# 3D

3D technology is used in a wide range of fields, including film, video games, architecture, engineering, and product design. It allows designers to create digital models of objects that can be manipulated and rendered in three dimensions. 3D modeling software is used to create and manipulate 3D models, and 3D animation software is used to create movement and effects within those models. 3D technology has also been adopted for use in 3D printing, where physical objects can be created from digital models.

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

## Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth

DevFeed: [Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth](<https://devfeed.tech/articles/depth-pro-2-sharp-and-temporally-consistent-metric-monocular-depth-145199.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26603>)

Author: Peiyun Hu, Marko Mihajlovic, Lyndon Duong, Lahav Lipson, Wei Dong, Ama\\"el Delaunoy, Stephan R. Richter, Vladlen Koltun

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

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

Topics: [Image](<https://devfeed.tech/topics/image.md>), [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [code](<https://devfeed.tech/tags/code.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [depth-estimation](<https://devfeed.tech/tags/depth-estimation.md>), [frontier](<https://devfeed.tech/tags/frontier.md>), [images](<https://devfeed.tech/tags/images.md>), [maps](<https://devfeed.tech/tags/maps.md>), [metric](<https://devfeed.tech/tags/metric.md>), [models](<https://devfeed.tech/tags/models.md>), [native](<https://devfeed.tech/tags/native.md>), [network](<https://devfeed.tech/tags/network.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [sharp](<https://devfeed.tech/tags/sharp.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [trade](<https://devfeed.tech/tags/trade.md>), [train](<https://devfeed.tech/tags/train.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

Depth Pro 2 is a scalable network for estimating dense metric depth from images and video at native resolution. The authors identify a common tradeoff in prior monocular methods: multi-frame approaches tend to favor temporal consistency, while single-frame approaches favor sharp boundaries. Their model processes both images and video and is reported to deliver metric accuracy, sharpness, and temporal consistency together, outperforming prior work on those dimensions. The released model family spans a Pareto frontier across metric accuracy, sharpness, temporal consistency, and runtime; the excerpt does not provide quantitative comparisons or details on runtime.

### Source excerpt

arXiv:2611.26603v1 Announce Type: cross Abstract: We present Depth Pro 2, an approach to estimating dense metric depth for images and video at full resolution. By analyzing prior methods for monocular depth estimation, we find that they commonly trade off temporal consistency and boundary sharpness: multi-frame methods favor consistency, single-frame methods favor sharpness. To overcome this trade-off, we train a single, scalable network that processes both images and video and predicts depth maps at native resolution. Depth Pro 2 produces depth maps that are metrically accurate, sharp, and temporally consistent all at once, outperforming prior work in all of these dimensions. We release a family of models that define a new Pareto frontier in terms of metric accuracy, sharpness, temporal consistency, and runtime. We release code and weights at https://apple-aiml-research.github.io/ml-depth-pro-2/

## Infer3D: Inverse Generative Modeling Enables Robust 3D Reconstruction

DevFeed: [Infer3D: Inverse Generative Modeling Enables Robust 3D Reconstruction](<https://devfeed.tech/articles/infer3d-inverse-generative-modeling-enables-robust-3d-reconstruction-145004.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25061>)

Author: Amani Kiruga, Mark Hamilton, Joshua B. Tenenbaum, William T. Freeman, Vincent Sitzmann, Yilun Du, Ayush Tewari

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

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

Topics: [3D](<https://devfeed.tech/topics/3d.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-reconstruction](<https://devfeed.tech/tags/3d-reconstruction.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [generative](<https://devfeed.tech/tags/generative.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [ood](<https://devfeed.tech/tags/ood.md>), [robust](<https://devfeed.tech/tags/robust.md>)

### AI overview

Infer3D reconstructs 3D scenes from a single image by optimizing the latent variables of a generative model to match the input, rather than relying only on fast feedforward inference. A frozen 3D lifting network constrains optimization to a valid, multi-view-consistent 3D manifold to prevent flat outputs. On controlled synthetic and real-world tasks, the authors report better out-of-distribution reconstruction accuracy than feedforward networks trained on equal or larger datasets. Its adaptive strategy spends more test-time compute on ambiguous out-of-distribution examples while routing in-distribution inputs efficiently; the abstract does not quantify this compute or accuracy tradeoff.

### Source excerpt

arXiv:2611.25061v1 Announce Type: cross Abstract: Humans can understand the 3D structure of scenes even from highly unfamiliar or extreme viewpoints. Cognitive science suggests this generalization stems from a top-down generative inference strategy. In contrast, state-of-the-art 3D reconstruction neural networks typically rely on amortized, feedforward inference. While fast, this pattern-matching approach degrades when faced with out-of-distribution (OOD) scene conditions unseen during training. Inspired by the generative nature of human vision, we propose Infer3D, an inverse generative modeling framework that recovers the latent variables of a generative model to best match the monocular input. To prevent degenerate flat outputs, we couple the generative image prior with a frozen 3D lifting network that constrains the optimization space to a valid, multi-view-consistent 3D manifold. Across a variety of controlled synthetic and real-world tasks, Infer3D demonstrates superior OOD reconstruction accuracy compared to feedforward networks trained on equal or larger datasets. Furthermore, mirroring how human perception requires more time to process confusing stimuli, we introduce an adaptive inference strategy that expends more test-time compute on ambiguous OOD examples while efficiently routing in-distribution inputs. Project website: https://amanikiruga.github.io/infer3d-site/

## AdsNet: A Graph Neural Network for Direct Adsorption Energy Prediction

DevFeed: [AdsNet: A Graph Neural Network for Direct Adsorption Energy Prediction](<https://devfeed.tech/articles/adsnet-a-graph-neural-network-for-direct-adsorption-energy-prediction-145085.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25646>)

Author: Changzhi Ai, Frank Abild-Pedersen, Johannes Voss

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

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

Topics: [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [graph theory](<https://devfeed.tech/topics/graph-theory.md>), [3D](<https://devfeed.tech/topics/3d.md>), [Hyperparameter optimization](<https://devfeed.tech/topics/hyperparameter-optimization.md>), [concept-learning](<https://devfeed.tech/topics/concept-learning.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [automatic](<https://devfeed.tech/tags/automatic.md>), [catalyst](<https://devfeed.tech/tags/catalyst.md>), [complexity](<https://devfeed.tech/tags/complexity.md>), [computational-complexity](<https://devfeed.tech/tags/computational-complexity.md>), [cond-mat-mtrl-sci](<https://devfeed.tech/tags/cond-mat-mtrl-sci.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [contributions](<https://devfeed.tech/tags/contributions.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [dft](<https://devfeed.tech/tags/dft.md>), [energy](<https://devfeed.tech/tags/energy.md>), [fast](<https://devfeed.tech/tags/fast.md>), [framework](<https://devfeed.tech/tags/framework.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [gradient-descent](<https://devfeed.tech/tags/gradient-descent.md>), [graph](<https://devfeed.tech/tags/graph.md>), [neural](<https://devfeed.tech/tags/neural.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [physics-comp-ph](<https://devfeed.tech/tags/physics-comp-ph.md>), [prediction](<https://devfeed.tech/tags/prediction.md>)

### AI overview

AdsNet predicts adsorption energies in one forward pass using an equivariant message-passing network over adsorbate atoms and nearby surface atoms within a cutoff. Its local graph uses distances and directional vectors, so computation is decoupled from total system size while retaining sensitivity to local geometry. On 33,920 DFT structures covering 26 transition metals and six adsorbates, it reports an energy RMSE of 0.032 eV and force RMSE of 0.047 eV/Å. Automatically differentiated forces support projected-gradient relaxation with adaptive line search, and predicted energies can be decomposed into individual local-graph atom contributions. These results are reported for the described dataset; the excerpt does not provide further validation details.

### Source excerpt

arXiv:2611.25646v1 Announce Type: cross Abstract: Fast and accurate prediction of adsorption energies is critical for high-throughput computational catalyst screening, existing methods compromise either on evaluation speed (full-graph machine learning potentials) or geometric sensitivity (coordination-based models like the alpha-scheme). Here, we present AdsNet, an equivariant graph neural network that directly predicts adsorption energies in a single forward pass, which operates on a local graph restricted only to adsorbate atoms and its immediate surface neighbors within a cutoff radius. This local graph formulation decouples computational complexity from total system size while encoding continuous geometric features (interatomic distances and directional vectors) enabling sensitivity to subtle variations in local bonding environments. AdsNet adopts a message-passing architecture with scalar and vector node features over multiple interaction layers. Trained on AdsTraj, a dataset of 33,920 density functional theory (DFT) calculated structures spanning 26 transition metals and 6 adsorbates (H*, C*, O*, CO*, OH*, HOCO*), the model achieves an adsorption energy root-mean-square error (RMSE) of 0.032 eV and a force RMSE of 0.047 eV/A. Analytic forces obtained via automatic differentiation enable structure relaxation through a projected gradient descent algorithm with adaptive line search, eliminating entire geometry optimizations. Additionally, AdsNet uniquely decomposes predicted adsorption energies into contributions from individual atoms within the local adsorbate graph - an interpretability feature unattainable with conventional machine-learning potentials. AdsNet thus establishes an accurate, highly efficient, and interpretable framework for large-scale adsorption energy prediction and local interface relaxation across various material surfaces.

## Multi-View Transformer with Geometry-Guided Multi-Modal ControlNet for 3D Virtual Try-On

DevFeed: [Multi-View Transformer with Geometry-Guided Multi-Modal ControlNet for 3D Virtual Try-On](<https://devfeed.tech/articles/multi-view-transformer-with-geometry-guided-multi-modal-controlnet-for-3d-virtual-try-on-145615.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25979>)

Author: Sarthak Batra, Armin Mustafa, Adrian Hilton

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

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

Topics: [gaussian splatting](<https://devfeed.tech/topics/gaussian-splatting.md>), [3D](<https://devfeed.tech/topics/3d.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-gaussian-splatting](<https://devfeed.tech/tags/3d-gaussian-splatting.md>), [3dgs](<https://devfeed.tech/tags/3dgs.md>), [attention](<https://devfeed.tech/tags/attention.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [camera](<https://devfeed.tech/tags/camera.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [image](<https://devfeed.tech/tags/image.md>), [modal](<https://devfeed.tech/tags/modal.md>), [proximity](<https://devfeed.tech/tags/proximity.md>), [reference](<https://devfeed.tech/tags/reference.md>), [self-attention](<https://devfeed.tech/tags/self-attention.md>), [structure](<https://devfeed.tech/tags/structure.md>), [training](<https://devfeed.tech/tags/training.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [view](<https://devfeed.tech/tags/view.md>), [virtual-try-on](<https://devfeed.tech/tags/virtual-try-on.md>)

### AI overview

GS-VTON-MVT aims to keep garment details consistent across views when editing a person captured as a 3D Gaussian Splatting scene. It jointly inpaints training views using cross-view self-attention, conditions its diffusion editor on the garment image plus depth and surface normals rendered from the current 3DGS, and adapts attention between current and reference views according to camera-pose proximity. The approach addresses inconsistencies associated with independently edited views and fixed, hand-designed fusion. On 3D-VTONBench, the authors report improvements in FID, KID, LPIPS-based cross-view consistency, and user preference over general-purpose 3D editors and earlier 3D try-on methods; the excerpt gives no metric values.

### Source excerpt

arXiv:2611.25979v1 Announce Type: cross Abstract: Editing a 3D Gaussian Splatting (3DGS) capture of a person so that they wear a new garment requires every rendered view to agree on the same garment details. Existing 3D virtual try-on (VTON) pipelines, however, edit training views largely independently and fuse them with hand-designed heuristics such as manually chosen reference views and fixed attention-blending weights. The resulting inconsistencies are baked into the 3D representation and surface as texture drift, blurred prints, and implausible geometry in novel views. We present GS-VTON-MVT, a three-stage framework that combines implicit and explicit 3D reasoning for consistent 3DGS try-on. (i) A multi-view inpainting transformer jointly edits a set of training views with full cross-view self-attention, so that cross-view correspondence is learned rather than imposed. (ii) A geometry-guided multi-modal ControlNet conditions the diffusion editor on the garment image together with depth and surface normals rendered from the current 3DGS state, supplying explicit structure where visual evidence is weakest. (iii) A pose-adaptive persona-aware attention replaces the fixed blending weight between current-view and reference-view features with weights derived from camera-pose proximity. On the 3D-VTONBench benchmark, GS-VTON-MVT improves FID, KID, LPIPS-based cross-view consistency, and user preference over general-purpose 3D editors and prior 3D try-on methods.

## A Complete Geometric Message-Passing Architecture for Point Clouds

DevFeed: [A Complete Geometric Message-Passing Architecture for Point Clouds](<https://devfeed.tech/articles/a-complete-geometric-message-passing-architecture-for-point-clouds-145173.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26384>)

Author: Nadav Dym, Tal Amir, Gia Chi Dang, Christopher Morris

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

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

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

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [complete](<https://devfeed.tech/tags/complete.md>), [completeness](<https://devfeed.tech/tags/completeness.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [learning](<https://devfeed.tech/tags/learning.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [message](<https://devfeed.tech/tags/message.md>), [point](<https://devfeed.tech/tags/point.md>), [theoretical](<https://devfeed.tech/tags/theoretical.md>)

### AI overview

The paper presents a simple equivariant message-passing architecture for 3D point clouds and proves it is complete: it can distinguish inputs unless they differ only by the rigid-motion and permutation symmetries considered. Experiments show it separates challenging point clouds that distance-based message passing provably cannot distinguish. The authors argue this expressivity may be achievable without computationally intensive high-order features, and report a completeness proof for a slightly modified SEGNN as initial evidence that the approach may extend to other equivariant architectures. The supplied text is the abstract.

### Source excerpt

arXiv:2611.26384v1 Announce Type: new Abstract: Three-dimensional point clouds are a fundamental data modality, and a large family of machine learning architectures has been developed to respect their natural symmetries to rigid motions and permutations. A principled way to compare these architectures, which vary widely in complexity and cost, is through their expressive power. That is, an architecture is complete if it can distinguish any two inputs not related by the symmetries it respects. Simple distance-based message-passing networks are known to be incomplete, and while there exist complete alternatives, they typically rely on computationally intensive mechanisms like high-order representations of the rotation group or higher-order Weisfeiler-Leman-type tests. In this work, we devise a novel, simple, equivariant message-passing architecture for point clouds, and prove that it is complete. We complement our theoretical result with experiments showing that our architecture separates challenging point clouds that distance-based message passing provably cannot distinguish. Our results suggest that high-order equivariant features may not be necessary to enhance the expressivity of point cloud architectures, and can help settle completeness for other equivariant architectures for which such results are currently unknown. We give initial evidence for this by proving completeness of a slightly modified version of SEGNN.

## DabbleCAD Takes Design Offline

DevFeed: [DabbleCAD Takes Design Offline](<https://devfeed.tech/articles/dabblecad-takes-design-offline-145225.md>)

Original publisher: [Read original article](<https://hackaday.com/2026/11/19/dabblecad-takes-design-offline/>)

Author: Zoe Skyforest

Published: 2026-11-20T03:00:57Z

Content type: article

Language: en

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

Topics: [3D](<https://devfeed.tech/topics/3d.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [Local-First](<https://devfeed.tech/topics/local-first.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-design](<https://devfeed.tech/tags/3d-design.md>), [3d-printing](<https://devfeed.tech/tags/3d-printing.md>), [cad](<https://devfeed.tech/tags/cad.md>), [dabblecad](<https://devfeed.tech/tags/dabblecad.md>), [design](<https://devfeed.tech/tags/design.md>), [export](<https://devfeed.tech/tags/export.md>), [g-code](<https://devfeed.tech/tags/g-code.md>), [laser](<https://devfeed.tech/tags/laser.md>), [models](<https://devfeed.tech/tags/models.md>), [offline](<https://devfeed.tech/tags/offline.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [slicer](<https://devfeed.tech/tags/slicer.md>), [software](<https://devfeed.tech/tags/software.md>), [tool-hacks](<https://devfeed.tech/tags/tool-hacks.md>)

### AI overview

DabbleCAD is an offline, open-source design tool for 3D printing and laser cutting. Its shape-based 3D modeling is described as similar to TinkerCAD, with tools to stretch, deform, and punch holes; models export as STL or 3MF for slicing. For laser work, users can import or draw artwork, export G-code, or send it over USB to a GRBL-compatible cutter. It also converts 3D models or images into height maps for relief engraving. The article presents it as a convenient, portable option rather than a source of new design capabilities.

### Source excerpt

These days, there are all kind of online-only and in-browser CAD packages. DabbleCAD is the opposite of all that--a simple, offline, open-source design solution. DabbleCAD handles 3D design in a ...read more

## Google adds computer use capabilities to Gemini's Mac app

DevFeed: [Google adds computer use capabilities to Gemini's Mac app](<https://devfeed.tech/articles/google-adds-computer-use-capabilities-to-gemini-s-mac-app-144598.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/11/19/google-adds-computer-use-capabilities-to-geminis-mac-app/>)

Author: Maria Deutscher

Published: 2026-11-19T23:41:48Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [generative-ai-tools](<https://devfeed.tech/topics/generative-ai-tools.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [apps](<https://devfeed.tech/tags/apps.md>), [business](<https://devfeed.tech/tags/business.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [computer-use](<https://devfeed.tech/tags/computer-use.md>), [data](<https://devfeed.tech/tags/data.md>), [dots](<https://devfeed.tech/tags/dots.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [google](<https://devfeed.tech/tags/google.md>), [llm](<https://devfeed.tech/tags/llm.md>), [mac](<https://devfeed.tech/tags/mac.md>), [meta](<https://devfeed.tech/tags/meta.md>), [muse](<https://devfeed.tech/tags/muse.md>), [nasdaq-goog](<https://devfeed.tech/tags/nasdaq-goog.md>), [news](<https://devfeed.tech/tags/news.md>), [openai](<https://devfeed.tech/tags/openai.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [top-story-5](<https://devfeed.tech/tags/top-story-5.md>)

### AI overview

Gemini for Mac can carry out multi-step tasks across local apps and web services, including transferring data between them. Users invoke it with "@Computer use"; Gemini selects an app, plans the task, and can perform dozens of actions, with outputs available for follow-up projects. Work runs in a background window, with progress shown in the chat preview pane and controls for feedback, pausing, and approval of key actions. Users choose which apps Gemini can access. At launch, the feature is available in the U.S. and requires a Google AI subscription. The excerpt says Meta's Muse also works with local apps and data and can run tasks on a cloud virtual machine while the user's computer is offline; OpenAI's Dots offers a similar capability and includes business workflow automation. It presents broader Gemini availability and business features as possible future extensions.

### Source excerpt

Google LLC today released a new version of Gemini's Mac client that can interact with other apps on the user's computer. The feature is available in the U.S. on launch. It requires a Google AI subscription, which equips consumer Google accounts with a broader lineup of artificial intelligence tools. The offering also includes additional storage [...] The post Google adds computer use capabilities to Gemini's Mac app appeared first on SiliconANGLE.

## Case for Adafruit 64x32 LED Matrix - MatrixPortal M4 + Diffuser Housing #3DThursday #3DPrinting

DevFeed: [Case for Adafruit 64x32 LED Matrix - MatrixPortal M4 + Diffuser Housing #3DThursday #3DPrinting](<https://devfeed.tech/articles/case-for-adafruit-64-32-led-matrix-matrixportal-m4-diffuser-housing-3dthursday-3dprinting-144276.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/11/19/case-for-adafruit-64x32-led-matrix-matrixportal-m4-diffuser-housing-3dthursday-3dprinting/>)

Author: Jessie Mae

Published: 2026-11-19T20:00:43Z

Content type: article

Language: en

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

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

Tags: [3d-printing](<https://devfeed.tech/tags/3d-printing.md>), [adafruit](<https://devfeed.tech/tags/adafruit.md>), [bus](<https://devfeed.tech/tags/bus.md>), [case](<https://devfeed.tech/tags/case.md>), [connectors](<https://devfeed.tech/tags/connectors.md>), [diffuser](<https://devfeed.tech/tags/diffuser.md>), [display](<https://devfeed.tech/tags/display.md>), [housing](<https://devfeed.tech/tags/housing.md>), [led](<https://devfeed.tech/tags/led.md>), [led-matrix](<https://devfeed.tech/tags/led-matrix.md>), [matrix](<https://devfeed.tech/tags/matrix.md>), [metro](<https://devfeed.tech/tags/metro.md>), [mini](<https://devfeed.tech/tags/mini.md>), [p4](<https://devfeed.tech/tags/p4.md>), [panel](<https://devfeed.tech/tags/panel.md>), [point](<https://devfeed.tech/tags/point.md>), [printers](<https://devfeed.tech/tags/printers.md>), [prusa](<https://devfeed.tech/tags/prusa.md>), [remix](<https://devfeed.tech/tags/remix.md>), [rgb](<https://devfeed.tech/tags/rgb.md>), [support](<https://devfeed.tech/tags/support.md>)

### AI overview

This two-piece case houses a P4 64x32 LED matrix panel (256x128 mm), an Adafruit MatrixPortal M4 behind it, and a 260x130 mm Adafruit diffuser (product 4749) in front. The original author used the setup to display Metro train and bus times. The remix adds support for mid-point connectors and is split to fit smaller printers such as the Prusa Mini. Printing requires supports; the listed settings are 0.16 mm layers, 2 walls, and 15% infill, with an estimated 6.2 hours and 188 g of PLA across two plates. Screws and an acrylic diffuser hold-down are used; double-sided dashes may be needed.

### Source excerpt

A case that holds a P4 64x32 LED RGB matrix panel (256x128mm), an Adafruit MatrixPortal M4 behind it, and an Adafruit diffuser (product 4749, 260x130mm) in front. Original author used it for a Metro train/bus times display. Printed in two pieces so it fits smaller printers (Prusa Mini). Remix adds support for mid-point connectors. Screws [...]

## This DIY Manga Reader Looks Like an Oversized Tamagotchi

DevFeed: [This DIY Manga Reader Looks Like an Oversized Tamagotchi](<https://devfeed.tech/articles/this-diy-manga-reader-looks-like-an-oversized-tamagotchi-143963.md>)

Original publisher: [Read original article](<https://www.yankodesign.com/2026/11/19/this-diy-manga-reader-looks-like-an-oversized-tamagotchi/>)

Author: JC Torres

Published: 2026-11-19T17:20:26Z

Content type: article

Language: en

Sources: [Yanko Design](<https://devfeed.tech/sources/yanko-design.md>)

Topics: [3D](<https://devfeed.tech/topics/3d.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>), [glyph matching algorithm](<https://devfeed.tech/topics/glyph-matching-algorithm.md>)

Tags: [audio](<https://devfeed.tech/tags/audio.md>), [battery](<https://devfeed.tech/tags/battery.md>), [capacitive](<https://devfeed.tech/tags/capacitive.md>), [comics](<https://devfeed.tech/tags/comics.md>), [diy](<https://devfeed.tech/tags/diy.md>), [e-book-reader](<https://devfeed.tech/tags/e-book-reader.md>), [esp32](<https://devfeed.tech/tags/esp32.md>), [esp32-c6](<https://devfeed.tech/tags/esp32-c6.md>), [esp32-p4](<https://devfeed.tech/tags/esp32-p4.md>), [gadgets](<https://devfeed.tech/tags/gadgets.md>), [gadgets-technology-toys-diy-e-book-reader-tamagotchi](<https://devfeed.tech/tags/gadgets-technology-toys-diy-e-book-reader-tamagotchi.md>), [jpeg](<https://devfeed.tech/tags/jpeg.md>), [lcd](<https://devfeed.tech/tags/lcd.md>), [manga](<https://devfeed.tech/tags/manga.md>), [manga-reader](<https://devfeed.tech/tags/manga-reader.md>), [tamagotchi](<https://devfeed.tech/tags/tamagotchi.md>), [technology](<https://devfeed.tech/tags/technology.md>), [toys](<https://devfeed.tech/tags/toys.md>)

### AI overview

The Mega Tamagotchi is a handmade manga reader built into an oversized Tamagotchi-shaped shell, with a 4.3-inch touchscreen and a 480x800 color LCD rather than E Ink. Its turquoise buttons are decorative; readers navigate by tapping and swiping. Startup shows a pixel-art egg with chiptune audio, then a manga-cover gallery, and the reader bookmarks pages automatically. The Waveshare ESP32-P4 board uses an ESP32-C6 coprocessor and speaker, while comics are stored locally on an SD card. To load them, a companion Python tool converts PDFs into display-sized JPEG pages; the reader does not open PDFs directly. An on-screen toggle switches between color and black-and-white contrast processing. The rechargeable battery charges over USB-C. The PLA case is screw-fastened, but hot glue securing the screen may complicate replacement. Its small display can make dialogue difficult to read, and the bulky body is better suited to a bag than a keychain.

### Source excerpt

This DIY Manga Reader Looks Like an Oversized Tamagotchi Tamagotchi toys have always made a little plastic egg feel like something worth carrying around. The Mega Tamagotchi takes that familiar shape in a considerably...

## Teaching robots to carve marble sculptures

DevFeed: [Teaching robots to carve marble sculptures](<https://devfeed.tech/articles/teaching-robots-to-carve-marble-sculptures-143718.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/11/19/teaching-robots-to-carve-marble-sculptures/>)

Author: Anne Barela

Published: 2026-11-19T15:05:20Z

Content type: article

Language: en

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

Topics: [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-model](<https://devfeed.tech/tags/3d-model.md>), [art](<https://devfeed.tech/tags/art.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [block](<https://devfeed.tech/tags/block.md>), [brooklyn](<https://devfeed.tech/tags/brooklyn.md>), [demo](<https://devfeed.tech/tags/demo.md>), [embodied-ai](<https://devfeed.tech/tags/embodied-ai.md>), [history](<https://devfeed.tech/tags/history.md>), [marble](<https://devfeed.tech/tags/marble.md>), [nyc](<https://devfeed.tech/tags/nyc.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [robots](<https://devfeed.tech/tags/robots.md>), [sculpture](<https://devfeed.tech/tags/sculpture.md>), [system](<https://devfeed.tech/tags/system.md>)

### AI overview

Monumental Labs uses KUKA KR240 robots to turn a 3D model and marble block into a sculpture without a person operating the machine. The software represents the stone as a sparse voxel grid, derives a signed distance field, and plans roughing passes to remove bulk material, including tilted passes for overhangs. Finishing removes the remaining stone in offset layers, with regional toolpaths following geodesic distances along the surface. It also calculates collision-free tool orientations and joint angles and simulates the full run before machining begins--a practical safeguard when the block is costly to machine.

### Source excerpt

Monumental Labs in Greenpoint, Brooklyn has put KUKA KR240 robots to work carving marble, and the team presented the system at Embodied AI NYC. It takes a 3D model and a block of stone and produces a finished sculpture without a person running the machine. The demo piece was a magic trick in marble: a [...]

## What to Check Before Adding a Tripo Model to a Website

DevFeed: [What to Check Before Adding a Tripo Model to a Website](<https://devfeed.tech/articles/what-to-check-before-adding-a-tripo-model-to-a-website-145865.md>)

Original publisher: [Read original article](<https://www.sitepoint.com/what-to-check-before-adding-a-tripo-model-to-a-website/>)

Author: Div John

Published: 2026-11-19T12:12:38Z

Content type: article

Language: en

Sources: [SitePoint](<https://devfeed.tech/sources/sitepoint.md>)

Topics: [3D](<https://devfeed.tech/topics/3d.md>), [Website](<https://devfeed.tech/topics/website.md>), [Programming language](<https://devfeed.tech/topics/programming-language.md>), [Software Testing](<https://devfeed.tech/topics/software-testing.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-model](<https://devfeed.tech/tags/3d-model.md>), [ai](<https://devfeed.tech/tags/ai.md>), [alt-text](<https://devfeed.tech/tags/alt-text.md>), [audit](<https://devfeed.tech/tags/audit.md>), [beginner](<https://devfeed.tech/tags/beginner.md>), [browser](<https://devfeed.tech/tags/browser.md>), [budget](<https://devfeed.tech/tags/budget.md>), [command-line](<https://devfeed.tech/tags/command-line.md>), [component](<https://devfeed.tech/tags/component.md>), [compression](<https://devfeed.tech/tags/compression.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [devices](<https://devfeed.tech/tags/devices.md>), [web](<https://devfeed.tech/tags/web.md>), [website](<https://devfeed.tech/tags/website.md>)

### AI overview

AI-generated models need review and testing before they are ready for a website. The article uses a Tripo vessel as an example and recommends setting page-specific budgets for file size, triangle count and texture dimensions, then auditing GLB files with a Node.js script using glTF Transform. Rotate the model to inspect hidden surfaces and openings; compression or simplification can damage thin details, so recheck the result and confirm viewer support. Test the intended viewer at desktop and phone widths, including touch, keyboard, scrolling and slower connections. A model-viewer component offers a low-code option, while three.js provides more control with more code. Use lazy loading, a poster, useful alt text, visible controls and a static fallback. The sample budgets are illustrative, and the audit does not catch geometry defects or rights issues; passing it does not certify an asset. The excerpt presents the vessel as a prototype, not proof of browser performance, mobile behavior or export compatibility.

### Source excerpt

null Continue reading What to Check Before Adding a Tripo Model to a Website on SitePoint.

## SixthView: A Benchmark for Hidden-View Reconstruction and 3D Assembly Reasoning

DevFeed: [SixthView: A Benchmark for Hidden-View Reconstruction and 3D Assembly Reasoning](<https://devfeed.tech/articles/sixthview-a-benchmark-for-hidden-view-reconstruction-and-3d-assembly-reasoning-142719.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23891>)

Author: Pooya Khosravi, Jen-Feng Chang, Fnu Pramono

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

Content type: article

Language: en

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

Topics: [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [3D](<https://devfeed.tech/topics/3d.md>), [vlm](<https://devfeed.tech/topics/vlm.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [assembly](<https://devfeed.tech/tags/assembly.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [computer-science](<https://devfeed.tech/tags/computer-science.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [github](<https://devfeed.tech/tags/github.md>), [grid](<https://devfeed.tech/tags/grid.md>), [hidden](<https://devfeed.tech/tags/hidden.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>), [view](<https://devfeed.tech/tags/view.md>), [vision-language-models](<https://devfeed.tech/tags/vision-language-models.md>)

### AI overview

SixthView tests whether models can reconstruct an unambiguous hidden orthographic view of a 3D polycube assembly from five views and component-shape information. It includes 602 synthetic assemblies, with the target represented as a dense grid of part labels; the authors verify that each item's exact geometry and observed labels determine a unique target. On 552 fully evaluated items, exact-grid accuracy with images plus exact text ranged from 33.2% to 85.4% across three vision-language models. Adding exact text to separate images improved accuracy by 19.7-63.0 percentage points, while adding images to exact text changed it by only −0.5 to +2.1 points. Separate image panels scored 6.7-11.1 points above a merged sheet. The abstract attributes the image-only variants' added challenge to recovering shapes from occluded renderings.

### Source excerpt

arXiv:2611.23891v1 Announce Type: cross Abstract: Inferring the unseen side of a 3D assembly requires reasoning about part placement and occlusion. Different assemblies can match the observed views while producing different hidden views, leaving the target ambiguous. We introduce SixthView, a benchmark in which models predict a sixth orthographic view from five observed views and information about the component shapes. The benchmark contains 602 synthetic polycube assemblies with 2--10 parts and requires a dense grid of part labels for the missing view, allowing both exact-view and cell-level evaluation. For each item, we exhaustively verify that all legal assemblies consistent with the exact component geometry and observed label grids yield the same target view. With these inputs, the task tests symbolic assembly and coordinate reasoning. The image-only variants additionally require shape recovery from rendered views, where occlusion can make different 3D shapes look identical. We evaluate three vision-language models under four input conditions. Across 552 items with complete evaluations, exact-grid accuracy with images plus exact text ranges from 33.2% to 85.4%. Adding exact text to separate images improves accuracy by 19.7--63.0 percentage points, whereas adding images to exact text changes it by only $-0.5$ to $+2.1$ points. Separate image panels outperform a merged sheet by 6.7--11.1 points. The results show that performance depends strongly on access to exact symbolic information, with little further improvement from images once the geometry is specified. GitHub: https://github.com/facebookresearch/sixthview_benchmark

## 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.

## CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use

DevFeed: [CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use](<https://devfeed.tech/articles/cadfather-autonomous-cad-reconstruction-through-coordinated-tool-use-142573.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.09127>)

Author: Gennadiy Savrasov, Maksim Elistratov, Nikita Gavrilov, Albert Garifullin, Oleg Pavlov, Soslan Kabisov, Vladimir Frolov, Anton Konushin, Andrey Kuznetsov, Dmitrii Zhemchuzhnikov

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

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: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>), [3D](<https://devfeed.tech/topics/3d.md>), [Tool](<https://devfeed.tech/topics/tool.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [cad](<https://devfeed.tech/tags/cad.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [tool-use](<https://devfeed.tech/tags/tool-use.md>)

### AI overview

CADFather reconstructs editable parametric CAD programs from 3D meshes by coordinating complementary proposal tools with numerical refinement. A vision-language assistant inspects target and intermediate renders, selects candidate programs and tools, controls proposal counts, and decides when to stop. Proposed or refined programs are executed and evaluated for feedback; the system keeps alternative candidates and preserves the best valid result. It uses pretrained models without additional training. The abstract reports evaluation of reconstruction quality and execution validity on DeepCAD, Fusion360, MCB, CADENA-Bench, CADBench, and BenchCAD, plus analysis of computational cost and its trade-off with quality, but gives no comparative results.

### Source excerpt

arXiv:2610.09127v2 Announce Type: replace Abstract: Reconstructing an editable CAD model from a 3D shape remains a challenging engineering task. Existing methods can propose CAD operations, but no single source of proposals works equally well across different part geometries and stages of reconstruction. We introduce CADFather, an autonomous agentic system that coordinates complementary tools to recover parametric CAD programs from 3D meshes. A vision-language assistant inspects renders of the target and intermediate reconstructions, then decides which candidate CAD programs to extend, which tools to invoke, how many proposals to generate, and when to finish. Learned and algorithmic tools propose CAD operations, while numerical optimization refines the parameters of existing programs. Proposed or refined programs are executed and evaluated to provide feedback for subsequent decisions. The agent maintains alternative candidate programs for each target part and preserves the best valid result throughout reconstruction. CADFather uses pretrained generation and assistant models without additional training. We evaluate reconstruction quality and execution validity on the full DeepCAD, Fusion360, and MCB test sets, as well as on CADENA-Bench, CADBench, and BenchCAD. We additionally analyze computational cost and the trade-off between cost and reconstruction quality.

## Grounding Radiology Reports in 3D Chest CT: Results of the ReXGrounding Challenge

DevFeed: [Grounding Radiology Reports in 3D Chest CT: Results of the ReXGrounding Challenge](<https://devfeed.tech/articles/grounding-radiology-reports-in-3d-chest-ct-results-of-the-rexgrounding-challenge-142713.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23862>)

Author: Mohammed Baharoon, Mahmoud Hussain Alabbad, Sung Eun Kim, Xiaoman Zhang, Lucas Bijnens, Zirong Chen, Jiayu Wang, Xi Ouyang, Mingyang Yu, Weiqiu Jin, Xiaodan Ye, Dijia Wu, Kwang-Hyun Uhm, Inhwa Son, Ra

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

Content type: news

Language: en

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

Topics: [3D](<https://devfeed.tech/topics/3d.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [3d](<https://devfeed.tech/tags/3d.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [challenge](<https://devfeed.tech/tags/challenge.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>), [first](<https://devfeed.tech/tags/first.md>), [grounding](<https://devfeed.tech/tags/grounding.md>), [location](<https://devfeed.tech/tags/location.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [multiple](<https://devfeed.tech/tags/multiple.md>), [open-problems](<https://devfeed.tech/tags/open-problems.md>), [problems](<https://devfeed.tech/tags/problems.md>), [report](<https://devfeed.tech/tags/report.md>), [reports](<https://devfeed.tech/tags/reports.md>), [results](<https://devfeed.tech/tags/results.md>), [test](<https://devfeed.tech/tags/test.md>)

### AI overview

The ReXGrounding Challenge evaluated models that map findings from radiology reports to 3D segmentations in non-contrast chest CT. Across 300 held-out scans containing 582 findings, the best method achieved Dice 0.375 and hit rate 0.77, comparable to agreement between two radiologist groups on a 50-scan subset (Dice 0.32, hit rate 0.76). On a 100-scan pre-challenge benchmark, the winner scored Dice 0.390, above VoxTell's 0.285; five of the six top teams fine-tuned VoxTell. Performance remained weaker for non-focal findings, and instance F1 (0.34) was below inter-reader agreement (0.47). Models also sometimes placed a correctly identified abnormality in the wrong location. The abstract identifies multiple-instance findings and matching the described anatomy as continuing challenges.

### Source excerpt

arXiv:2611.23862v1 Announce Type: cross Abstract: Segmenting each reported finding in a radiology scan would allow findings to be measured and tracked over time and let AI systems generate reports that are verifiable, but so far AI models have performed poorly at this task. To advance this task, we organized the ReXGrounding Challenge at MICCAI 2026, the first challenge dedicated to it. Given a non-contrast chest CT scan and the set of findings from its report, participants trained models to produce the corresponding set of 3D segmentations. The challenge used 2,992 training and 200 validation scans from the ReXGroundingCT dataset, and evaluated methods on a held-out test set of 300 scans with 582 findings, exhaustively annotated by board-certified radiologists. In total, 48 teams from 15 countries made 760 submissions, and the best method reached a Dice of 0.375 and a hit rate of 0.77, matching agreement between two independent radiologist groups (Dice 0.32, hit rate 0.76, on a 50-scan subset). On the 100 scans of the pre-challenge benchmark, the winner reached a Dice of 0.390, against 0.285 for VoxTell, the best model before the challenge, which five of the six best teams fine-tuned. Non-focal findings remained far harder to segment than focal ones, instance F1 stayed below inter-reader agreement (0.34 vs. 0.47), and models sometimes segmented the right abnormality in the wrong location. Top methods thus match radiologist agreement in Dice, but non-focal findings, findings with multiple instances, and adherence to the anatomical location described in the text remain open problems.

## Do 3D Point Representations Encode Architectural Functions? Probing Supervised and Pretrained Models on Urban Facades

DevFeed: [Do 3D Point Representations Encode Architectural Functions? Probing Supervised and Pretrained Models on Urban Facades](<https://devfeed.tech/articles/do-3d-point-representations-encode-architectural-functions-probing-supervised-and-pretrained-models-on-urban-facades-143438.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23720>)

Author: Abdiaziz Muse, Jiju Poovvancheri

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

Content type: article

Language: en

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

Topics: [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [AI Models](<https://devfeed.tech/topics/ai-models.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [3D](<https://devfeed.tech/topics/3d.md>), [Feature Engineering](<https://devfeed.tech/topics/feature-engineering.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [building](<https://devfeed.tech/tags/building.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [elements](<https://devfeed.tech/tags/elements.md>), [features](<https://devfeed.tech/tags/features.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [function](<https://devfeed.tech/tags/function.md>), [functional](<https://devfeed.tech/tags/functional.md>), [functions](<https://devfeed.tech/tags/functions.md>), [lidar](<https://devfeed.tech/tags/lidar.md>), [linear](<https://devfeed.tech/tags/linear.md>), [models](<https://devfeed.tech/tags/models.md>), [point](<https://devfeed.tech/tags/point.md>), [pretraining](<https://devfeed.tech/tags/pretraining.md>), [transformers](<https://devfeed.tech/tags/transformers.md>)

### AI overview

On 22 mobile-LiDAR buildings labeled with 15 functional attributes per element, frozen self-supervised Utonia features reached 0.732 mAP on functionally ambiguous elements, compared with 0.610 for hand-crafted descriptors. Networks trained from scratch, including models up to 108M parameters, did not clearly surpass the descriptors. Random-weight controls scored 0.649 and 0.652; Utonia's reported pretraining gain was +0.080, with a 95% building interval of [+0.035, +0.124]. Pretrained features improved as labeled buildings increased, while descriptors and random features plateaued. Fine-tuning eroded the benefit in the tested configurations, suggesting that at this data scale function is better read from pretrained representations than learned from scratch.

### Source excerpt

arXiv:2611.23720v1 Announce Type: cross Abstract: Semantic labels say what a building element is, not what it does: two identical-looking windows on one facade may be operable or fixed, a column may carry load or only decorate. We ask whether 3D point representations encode such architectural function. On 22 mobile-LiDAR buildings with 15 functional attributes per element, we hold out entire buildings and compare hand-crafted descriptors, networks trained from scratch and frozen self-supervised point transformers. Descriptors and frozen features are read by the same linear layer. No network trained from scratch, from PointNet to a 108M-parameter PTv3, clearly exceeds the descriptors (0.610 mAP on functionally ambiguous elements), whereas frozen Utonia reaches 0.732. Random-weight controls of the same architectures (0.649 and 0.652) attribute the gain to pretraining (Utonia: +0.080, 95% building interval [+0.035, +0.124]). Pretrained features improve at every tested number of labelled buildings while descriptors and random features plateau, and, in the configurations we tested, fine-tuning erodes the benefit: at today's data scale, function is better read from pretrained representations than learned from scratch.

## RoboBuilder: Agentic Robot Co-Design with Real-world Video Feedback in the Loop

DevFeed: [RoboBuilder: Agentic Robot Co-Design with Real-world Video Feedback in the Loop](<https://devfeed.tech/articles/robobuilder-agentic-robot-co-design-with-real-world-video-feedback-in-the-loop-142711.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23855>)

Author: Ghadi Nehme, Dahyun Nam, Akshay Govind Srinivasan, Faez Ahmed

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

Content type: article

Language: en

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

Topics: [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [3D](<https://devfeed.tech/topics/3d.md>), [Robot Navigation](<https://devfeed.tech/topics/robot-navigation.md>), [Computer vision](<https://devfeed.tech/topics/computer-vision.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-printed](<https://devfeed.tech/tags/3d-printed.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [co-design](<https://devfeed.tech/tags/co-design.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [course](<https://devfeed.tech/tags/course.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [custom](<https://devfeed.tech/tags/custom.md>), [data](<https://devfeed.tech/tags/data.md>), [design](<https://devfeed.tech/tags/design.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [in-the-loop](<https://devfeed.tech/tags/in-the-loop.md>), [real-world](<https://devfeed.tech/tags/real-world.md>), [robot](<https://devfeed.tech/tags/robot.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

RoboBuilder evaluates coding agents that co-design robot hardware and programs, build designs that pass simulation, and test them on a physical obstacle course. In the reported experiments, none of 15 initial simulation-passing designs crossed the real course, motivating agents to learn simulator behavior from requested measurements and videos. Across four agents, ten obstacles, and three difficulty levels, agents solved nearly all easy obstacles and produced mechanisms not reached by the search baselines, but struggled with harder levels and the task of one robot crossing every obstacle. Only 66% of simulated passes held in reality across levels. Providing video of a real failure led agents to redesign robots, sometimes correcting the simulator, and removed 72% of level-1 and level-2 failures.

### Source excerpt

arXiv:2611.23855v1 Announce Type: new Abstract: Can AI agents design robots that work in the real world? We introduce RoboBuilder, a benchmark in which coding agents co-design a robot's hardware and program from standard parts, motors and a custom 3D-printed part, and every design that passes in simulation is built and tested on a physical course. Simulation alone is not enough: under public part data, none of 15 initial passing designs crossed the real course, so an agent learns the simulator from measurements it requests and videos of real runs. Across four frontier coding agents, ten obstacles at three difficulty levels, 16,427 simulations of 12,774 distinct robots and 135 physical robots built in an estimated 240 hours, agents solve nearly all easy obstacles and invent mechanisms our search baselines do not reach, but falter at harder levels, when one robot must cross every obstacle, and in the real world, where 66% of simulated passes hold across all levels. Closing the loop helps: shown a video of its real failure, an agent redesigns the robot, sometimes correcting its simulator, and removes 72% of level-1 and level-2 failures. RoboBuilder measures progress toward agents that engineer real machines. Project Page: https://ghadinehme.com/robobuilder.github.io/

## 3D GameDev Arena: Benchmarking Coding Agents That Plan, Build, and Playtest extreme Long-Horizon Browser Games

DevFeed: [3D GameDev Arena: Benchmarking Coding Agents That Plan, Build, and Playtest extreme Long-Horizon Browser Games](<https://devfeed.tech/articles/3d-gamedev-arena-benchmarking-coding-agents-that-plan-build-and-playtest-extreme-long-horizon-browser-games-142750.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24073>)

Author: Bizhe Bai, Jiliang Jian, Yuqing Yan, Tao Chen, Ying Wen

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

Content type: article

Language: en

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

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [browser-game](<https://devfeed.tech/topics/browser-game.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [acceptance](<https://devfeed.tech/tags/acceptance.md>), [agents](<https://devfeed.tech/tags/agents.md>), [arena](<https://devfeed.tech/tags/arena.md>), [automated](<https://devfeed.tech/tags/automated.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [bradley-terry](<https://devfeed.tech/tags/bradley-terry.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browser-game](<https://devfeed.tech/tags/browser-game.md>), [browser-games](<https://devfeed.tech/tags/browser-games.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [development](<https://devfeed.tech/tags/development.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [gamedev](<https://devfeed.tech/tags/gamedev.md>), [games](<https://devfeed.tech/tags/games.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [plan](<https://devfeed.tech/tags/plan.md>)

### AI overview

3D GameDev Arena evaluates whether coding agents can build large 3D browser games from scratch across 108 tasks in 14 genres. Each task provides a text specification and UI/UX reference images; an automated plan-implement-test-repair pipeline produces a self-contained game. Runs average about 1,000 LLM calls, while the longest reported run used 14,407 calls, 2.13 billion tokens, and 608 assets. Evaluation combines functional acceptance against the specification, agent-based QA and playtesting of presentation and playability, and blind pairwise human preference. Preliminary findings suggest long-horizon 3D game development remains unsolved, and passing code-level checks alone does not determine player preference.

### Source excerpt

arXiv:2611.24073v1 Announce Type: new Abstract: Coding agents now resolve repository issues and generate compact playable games, but whether they can build a large 3D game from scratch remains open. Such games tightly couple mechanics, scenes, assets, and interaction logic, and their quality rests on player enjoyment, which existing benchmarks rarely assess. Thus, we introduce 3D GameDev Arena, a first extreme long-horizon benchmark of 108 from-scratch game-development tasks across 14 genres. Given only a text specification and UI/UX reference images, a fully automated plan--implement--test--repair pipeline builds each task into a self-contained browser game. Runs average $\sim$1,000 LLM calls ; the longest uses 14,407 calls, 2.13B tokens, and 608 assets. Evaluation spans (1) objective code-level functional acceptance against the game specification, (2) agent-based QA and playtesting of 3D presentation and playability, and (3) blind pairwise Bradley-Terry human preference in a public arena. The preliminary findings indicate that long-horizon 3D game development remains far from solved, and code-level correctness alone does not dictate player preference. The public arena is hosted online.

## Pose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation

DevFeed: [Pose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation](<https://devfeed.tech/articles/pose6daug-physically-plausible-multi-view-object-swapping-for-robot-data-augmentation-143277.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.20118>)

Author: Jonghoon Lee, Seong Hyeon Park, Byungwoo Jeon, Minha Lee, Jinwoo Shin

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

Content type: article

Language: en

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

Topics: [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [3D](<https://devfeed.tech/topics/3d.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>)

Tags: [2d](<https://devfeed.tech/tags/2d.md>), [3d](<https://devfeed.tech/tags/3d.md>), [appearance](<https://devfeed.tech/tags/appearance.md>), [camera](<https://devfeed.tech/tags/camera.md>), [coherent](<https://devfeed.tech/tags/coherent.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [data](<https://devfeed.tech/tags/data.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [data-collection](<https://devfeed.tech/tags/data-collection.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [failure](<https://devfeed.tech/tags/failure.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [framework](<https://devfeed.tech/tags/framework.md>), [manipulation](<https://devfeed.tech/tags/manipulation.md>), [mesh](<https://devfeed.tech/tags/mesh.md>), [object](<https://devfeed.tech/tags/object.md>), [performance](<https://devfeed.tech/tags/performance.md>), [plausible](<https://devfeed.tech/tags/plausible.md>), [policies](<https://devfeed.tech/tags/policies.md>), [robot](<https://devfeed.tech/tags/robot.md>)

### AI overview

Pose6DAug creates targeted demonstrations for VLA policy failure cases by swapping the manipulated object in existing successful episodes while preserving their action trajectories. It anchors the replacement object with a mesh and temporally coherent 6D pose trajectory in 3D, enabling geometrically consistent renderings across calibrated camera views. This addresses multi-view inconsistency and implausible edits that can arise from naive 2D video editing, especially with heavy occlusion and egocentric views. The abstract reports a 16.5% success-rate improvement over the state-of-the-art baseline on novel objects while preserving in-distribution performance; on a real robot, success more than doubled relative to the base policy. These are abstract-level claims; the supplied text gives no further experimental details.

### Source excerpt

arXiv:2606.20118v3 Announce Type: replace-cross Abstract: Vision-language-action (VLA) policies have shown strong potential for general-purpose manipulation, yet they often fail on novel, out-of-distribution objects whose appearance or geometry deviates from the training distribution. The standard remedy is to collect multi-view teleoperation data for every failure case, but this scales poorly in both cost and time. We introduce Pose6DAug, a failure-driven data augmentation framework that turns existing successful episodes into targeted demonstrations for a policy's failure modes, without any new data collection. Our key insight is that each successful episode already encodes a physically valid action trajectory together with calibrated multi-view observations. By swapping only the manipulated object while preserving this trajectory, we obtain new and physically grounded demonstrations. However, the challenge lies in synthesizing object swaps, e.g., naive 2D video editing breaks multi-view consistency and physical plausibility, particularly under heavy occlusion and egocentric viewpoints. Our method instead operates directly in 3D, anchoring the target object with an explicit mesh driven by a temporally coherent 6D pose trajectory. This ensures geometrically consistent renderings across all camera views. Fine-tuning a VLA on data augmented by our method improves success rates by 16.5% relative to the state-of-the-art baseline on novel objects, while preserving in-distribution performance. On a real robot, it more than doubles the success rate of the base policy. These results show that multi-view and physically consistent augmentation is a practical path to scalable VLA generalization.

## llm-gemini 0.38

DevFeed: [llm-gemini 0.38](<https://devfeed.tech/articles/llm-gemini-0-38-143027.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/18/llm-gemini/>)

Author: Simon Willison

Published: 2026-11-18T23:59:20Z

Content type: news

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

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

Tags: [1-4](<https://devfeed.tech/tags/1-4.md>), [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-330](<https://devfeed.tech/tags/ai-2-330.md>), [also](<https://devfeed.tech/tags/also.md>), [animation](<https://devfeed.tech/tags/animation.md>), [announcement](<https://devfeed.tech/tags/announcement.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [argon](<https://devfeed.tech/tags/argon.md>), [better](<https://devfeed.tech/tags/better.md>), [brooklyn](<https://devfeed.tech/tags/brooklyn.md>), [but](<https://devfeed.tech/tags/but.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [cool](<https://devfeed.tech/tags/cool.md>), [data](<https://devfeed.tech/tags/data.md>), [discount](<https://devfeed.tech/tags/discount.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-204](<https://devfeed.tech/tags/gemini-204.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-068](<https://devfeed.tech/tags/generative-ai-2-068.md>), [google](<https://devfeed.tech/tags/google.md>), [google-421](<https://devfeed.tech/tags/google-421.md>), [has](<https://devfeed.tech/tags/has.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-655](<https://devfeed.tech/tags/llm-655.md>), [llm-release](<https://devfeed.tech/tags/llm-release.md>), [llm-release-244](<https://devfeed.tech/tags/llm-release-244.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-032](<https://devfeed.tech/tags/llms-2-032.md>), [pelican-riding-a-bicycle](<https://devfeed.tech/tags/pelican-riding-a-bicycle.md>), [pelican-riding-a-bicycle-160](<https://devfeed.tech/tags/pelican-riding-a-bicycle-160.md>), [yonkers-rising](<https://devfeed.tech/tags/yonkers-rising.md>), [yonkers-rising-4](<https://devfeed.tech/tags/yonkers-rising-4.md>)

### AI overview

Google's Gemini 4 Neon adds another pricing wrinkle to the Gemini 4 lineup: its listed rates are $3/$15 per million input/output tokens, above Carbon's temporary $2/$10 and Hydrogen's $1.50/$7.50. The author says Carbon is due to rise to $4/$20 on December 1, after which the announced ordering of Carbon, Neon, and Hydrogen by price would make sense; the announcement also omits Argon, previously priced the same as Carbon. In the author's pelican comparison, Neon looked better than Hydrogen and worse than Carbon, across tests at three reasoning levels. A separate experiment ran a prompt for a mapped Yonkers-mech animation in Google Antigravity at "extra" effort.

### Source excerpt

Release: llm-gemini 0.38 Today Google introduced Gemini 4 Neon. I wrote recently about how confusing the pricing for the Gemini 4 series was - Neon has somehow made this even worse. Previously the Gemini 4 lineup was Hydrogen, Argon, and Carbon - where Argon and Carbon were the same price, and Hydrogen was 3/4 of that price now but will be 1/4 of that price when the other two double an 1st December once their initial discount pricing expires. The Neon announcement pretends that Argon doesn't exist. Here's their new image explaining the model line-up: So the lineup now, from most to least expensive, is Carbon, Neon, Hydrogen. Except Carbon is currently half price, so right now Neon ($3/million input, $15/million output) is the most expensive of the three - then Carbon ($2/$10), then Hydrogen ($1.50/$7.50). I guess this will make more sense when Carbon doubles to $4/$20 on December 1st. I ran some pelicans through the three reasoning levels for Neon - low, medium, high. I dropped Argon from my Gemini 4 comparison grid - here's the new Gemini 4 lineup, where the Neon pelicans do look better than Hydrogen and worse than Carbon: As I've done with several recent models, I also fired the following prompt against Gemini 4 Neon on "extra" effort level in Google Antigravity: Make a three js animation where yonkers stands up as a big mech (cool stand up motion) and stomps around manhattan and queens and Brooklyn, use openstreetmap mapping data Here's the result. Tags: yonkers-rising, gemini, llm, pelican-riding-a-bicycle, ai, llms, llm-release, google, generative-ai

## MSI EdgeMesa N AI+ Review: RTX Spark N1X and 128GB in a 1.18-Liter Mini PC

DevFeed: [MSI EdgeMesa N AI+ Review: RTX Spark N1X and 128GB in a 1.18-Liter Mini PC](<https://devfeed.tech/articles/msi-edgemesa-n-ai-review-rtx-spark-n1x-and-128gb-in-a-1-18-liter-mini-pc-141149.md>)

Original publisher: [Read original article](<https://www.storagereview.com/review/msi-edgemesa-n-ai-plus-review>)

Author: Brian Beeler

Published: 2026-11-18T14:40:38Z

Content type: article

Language: en

Sources: [StorageReview.com](<https://devfeed.tech/sources/storagereview-com.md>)

Topics: [NVIDIA RTX](<https://devfeed.tech/topics/nvidia-rtx.md>), [NVIDIA Blackwell](<https://devfeed.tech/topics/nvidia-blackwell.md>), [NVMe](<https://devfeed.tech/topics/nvme.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [DGX Spark](<https://devfeed.tech/topics/dgx-spark.md>), [Image](<https://devfeed.tech/topics/image.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [10gbe](<https://devfeed.tech/tags/10gbe.md>), [aluminum](<https://devfeed.tech/tags/aluminum.md>), [arm](<https://devfeed.tech/tags/arm.md>), [blackwell](<https://devfeed.tech/tags/blackwell.md>), [end-user](<https://devfeed.tech/tags/end-user.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [memory](<https://devfeed.tech/tags/memory.md>), [mini-pc](<https://devfeed.tech/tags/mini-pc.md>), [msi](<https://devfeed.tech/tags/msi.md>), [n1x](<https://devfeed.tech/tags/n1x.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [pcie-gen5](<https://devfeed.tech/tags/pcie-gen5.md>), [review](<https://devfeed.tech/tags/review.md>), [rtx](<https://devfeed.tech/tags/rtx.md>), [rtx-spark](<https://devfeed.tech/tags/rtx-spark.md>), [ssd](<https://devfeed.tech/tags/ssd.md>), [unified-memory](<https://devfeed.tech/tags/unified-memory.md>), [windows](<https://devfeed.tech/tags/windows.md>), [windows-11](<https://devfeed.tech/tags/windows-11.md>), [windows-11-pro](<https://devfeed.tech/tags/windows-11-pro.md>), [workstation](<https://devfeed.tech/tags/workstation.md>)

### AI overview

The MSI EdgeMesa N AI+ delivers higher sustained performance and lower average CPU temperatures than tested RTX Spark laptops, while matching the ASUS ProArt GR1X mini PC in most workloads. In a 30-minute Cinebench loop it scored 7,276, 4-11% ahead of the laptops; with eight concurrent requests on Qwen3.8 27B it reached 39.8 tokens/s versus 31.9-33.8 on the laptops. Single-request AI performance was similar across systems. Its 128GB unified memory let the review run Qwen-Image 20B at Q8 and a 35B coding-agent model that the 64GB systems did not run. The tested configuration also includes a 4TB Gen5 SSD and 10GbE. Tradeoffs include fixed, non-upgradeable memory, one M.2 2242 slot, no USB-A or audio jack, and some CPU peak readings above 100°C. The advertised 120B model support was not tested; the Windows suite tested models up to 35B.

### Source excerpt

The MSI EdgeMesa N AI+ is a 1.18-liter aluminum mini PC built on NVIDIA's RTX Spark N1X, the 20-core Arm processor with a 6,144-core Blackwell RTX GPU that we had previously tested only in laptops. Our review unit carries 128GB of unified memory, a 4TB PCIe Gen5 SSD, 10GbE, and Windows 11 Pro. We ran The post MSI EdgeMesa N AI+ Review: RTX Spark N1X and 128GB in a 1.18-Liter Mini PC appeared first on StorageReview.com.

## Local Prusa Connect Cuts Out the Cloud

DevFeed: [Local Prusa Connect Cuts Out the Cloud](<https://devfeed.tech/articles/local-prusa-connect-cuts-out-the-cloud-140526.md>)

Original publisher: [Read original article](<https://hackaday.com/2026/11/18/local-prusa-connect-cuts-out-the-cloud/>)

Author: Jenny List

Published: 2026-11-18T12:00:03Z

Content type: release

Language: en

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

Topics: [Cloud](<https://devfeed.tech/topics/cloud.md>), [Advantages and Disadvantages of Cloud Service Models](<https://devfeed.tech/topics/advantages-and-disadvantages-of-cloud-service-models.md>), [hosting](<https://devfeed.tech/topics/hosting.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [3d-printer-hacks](<https://devfeed.tech/tags/3d-printer-hacks.md>), [3d-printing](<https://devfeed.tech/tags/3d-printing.md>), [api](<https://devfeed.tech/tags/api.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-services](<https://devfeed.tech/tags/cloud-services.md>), [connect](<https://devfeed.tech/tags/connect.md>), [labs](<https://devfeed.tech/tags/labs.md>), [linux](<https://devfeed.tech/tags/linux.md>), [local](<https://devfeed.tech/tags/local.md>), [local-cloud](<https://devfeed.tech/tags/local-cloud.md>), [model](<https://devfeed.tech/tags/model.md>), [network](<https://devfeed.tech/tags/network.md>), [pi](<https://devfeed.tech/tags/pi.md>), [platforms](<https://devfeed.tech/tags/platforms.md>), [printers](<https://devfeed.tech/tags/printers.md>), [prusa](<https://devfeed.tech/tags/prusa.md>), [prusa-connect](<https://devfeed.tech/tags/prusa-connect.md>), [raspberry-pi](<https://devfeed.tech/tags/raspberry-pi.md>), [run](<https://devfeed.tech/tags/run.md>), [server](<https://devfeed.tech/tags/server.md>), [service](<https://devfeed.tech/tags/service.md>)

### AI overview

Prusa has released a local version of Prusa Connect that owners can run on their own server, keeping the service closer to the printer and avoiding reliance on the vendor's cloud. The code is available under the Open Community Licence, which includes restrictions such as requiring large enterprises to use a paid version. Prebuilt versions are offered for Apple, Windows, and Linux, including Raspberry Pi architectures. It supports Prusa printers out of the box and provides a driver API for adding other models.

### Source excerpt

One of the ways 3D printing has changed over the last few years has come in the form of cloud services that exist alongside your printer. In some cases they ...read more

## 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

## Data-Driven Variable-Length Compression of 3D Representations

DevFeed: [Data-Driven Variable-Length Compression of 3D Representations](<https://devfeed.tech/articles/data-driven-variable-length-compression-of-3d-representations-141678.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21802>)

Author: Yvette Y. Lin, Sai Karthikey Pentapati, Sarvesh Sundaram, Guandao Yang, Sara Fridovich-Keil

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

Content type: article

Language: en

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

Topics: [Compression](<https://devfeed.tech/topics/compression.md>), [3D](<https://devfeed.tech/topics/3d.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [signed distance functions](<https://devfeed.tech/topics/signed-distance-functions.md>), [dataset](<https://devfeed.tech/topics/dataset.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [adapting](<https://devfeed.tech/tags/adapting.md>), [applications](<https://devfeed.tech/tags/applications.md>), [complexity](<https://devfeed.tech/tags/complexity.md>), [compression](<https://devfeed.tech/tags/compression.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data-driven](<https://devfeed.tech/tags/data-driven.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [exploits](<https://devfeed.tech/tags/exploits.md>), [fast](<https://devfeed.tech/tags/fast.md>), [fields](<https://devfeed.tech/tags/fields.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [general](<https://devfeed.tech/tags/general.md>), [inference](<https://devfeed.tech/tags/inference.md>), [leverage](<https://devfeed.tech/tags/leverage.md>), [ratio](<https://devfeed.tech/tags/ratio.md>), [shapes](<https://devfeed.tech/tags/shapes.md>), [size](<https://devfeed.tech/tags/size.md>), [variable](<https://devfeed.tech/tags/variable.md>)

### AI overview

The method learns dataset-wide structure to compress 3D representations at variable lengths, adapting each shape's representation size to its complexity through fast feed-forward inference. It works on general latent representations and is reported to improve rate-distortion for both meshes and signed distance fields. The supplied text does not include quantitative results or details of the evaluation.

### Source excerpt

arXiv:2611.21802v1 Announce Type: cross Abstract: Compressing 3D shapes is important for the efficiency of many applications, yet existing methods either cannot leverage dataset-level statistics or use a fixed compression ratio for all shapes. We propose a learned variable-length compression method that exploits structure across a training dataset while adapting compressed representation size to individual shape complexity using only fast feed-forward inference. Our method operates on general latent representations and improves rate-distortion for both meshes and signed distance fields. Code is available at https://github.com/voilalab/varlen-3D.

[Next page](<https://devfeed.tech/topics/3d.md?cursor=WyIyMDI2LTExLTE4VDA1OjAwOjAwKzAwOjAwIiwgImM3Mjk5MzU5LWJhODktNGI4ZC04YzIyLTdmOTU5ZWM2MTkxOCJd>)