Papers

Field

Top tools here

Open problems in CAD models

Long-horizon iterative 3D editing1 paper raises it · 2 address it
Real-world CAD assets are built through many sequential edits, but current methods fail to preserve unedited parts or follow instructions over long sequences.
- EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modelingraises · addresses
- 3DCodeVerse: Exploring 3D Worlds as Codeaddresses
Physical realizability and functionality2 papers raise it · 3 address it
Generated 3D structures often look plausible but cannot be built or perform their intended function in the real world.
- LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structuresraises · addresses
- Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmarkraises · addresses
- BrickBench: Evaluating Agentic Brick Designaddresses
Design intelligence for coherent 3D scenes1 paper raises it · 1 addresses it
Generating complete, usable 3D scenes requires domain-specific knowledge of physical validity, functional correctness, and layout coherence.
- Scene-Designer: Learning Design Intelligence for Agentic 3D Scene Generationraises · addresses
Autonomous CAD reconstruction from 3D shapes1 paper raises it · 1 addresses it
Recovering editable, parametric CAD programs from raw 3D meshes remains unreliable and requires human intervention.
- CADFather: Autonomous CAD Reconstruction through Coordinated Tool Useraises · addresses
Local control in 3D generation1 paper raises it · 1 addresses it
Existing 3D generation methods lack fine-grained control over geometry and appearance, limiting precise editing and customization.
- SpaceFlow: Locally Controllable 3D Generationraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

cad models · cad · parametric cad83 papers15 this week

Topics in this field

Active contributors · 90 days

Yifan ShenAssemState: Manual and Physical-State-Guided Reasoning for Zero-shot Furniture Assembly3
Kaipeng ZhangInfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation2
Zheng-Hui HuangInfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation2
Zhixiang WangInfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation2
Hao GengGNN-Guided Local Refinement for Efficient Layout Decomposition with DSA-MP2
Jiajun WuInverse Garment Design with Visual Agents2

Active contributors

Activity · 12 weeks

Coming with more sources: repos

Activity

Recent papers

All in Research →

arXiv cs.CVCodeOct 6▲ 12
SPLATIFY: Reproduce, Discover, Innovate! From Papers and Ideas to Trainable 3DGS Code
Seemandhar Jain, Keshav Gupta, Manmohan Chandraker
The rapid growth of 3D Gaussian Splatting (3DGS) research demands significant effort to reimplement papers before building on them. We introduce SPLATIFY, a multi-agent framework that converts 3DGS papers into trainable gsplat-based implementations, where generic paper-to-code methods and frontier models fail. SPLATIFY achieves this through five innovations: (1) A context-free grammar for gsplat over a modular method template with extension points for losses, densification, rendering, and optimization, constraining synthesis so generated code satisfies gsplat's architectural invariants by construction. (2) Architectural elements for faithful reproduction: fork-aware citation recovery retrieving component-level code at function-level granularity, Graph-of-Thought synthesis in topological dependency order, RAG-guided in-context example selection from over 20 verified implementations, and visual feedback combining PSNR-guided regeneration, Gaussian-level structural checks, and VLM-driven patching. (3) Knowledge-driven compositional improvement that autonomously finds weaknesses and composes complementary regularizers, losses, and densification strategies to improve upon original…
PDF arXiv Code
arXiv cs.AIOct 6
AssemState: Manual and Physical-State-Guided Reasoning for Zero-shot Furniture Assembly
Zhiyuan Qi, Jierui Li, Yifan Shen, Cheng Qian, Jiateng Liu
Multimodal large language models (MLLMs) have made significant progress in visual understanding, but precise 3D spatial reasoning integrated with physical environment remains difficult. Furniture assembly requires not only recovering step-level operations from diagrammatic manuals, but also translating semantic attachment relations into 6D pose updates that enable parts to physically interact with the environment and previously assembled components. To study this problem, we propose AssemState, a zero-shot framework for manual and physical-state-guided furniture assembly. It firstly employs anchor-guided boundary assembly states to decompose manual pages into single-part operations and recover an assembly-tree. Then, it uses iterative after-state feedback refinement to guide successive (SE(3)) updates and corrections, and validates their physical plausibility through simulation-based release tests. Experiments show that compared with the strongest prior baseline, AssemState improves F1 from 38.58\% to 62.80\% and Tree Exact Match from 28.24\% to 53.92\% for assembly-tree recovery. On 243 independently evaluated part-level operations, our proposed iterative refinement improves…
PDF arXiv
arXiv cs.GROct 6
Physics-based Sphere Packing for Lagrangian Mesh Morphing
Jiong Lin, Hod Lipson
This paper studies tetrahedral meshes as the body representation for differentiable simulation and computational design. Fixed-connectivity meshes degrade under large morphs, while remeshing from scratch discards node correspondence. We present JamTet, a physics-based sphere-packing framework for volumetric meshing and morphing. We contribute (i) a GPU-parallel mesher combining octree-hierarchical packing with constrained Delaunay tetrahedralization, producing more uniform element volumes than TetGen and fTetWild; (ii) Lagrangian mesh morphing that preserves interior-node identities by re-equilibrating the same spheres within changing shapes and rebuilding the boundary and connectivity, remaining inversion-free where fixed-connectivity and TetSphere meshes invert; and (iii) a differentiable GPU simulator in JAX, with mass-spring edges and a volumetric Neo-Hookean term, integrated with mesh morphing in a design pipeline. In soft-robot morphology design experiments, interior-node gradients improve swimming fitness by 0.73-1.07 over a matched surface-only variant, while voxelized versions of the same designs yield 32-63% lower fitness. These results establish sphere packing as a…
PDF arXiv
arXiv cs.AIOct 5
2d-fet-bench: from spatial reasoning to fet design on flakes
Dunzhi Zhou, Chengyu Zhu, Gang Qiu, Caiwen Ding
Field-effect transistor (FET) layouts on exfoliated two-dimensional flakes are typically drawn by hand for each flake, placing contacts and gates to match its position and outline in optical micrographs. To our knowledge, no executable benchmark tests whether language-model agents can perform this flake-specific construction reliably. We introduce 2D-FET-Bench V2, a benchmark of 128 layout tasks built from microscopy-derived flake contours, including hole-containing flakes and multi-flake tasks. Each task supplies a textual device specification and contour coordinates. An agent generates typed polygon and path operations rendered to GDSII. A deterministic verifier checks geometric and structural requirements, and a separate integrity check verifies that the supplied contours remain unchanged. Scripted reference layouts pass all 128 tasks, showing that every task is solvable. We evaluate six models and seven workflow and scaffold variants of GPT5.6-Luna, with five attempts per task. The best-performing configuration in the six-model panel, GPT5.6-Luna with ReAct-3, passes 62.3% of attempts and solves 80.5% of tasks at least once (coverage) and 43.8% in all five attempts…
PDF arXiv
arXiv cs.SEOct 5
A Validated Dataset and Benchmark for Coherent Multi-Diagram SysML Models
Ardalan Aryashad, Yan Jin
Systems engineers use several diagrams to describe the structure and behavior of systems. Engineers create these diagrams together to make sure that they use the same elements and remain consistent with one another. Large language models can generate diagrams as text or code, which makes it possible to create system diagrams automatically. However, their ability to generate coherent sets of diagrams is not well understood, and existing datasets and benchmarks do not directly measure this ability at scale. We introduce SEMAADB (Systems Engineering Modeling Assistant with AI Dataset and Benchmark), a dataset of 3,000 engineering contexts and 15,000 diagrams. Each context contains five connected SysML views: Requirement, Block Definition, Activity, State Machine, and Sequence. Here, a view is a diagram that presents one aspect of a system. We checked the diagram sets for consistency and valid rendering. A set of 100 contexts is also human-verified and forms the benchmark test set. We evaluate three language models on two tasks. In diagram repair, the strongest model repairs 64.3% of semantic errors . In cross-diagram update the best propagation F1 is 80.7% when a model applies one…
PDF arXiv
arXiv cs.AIOct 5
RollPlace: Improving Macro Placement via Monte Carlo Rollout Search
Qi Zhou, Guojun Liu, Guangzhi Qi, Ming Lu, Jiechu Liu +3
The application of Reinforcement Learning (RL) in Electronic Design Automation (EDA), particularly for chip placement, has attracted considerable attention in recent years. While existing machine learning (ML)-based approaches have achieved notable progress, they predominantly focus on generating optimal layouts in a single attempt, often producing solutions that require subsequent refinement. To address this limitation, we propose RollPlace, a novel and generalized macro placement framework. RollPlace adopts a two-stage optimization strategy: generating initial placement solutions via machine learning methods or heuristic-based strategies, and refining these layouts efficiently by adjusting specific macros derived from the initial stage. This strategy circumvents the sequential generation constraints inherent in traditional RL-based placement methods. Furthermore, RollPlace seamlessly integrates Monte Carlo Tree Search (MCTS) to balance exploration and exploitation, and employs a rollout mechanism for efficient local search. Extensive experiments on the ISPD 2005 benchmark demonstrate that RollPlace outperforms state-of-the-art methods. Additionally, end-to-end experimental…
PDF arXiv

Papers

Topics in this field

cad models · cad · parametric cad83 papers15 this week

Recent papers

All in Research →

arXiv cs.CVCodeOct 6▲ 12
SPLATIFY: Reproduce, Discover, Innovate! From Papers and Ideas to Trainable 3DGS Code
Seemandhar Jain, Keshav Gupta, Manmohan Chandraker
The rapid growth of 3D Gaussian Splatting (3DGS) research demands significant effort to reimplement papers before building on them. We introduce SPLATIFY, a multi-agent framework that converts 3DGS papers into trainable gsplat-based implementations, where generic paper-to-code methods and frontier models fail. SPLATIFY achieves this through five innovations: (1) A context-free grammar for gsplat over a modular method template with extension points for losses, densification, rendering, and optimization, constraining synthesis so generated code satisfies gsplat's architectural invariants by construction. (2) Architectural elements for faithful reproduction: fork-aware citation recovery retrieving component-level code at function-level granularity, Graph-of-Thought synthesis in topological dependency order, RAG-guided in-context example selection from over 20 verified implementations, and visual feedback combining PSNR-guided regeneration, Gaussian-level structural checks, and VLM-driven patching. (3) Knowledge-driven compositional improvement that autonomously finds weaknesses and composes complementary regularizers, losses, and densification strategies to improve upon original…
PDF arXiv Code
arXiv cs.AIOct 6
AssemState: Manual and Physical-State-Guided Reasoning for Zero-shot Furniture Assembly
Zhiyuan Qi, Jierui Li, Yifan Shen, Cheng Qian, Jiateng Liu
Multimodal large language models (MLLMs) have made significant progress in visual understanding, but precise 3D spatial reasoning integrated with physical environment remains difficult. Furniture assembly requires not only recovering step-level operations from diagrammatic manuals, but also translating semantic attachment relations into 6D pose updates that enable parts to physically interact with the environment and previously assembled components. To study this problem, we propose AssemState, a zero-shot framework for manual and physical-state-guided furniture assembly. It firstly employs anchor-guided boundary assembly states to decompose manual pages into single-part operations and recover an assembly-tree. Then, it uses iterative after-state feedback refinement to guide successive (SE(3)) updates and corrections, and validates their physical plausibility through simulation-based release tests. Experiments show that compared with the strongest prior baseline, AssemState improves F1 from 38.58\% to 62.80\% and Tree Exact Match from 28.24\% to 53.92\% for assembly-tree recovery. On 243 independently evaluated part-level operations, our proposed iterative refinement improves…
PDF arXiv
arXiv cs.GROct 6
Physics-based Sphere Packing for Lagrangian Mesh Morphing
Jiong Lin, Hod Lipson
This paper studies tetrahedral meshes as the body representation for differentiable simulation and computational design. Fixed-connectivity meshes degrade under large morphs, while remeshing from scratch discards node correspondence. We present JamTet, a physics-based sphere-packing framework for volumetric meshing and morphing. We contribute (i) a GPU-parallel mesher combining octree-hierarchical packing with constrained Delaunay tetrahedralization, producing more uniform element volumes than TetGen and fTetWild; (ii) Lagrangian mesh morphing that preserves interior-node identities by re-equilibrating the same spheres within changing shapes and rebuilding the boundary and connectivity, remaining inversion-free where fixed-connectivity and TetSphere meshes invert; and (iii) a differentiable GPU simulator in JAX, with mass-spring edges and a volumetric Neo-Hookean term, integrated with mesh morphing in a design pipeline. In soft-robot morphology design experiments, interior-node gradients improve swimming fitness by 0.73-1.07 over a matched surface-only variant, while voxelized versions of the same designs yield 32-63% lower fitness. These results establish sphere packing as a…
PDF arXiv
arXiv cs.AIOct 5
2d-fet-bench: from spatial reasoning to fet design on flakes
Dunzhi Zhou, Chengyu Zhu, Gang Qiu, Caiwen Ding
Field-effect transistor (FET) layouts on exfoliated two-dimensional flakes are typically drawn by hand for each flake, placing contacts and gates to match its position and outline in optical micrographs. To our knowledge, no executable benchmark tests whether language-model agents can perform this flake-specific construction reliably. We introduce 2D-FET-Bench V2, a benchmark of 128 layout tasks built from microscopy-derived flake contours, including hole-containing flakes and multi-flake tasks. Each task supplies a textual device specification and contour coordinates. An agent generates typed polygon and path operations rendered to GDSII. A deterministic verifier checks geometric and structural requirements, and a separate integrity check verifies that the supplied contours remain unchanged. Scripted reference layouts pass all 128 tasks, showing that every task is solvable. We evaluate six models and seven workflow and scaffold variants of GPT5.6-Luna, with five attempts per task. The best-performing configuration in the six-model panel, GPT5.6-Luna with ReAct-3, passes 62.3% of attempts and solves 80.5% of tasks at least once (coverage) and 43.8% in all five attempts…
PDF arXiv
arXiv cs.SEOct 5
A Validated Dataset and Benchmark for Coherent Multi-Diagram SysML Models
Ardalan Aryashad, Yan Jin
Systems engineers use several diagrams to describe the structure and behavior of systems. Engineers create these diagrams together to make sure that they use the same elements and remain consistent with one another. Large language models can generate diagrams as text or code, which makes it possible to create system diagrams automatically. However, their ability to generate coherent sets of diagrams is not well understood, and existing datasets and benchmarks do not directly measure this ability at scale. We introduce SEMAADB (Systems Engineering Modeling Assistant with AI Dataset and Benchmark), a dataset of 3,000 engineering contexts and 15,000 diagrams. Each context contains five connected SysML views: Requirement, Block Definition, Activity, State Machine, and Sequence. Here, a view is a diagram that presents one aspect of a system. We checked the diagram sets for consistency and valid rendering. A set of 100 contexts is also human-verified and forms the benchmark test set. We evaluate three language models on two tasks. In diagram repair, the strongest model repairs 64.3% of semantic errors . In cross-diagram update the best propagation F1 is 80.7% when a model applies one…
PDF arXiv
arXiv cs.AIOct 5
RollPlace: Improving Macro Placement via Monte Carlo Rollout Search
Qi Zhou, Guojun Liu, Guangzhi Qi, Ming Lu, Jiechu Liu +3
The application of Reinforcement Learning (RL) in Electronic Design Automation (EDA), particularly for chip placement, has attracted considerable attention in recent years. While existing machine learning (ML)-based approaches have achieved notable progress, they predominantly focus on generating optimal layouts in a single attempt, often producing solutions that require subsequent refinement. To address this limitation, we propose RollPlace, a novel and generalized macro placement framework. RollPlace adopts a two-stage optimization strategy: generating initial placement solutions via machine learning methods or heuristic-based strategies, and refining these layouts efficiently by adjusting specific macros derived from the initial stage. This strategy circumvents the sequential generation constraints inherent in traditional RL-based placement methods. Furthermore, RollPlace seamlessly integrates Monte Carlo Tree Search (MCTS) to balance exploration and exploitation, and employs a rollout mechanism for efficient local search. Extensive experiments on the ISPD 2005 benchmark demonstrate that RollPlace outperforms state-of-the-art methods. Additionally, end-to-end experimental…
PDF arXiv

Active contributors · 90 days

Yifan ShenAssemState: Manual and Physical-State-Guided Reasoning for Zero-shot Furniture Assembly3
Kaipeng ZhangInfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation2
Zheng-Hui HuangInfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation2
Zhixiang WangInfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation2
Hao GengGNN-Guided Local Refinement for Efficient Layout Decomposition with DSA-MP2
Jiajun WuInverse Garment Design with Visual Agents2

Activity · 12 weeks

Coming with more sources: repos

Fields · AI · updated 1h ago

CAD models

Found by the topic model: cad models.

15papers this week−25.0% vs last week

All papers · 83 With code · 12

Newest Most relevant

77 papers this month

Open problems in CAD models

Long-horizon iterative 3D editing1 paper raises it · 2 address it
Real-world CAD assets are built through many sequential edits, but current methods fail to preserve unedited parts or follow instructions over long sequences.
- EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modelingraises · addresses
- 3DCodeVerse: Exploring 3D Worlds as Codeaddresses
Physical realizability and functionality2 papers raise it · 3 address it
Generated 3D structures often look plausible but cannot be built or perform their intended function in the real world.
- LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structuresraises · addresses
- Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmarkraises · addresses
- BrickBench: Evaluating Agentic Brick Designaddresses
Design intelligence for coherent 3D scenes1 paper raises it · 1 addresses it
Generating complete, usable 3D scenes requires domain-specific knowledge of physical validity, functional correctness, and layout coherence.
- Scene-Designer: Learning Design Intelligence for Agentic 3D Scene Generationraises · addresses
Autonomous CAD reconstruction from 3D shapes1 paper raises it · 1 addresses it
Recovering editable, parametric CAD programs from raw 3D meshes remains unreliable and requires human intervention.
- CADFather: Autonomous CAD Reconstruction through Coordinated Tool Useraises · addresses
Local control in 3D generation1 paper raises it · 1 addresses it
Existing 3D generation methods lack fine-grained control over geometry and appearance, limiting precise editing and customization.
- SpaceFlow: Locally Controllable 3D Generationraises · addresses

Named by an AI from these papers' abstracts.