graphics Turbo Demos #CircuitPython #AdafruitLearningSystem @Adafruit](<https://devfeed.tech/articles/new-guide-computer-graphics-turbo-demos-circuitpython-adafruitlearningsystem-adafruit-112627.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/11/02/new-guide-computer-graphics-turbo-demos-circuitpython-adafruitlearningsystem-adafruit/>)

Author: Adafruit Learning System

Published: 2026-11-02T20:11:42Z

Content type: release

Language: en

Sources: [Adafruit Industries](<https://devfeed.tech/sources/adafruit-industries-makers-hackers-artists-designers-and-engineers.md>)

Topics: [Graphics](<https://devfeed.tech/topics/graphics.md>), [Content Creation / Rendering](<https://devfeed.tech/topics/content-creation-rendering.md>), [Ray Tracing / Path Tracing](<https://devfeed.tech/topics/ray-tracing-path-tracing.md>), [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [adafruit-learning-system](<https://devfeed.tech/tags/adafruit-learning-system.md>), [box](<https://devfeed.tech/tags/box.md>), [circuitpython](<https://devfeed.tech/tags/circuitpython.md>), [circuitpython-turbo](<https://devfeed.tech/tags/circuitpython-turbo.md>), [computer-graphics](<https://devfeed.tech/tags/computer-graphics.md>), [fruit-jam](<https://devfeed.tech/tags/fruit-jam.md>), [graphics](<https://devfeed.tech/tags/graphics.md>), [guide](<https://devfeed.tech/tags/guide.md>), [models](<https://devfeed.tech/tags/models.md>), [rendering](<https://devfeed.tech/tags/rendering.md>), [shaders](<https://devfeed.tech/tags/shaders.md>), [siggraph](<https://devfeed.tech/tags/siggraph.md>), [stanford](<https://devfeed.tech/tags/stanford.md>), [utah](<https://devfeed.tech/tags/utah.md>), [voxel](<https://devfeed.tech/tags/voxel.md>)

### AI overview

The guide runs classic computer graphics demos in CircuitPython on the Fruit Jam, using CircuitPython Turbo to pre-compile math-intensive code for speed. It features Voxel Space, Cornell Box path-trace rendering, metaballs, and shader-based 3D models of the Utah Teapot and Stanford bunny. The supplied text does not give setup instructions or performance measurements.

### Source excerpt

It's time to run some classic computer graphics demos in CircuitPython on the Fruit Jam. You'll feel like you're right back at SIGGRAPH in the golden olden days of CGI! By using CircuitPython Turbo you can pre-compile some intensely math-y bits of code for maximum speed. Check out these classic demos of Voxel Space, Cornell [...]

## Can AI Write CAD? Testing LLM-Generated 3D Models for Manufacturability

DevFeed: [Can AI Write CAD? Testing LLM-Generated 3D Models for Manufacturability](<https://devfeed.tech/articles/can-ai-write-cad-testing-llm-generated-3d-models-for-manufacturability-112508.md>)

Original publisher: [Read original article](<https://hackernoon.com/can-ai-write-cad-testing-llm-generated-3d-models-for-manufacturability?source=rss>)

Author: Melody Cole

Published: 2026-11-02T12:48:11Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [CadQuery](<https://devfeed.tech/topics/cadquery.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-3d-model-generation](<https://devfeed.tech/tags/ai-3d-model-generation.md>), [ai-for-engineering-design](<https://devfeed.tech/tags/ai-for-engineering-design.md>), [ai-generated-cad](<https://devfeed.tech/tags/ai-generated-cad.md>), [cad](<https://devfeed.tech/tags/cad.md>), [cadquery](<https://devfeed.tech/tags/cadquery.md>), [hackernoon-top-story](<https://devfeed.tech/tags/hackernoon-top-story.md>), [llm](<https://devfeed.tech/tags/llm.md>), [mechanical-engineering](<https://devfeed.tech/tags/mechanical-engineering.md>), [parametric-modeling](<https://devfeed.tech/tags/parametric-modeling.md>), [parts](<https://devfeed.tech/tags/parts.md>), [plan](<https://devfeed.tech/tags/plan.md>), [rules](<https://devfeed.tech/tags/rules.md>), [test-plan](<https://devfeed.tech/tags/test-plan.md>), [testing](<https://devfeed.tech/tags/testing.md>)

### AI overview

The article sets out a reproducible plan to test whether LLM-generated CadQuery scripts produce usable parametric CAD, but reports no experiment results yet. Five parts--an L-bracket, shaft coupling, spur gear, electronics enclosure, and bolt-nut-plate assembly--will be tested from fixed prompts, first with one attempt and then with up to three repair prompts. The rubric checks execution, solid validity, dimensions, parametric updates, process-specific digital manufacturability, STEP/STL exports, and repair effort; manual edits count separately. The author illustrates design intent with a parameterized L-bracket script whose geometry is checked against hand-calculated volume and bounding-box dimensions. DFM checks differ by process: FDM rules cover wall thickness, overhangs, hole allowance, and clearances; CNC checks cover tool access, internal radii, and deep narrow holes. Manufacturability is digital unless physical fabrication is explicitly reported. The planned study is small, limited to CadQuery and selected model versions, and includes subjective engineering review.

### Source excerpt

A student's test plan for checking whether LLMs can write usable parametric CAD: five parts, fixed pass/fail rules, and manufacturability checks.

## Adaptive Calibration of RF Digital Twins via Budget-Constrained Radio Measurement Selection

DevFeed: [Adaptive Calibration of RF Digital Twins via Budget-Constrained Radio Measurement Selection](<https://devfeed.tech/articles/adaptive-calibration-of-rf-digital-twins-via-budget-constrained-radio-measurement-selection-104197.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.36406>)

Author: Yalin E. Sagduyu, Tugba Erpek, Hossein Jafari

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [communications](<https://devfeed.tech/topics/communications.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>)

Tags: [3d-modeling](<https://devfeed.tech/tags/3d-modeling.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [blender](<https://devfeed.tech/tags/blender.md>), [budget](<https://devfeed.tech/tags/budget.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [digital-twins](<https://devfeed.tech/tags/digital-twins.md>), [eess-sp](<https://devfeed.tech/tags/eess-sp.md>), [measurement](<https://devfeed.tech/tags/measurement.md>), [monte-carlo](<https://devfeed.tech/tags/monte-carlo.md>), [online](<https://devfeed.tech/tags/online.md>), [openstreetmap](<https://devfeed.tech/tags/openstreetmap.md>), [physics](<https://devfeed.tech/tags/physics.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [radio](<https://devfeed.tech/tags/radio.md>), [ray-tracing](<https://devfeed.tech/tags/ray-tracing.md>), [rf](<https://devfeed.tech/tags/rf.md>), [sampling](<https://devfeed.tech/tags/sampling.md>), [select](<https://devfeed.tech/tags/select.md>), [selection](<https://devfeed.tech/tags/selection.md>), [strategies](<https://devfeed.tech/tags/strategies.md>), [uncertainty](<https://devfeed.tech/tags/uncertainty.md>)

### AI overview

The study finds that adaptive and structure-aware selection of radio measurement locations improves mean and worst-case RF digital twin calibration accuracy, especially with small measurement budgets. It builds a physics-based pipeline from OpenStreetMap geospatial data, Blender 3D models, and Sionna deterministic ray tracing, then calibrates its path-loss predictions against software-defined radio measurements. Locations are selected online to estimate a calibration offset. Compared approaches include random sampling, rank-structured sampling with balanced coverage, quasi-Monte Carlo ranked selection, progressive structure-aware allocation, and adaptive uncertainty-driven sampling with estimator stabilization. The supplied abstract does not provide quantitative results.

### Source excerpt

arXiv:2610.36406v1 Announce Type: new Abstract: Radio-frequency (RF) digital twins (DTs) enable site-specific wireless propagation prediction by explicitly reconstructing the physical environment and modeling electromagnetic interactions. Although physics-based DTs reduce reliance on exhaustive measurements, systematic bias relative to real radio data arises from environmental uncertainty, material inaccuracies, and geometric abstractions. Calibration using field measurements is therefore necessary but costly under limited sampling budgets. This paper studies active RF DT calibration, in which measurement locations are selected sequentially and in an online manner to estimate a calibration offset under strict measurement budget constraints. A physics-based RF DT pipeline is developed, integrating semantic geospatial data from OpenStreetMap, 3D modeling in Blender, and deterministic ray tracing in Sionna to capture dominant building and foliage effects. This RF DT is calibrated using path-loss measurements collected with software-defined radios. Multiple online calibration strategies that select radio measurement locations are compared, including random sampling, rank-structured sampling with balanced coverage, quasi-Monte Carlo ranked selection, progressive structure-aware allocation, and fully adaptive uncertainty-driven sampling with estimator stabilization. Results demonstrate that adaptive and structure-aware schemes significantly improve both mean and worst-case calibration accuracy, particularly in the low-budget regime for radio measurements.

## DIP-CAD: A Design-Intent-Preserving Agent Harness for Parametric CAD Modeling

DevFeed: [DIP-CAD: A Design-Intent-Preserving Agent Harness for Parametric CAD Modeling](<https://devfeed.tech/articles/dip-cad-a-design-intent-preserving-agent-harness-for-parametric-cad-modeling-103008.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.22688>)

Author: Xi Cheng, Chenxi Zhai, Hang Cheng, Mingyu Fan, Pingfa Feng, Long Zeng

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [3D](<https://devfeed.tech/topics/3d.md>), [Data Quality](<https://devfeed.tech/topics/data-quality.md>)

Tags: [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [cad](<https://devfeed.tech/tags/cad.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [reference](<https://devfeed.tech/tags/reference.md>), [vision](<https://devfeed.tech/tags/vision.md>), [vision-language-model](<https://devfeed.tech/tags/vision-language-model.md>)

### AI overview

DIP-CAD targets parametric CAD models that retain design intent when parameters change, rather than optimizing only the initial shape. Its agent combines vision-language reasoning with CAD kernel operations: ID-based references bind commands to selected faces, edges, or vertices, while a local-coordinate bridge supports sketch placement and constraints preserve relationships within sketches and to projected geometry. The authors also introduce GERD, a dataset format linking stepwise commands and intermediate models through explicit geometry references. On GERD-EVL and a DeepCAD test subset, reported mIoU gains were 11.1% and 5.6% for static generation, and 7.0% and 4.2% in parameter-editing evaluations, respectively.

### Source excerpt

arXiv:2609.22688v3 Announce Type: replace-cross Abstract: Parametric CAD modeling requires not only matching the target shape, but also preserving design intent under parameter edits. However, most existing methods focus on improving static shape generation accuracy, while the dependencies that govern later edits are often overlooked. To tackle this issue, we present DIP-CAD, a design-intent-preserving agent harness for generating parametric CAD models from images. DIP-CAD combines vision-language model reasoning with CAD kernel operations to establish dependencies that encode the design intent. In parametric CAD, these dependencies are mainly established through geometry references in modeling commands and constraints in parametric sketches. At the command level, ID-based explicit geometry reference binds modeling commands to selected faces, edges, or vertices. At the sketch level, a local-coordinate bridge ensures accurate sketch placement, providing the basis for correctly establishing sketch constraints. Constraints among sketch primitives and constraints to external projected geometry further preserve both internal sketch relationships and dependencies on existing geometry. To provide a more comprehensive data foundation for parametric CAD modeling tasks, we introduce the Geometry Explicit Reference Dataset (GERD), whose structured data format links stepwise modeling commands to intermediate CAD models through explicit geometry references. On GERD-EVL and a DeepCAD test subset, DIP-CAD improves mIoU for static model generation by 11.1% and 5.6%, respectively. In parameter-editing evaluations, the corresponding mIoU improvements are 7.0% and 4.2%. Case studies further demonstrate how parameter edits drive shape updates while preserving design intent.

## AcoustiPrint: Physics-Guided Neural Design of Manufacturable Acoustic Structures

DevFeed: [AcoustiPrint: Physics-Guided Neural Design of Manufacturable Acoustic Structures](<https://devfeed.tech/articles/acoustiprint-physics-guided-neural-design-of-manufacturable-acoustic-structures-96935.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.30411>)

Author: Shanmuka Sadhu, Harshvardhan C. Takawale, Yehia Zakaria, Ahmed Allam, Nirupam Roy

Published: 2026-10-23T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [3D](<https://devfeed.tech/topics/3d.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>)

Tags: [additive-manufacturing](<https://devfeed.tech/tags/additive-manufacturing.md>), [connectivity](<https://devfeed.tech/tags/connectivity.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [design](<https://devfeed.tech/tags/design.md>), [inverse-design](<https://devfeed.tech/tags/inverse-design.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [manufacturing](<https://devfeed.tech/tags/manufacturing.md>), [material](<https://devfeed.tech/tags/material.md>), [neural](<https://devfeed.tech/tags/neural.md>), [physics](<https://devfeed.tech/tags/physics.md>), [physics-informed](<https://devfeed.tech/tags/physics-informed.md>), [ultrasound](<https://devfeed.tech/tags/ultrasound.md>)

### AI overview

AcoustiPrint jointly designs 3D geometry and material composition while accounting for fabrication constraints during physics-based optimization. It represents structures with an implicit neural representation and applies a printability operator--enforcing layer-wise self-support, discrete material selection, and whole-body connectivity--before evaluating each candidate's acoustic response. Surrogate gradients enable backpropagation through these non-differentiable operations, while a self-supervised objective progressively moves designs toward printability. In personalized transcranial focused ultrasound experiments, the authors report manufacturable structures with improved focal accuracy over density-based and phase-based baselines. The supplied abstract does not provide quantitative results or implementation details.

### Source excerpt

arXiv:2610.30411v1 Announce Type: new Abstract: Recent work in additive manufacturing and neural inverse design enables the creation of complex three-dimensional structures to manipulate physical fields, yet these designs must also adhere to discrete, non-differentiable fabrication constraints. Current methods limit the design space by imposing differentiable soft manufacturability loss penalties, or by fixing structures through post-processing, causing a discrepancy between the geometry optimized by the physics model and the final fabricated result. Thus, we present AcoustiPrint, a physics-informed neural architecture for constrained inverse design that represents three-dimensional geometries with an implicit neural representation (INR) and passes each candidate through a printability operator before evaluating its final response. The printability operator executes layer-wise self-support, discrete material selection, and whole-body connectivity, assuring fabrication feasibility. To allow for backpropagation through the discrete non-differentiable operations, we use surrogate gradients for the backward pass and a self-supervised printability objective that progressively drives the INR toward a valid design domain. We demonstrate AcoustiPrint for personalized transcranial focused ultrasound, where inter-patient differences in acoustic properties and head geometry deform wave propagation and requires patient-specific acoustic focusing. AcoustiPrint jointly optimizes three-dimensional geometry and material composition through differentiable wave physics while ensuring manufacturability. Experiments show manufacturable acoustic structures with enhanced focal accuracy and over density-based and phase-based baselines, demonstrating a generalized methodology for neural design through non-differentiable manufacturing constraints and differentiable physics.

## SolidCraft is Parametric, Automation-friendly CAD for Desktop and Browser

DevFeed: [SolidCraft is Parametric, Automation-friendly CAD for Desktop and Browser](<https://devfeed.tech/articles/solidcraft-is-parametric-automation-friendly-cad-for-desktop-and-browser-89339.md>)

Original publisher: [Read original article](<https://hackaday.com/2026/10/17/solidcraft-is-parametric-automation-friendly-cad-for-desktop-and-browser/>)

Author: Donald Papp

Published: 2026-10-17T11:00:51Z

Content type: news

Language: en

Sources: [Hackaday](<https://devfeed.tech/sources/hackaday.md>)

Topics: [3D](<https://devfeed.tech/topics/3d.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [CadQuery](<https://devfeed.tech/topics/cadquery.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-modeling](<https://devfeed.tech/tags/3d-modeling.md>), [cad](<https://devfeed.tech/tags/cad.md>), [development](<https://devfeed.tech/tags/development.md>), [json](<https://devfeed.tech/tags/json.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [software-hacks](<https://devfeed.tech/tags/software-hacks.md>), [web-app](<https://devfeed.tech/tags/web-app.md>)

### AI overview

SolidCraft is an open-source parametric CAD suite in early development, with sketching, solid modeling, constraints, and a feature timeline that rebuilds dependent features when values change. Written in Rust, it runs as a desktop or browser app and exposes JSON-command interfaces, a headless CLI, and an MCP server for AI-agent use.

### Source excerpt

If you're looking to try a new, open source 3D modeling CAD suite, especially one with automation-friendly interfaces, take a look at SolidCraft. It's under development but there's support for ...read more

## Cinema 4D adds procedural scattering, more realistic liquids, and faster rendering

DevFeed: [Cinema 4D adds procedural scattering, more realistic liquids, and faster rendering](<https://devfeed.tech/articles/cinema-4d-adds-procedural-scattering-more-realistic-liquids-and-faster-rendering-88613.md>)

Original publisher: [Read original article](<https://www.techspot.com/downloads/5681-maxon-cinema-4d.html>)

Author: Ivan Franco

Published: 2026-10-16T13:54:00Z

Content type: release

Language: en

Sources: [TechSpot](<https://devfeed.tech/sources/techspot.md>)

Topics: [3D rendering](<https://devfeed.tech/topics/3d-rendering.md>), [GPU rendering](<https://devfeed.tech/topics/gpu-rendering.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>)

Tags: [performance](<https://devfeed.tech/tags/performance.md>), [procedural](<https://devfeed.tech/tags/procedural.md>), [redshift](<https://devfeed.tech/tags/redshift.md>), [simulations](<https://devfeed.tech/tags/simulations.md>)

### AI overview

Cinema 4D 2027 adds procedural scattering, Liquid FX for foam, spray and bubbles, and new node-based fields and effectors. Redshift improvements address GPU memory management and rendering responsiveness, alongside expanded CAD imports, workflow changes and bug fixes.

### Source excerpt

Cinema 4D 2027 introduces a new procedural scattering system for creating detailed environments with vegetation, rocks, and other objects. The update also brings Liquid FX, which automatically generates foam, spray, and bubbles for more realistic fluid simulations, alongside Redshift performance improvements, expanded CAD support, and new node-based tools. Read Entire Article

## InstructMesh lets users edit AI-generated 3D models before fabrication

DevFeed: [InstructMesh lets users edit AI-generated 3D models before fabrication](<https://devfeed.tech/articles/new-tool-lets-users-repair-ai-generated-3d-models-then-fabricate-them-just-the-way-they-want-63745.md>)

Original publisher: [Read original article](<https://news.mit.edu/2026/instructmesh-tool-lets-users-repair-ai-3d-models-then-fabricate-them-1001>)

Author: Alex Shipps | MIT CSAIL

Published: 2026-10-01T22:00:00Z

Content type: news

Language: en

Sources: [MIT AI News](<https://devfeed.tech/sources/mit-ai-news.md>)

Topics: [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [generative-ai-tools](<https://devfeed.tech/topics/generative-ai-tools.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>)

Tags: [3-d-printing](<https://devfeed.tech/tags/3-d-printing.md>), [3d-printing](<https://devfeed.tech/tags/3d-printing.md>), [3d-reconstruction](<https://devfeed.tech/tags/3d-reconstruction.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [computer-science-and-artificial-intelligence-laboratory-csail](<https://devfeed.tech/tags/computer-science-and-artificial-intelligence-laboratory-csail.md>), [computer-science-and-technology](<https://devfeed.tech/tags/computer-science-and-technology.md>), [design](<https://devfeed.tech/tags/design.md>), [electrical-engineering-and-computer-science-eecs](<https://devfeed.tech/tags/electrical-engineering-and-computer-science-eecs.md>), [faraz-faruqi](<https://devfeed.tech/tags/faraz-faruqi.md>), [generative-3d-models](<https://devfeed.tech/tags/generative-3d-models.md>), [gpt-4](<https://devfeed.tech/tags/gpt-4.md>), [instructmesh](<https://devfeed.tech/tags/instructmesh.md>), [latent-editing](<https://devfeed.tech/tags/latent-editing.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mit-csail](<https://devfeed.tech/tags/mit-csail.md>), [mit-eecs](<https://devfeed.tech/tags/mit-eecs.md>), [mit-schwarzman-college-of-computing](<https://devfeed.tech/tags/mit-schwarzman-college-of-computing.md>), [personal-fabrication](<https://devfeed.tech/tags/personal-fabrication.md>), [school-of-architecture-and-planning](<https://devfeed.tech/tags/school-of-architecture-and-planning.md>), [school-of-engineering](<https://devfeed.tech/tags/school-of-engineering.md>), [stefanie-mueller](<https://devfeed.tech/tags/stefanie-mueller.md>), [thingiverse](<https://devfeed.tech/tags/thingiverse.md>), [trellis](<https://devfeed.tech/tags/trellis.md>)

### AI overview

InstructMesh combines TRELLIS and GPT-4 to generate 3D models and let users refine them through natural language and interactive controls before fabrication. In the reported evaluation, novices identified and fixed structural flaws around 90 percent of the time, as reviewed by an expert. Possible future additions include physics simulations and augmented reality integration.

### Source excerpt

"InstructMesh" can generate designs for everyday objects that are easy to edit and fabricate for both experts and newcomers to 3D modeling.

## Storyboarding the future of design and creativity

DevFeed: [Storyboarding the future of design and creativity](<https://devfeed.tech/articles/storyboarding-the-future-of-design-and-creativity-9490.md>)

Original publisher: [Read original article](<https://www.figma.com/blog/adobe-figma-storyboarding-the-future/>)

Author: Yuhki Yamashita

Published: 2023-10-26T00:00:00Z

Content type: opinion

Language: en

Sources: [Figma Blog](<https://devfeed.tech/sources/figma-blog.md>)

Topics: [Figma](<https://devfeed.tech/topics/figma.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [App](<https://devfeed.tech/topics/app.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [adobe](<https://devfeed.tech/tags/adobe.md>), [ai](<https://devfeed.tech/tags/ai.md>), [creativity](<https://devfeed.tech/tags/creativity.md>), [design](<https://devfeed.tech/tags/design.md>), [figma](<https://devfeed.tech/tags/figma.md>), [fonts](<https://devfeed.tech/tags/fonts.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [image](<https://devfeed.tech/tags/image.md>), [lighting](<https://devfeed.tech/tags/lighting.md>), [marketing](<https://devfeed.tech/tags/marketing.md>), [product](<https://devfeed.tech/tags/product.md>), [ui](<https://devfeed.tech/tags/ui.md>)

### AI overview

The article imagines a future in which Figma and Adobe tools work together across storyboarding, 3D design, generative AI, prototypes, video, and shared design systems.

### Source excerpt

Editor's Note: On December 18, 2023, Figma and Adobe ended our pending acquisition, as we no longer saw a path toward regulatory approval of the deal. Read more here.

## A Review of Generative Art, Blogging, Work, and Side Projects in 2021

DevFeed: [A Review of Generative Art, Blogging, Work, and Side Projects in 2021](<https://devfeed.tech/articles/into-2022-37290.md>)

Original publisher: [Read original article](<https://muffinman.io/blog/into-2022/>)

Author: Stanko

Published: 2022-03-04T00:00:00Z

Content type: opinion

Language: en

Sources: [Stanko Tadić](<https://devfeed.tech/sources/stanko-tadic.md>)

Topics: [generative art](<https://devfeed.tech/topics/generative-art.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [pixel](<https://devfeed.tech/topics/pixel.md>), [ibm](<https://devfeed.tech/topics/ibm.md>)

Tags: [3d-modeling](<https://devfeed.tech/tags/3d-modeling.md>), [clients](<https://devfeed.tech/tags/clients.md>), [code](<https://devfeed.tech/tags/code.md>), [generative-art](<https://devfeed.tech/tags/generative-art.md>), [ibm](<https://devfeed.tech/tags/ibm.md>), [pixel](<https://devfeed.tech/tags/pixel.md>)

### AI overview

The author reviews 2021, covering generative art, reduced blogging activity, a redesign of the site from Jekyll to Zola, work with TED and IBM Research, and side projects including 3D modeling, electronics, and a pixel art frame.

### Source excerpt

I'm super late with this post, but again, better late than never. I just couldn't find the inspiration and drive for writing last year. Generally, I lacked motivation and wasn't really productive. Generative Art # As for my art, 2021 wasn't as fruitful as the year before, but I did finish a couple of drawings. I'm still very much into it and lately I have found my drive again. AxiDraw, the pen plotter, continues to be my favorite purchase ever. Here are a couple of my plotted drawings from the last year: I wrote a separate post about the creative process behind the last drawing - Breaking down Krypton. Blog # Oh boy, did I neglect this blog last year. I wrote only four posts. But I really couldn't find the inspiration and will to write. Naturally, the number of visits dropped, and it was a little above 90K. The fact that adblockers now block Goat Analytics also had an impact on numbers. Luckily, now I have way more drive to write and keep the site updated. This February, the blog got a redesign that I planned for a long time. I wanted to add "Art" and "Projects" sections, but I kept redesigning it over and over again. Finally, when I decided to switch from JekyllI'll probably cover that in a another post. to Zola I was able to focus and finish the redesign. I did the design myself, using the thing or two I picked up from my designer colleagues. I released it as soon as I had something presentable. It was super bare bones and I'm still tweaking it and adding more personality, but nonetheless, I'm pretty satisfied with how it turned out. Fun fact, you can try my layout debug mode, I kept it in the production on purpose. Work # Last year was productive for my company as a whole. I had the pleasure of working with two clients, TED and IBM Research. In both cases, teams consisted of wonderful people and I feel proud that I was able to help them build and improve their digital products. Side projects # I tremendously enjoy these small pet projects. Generative art was a bi