AI News HubLIVE
原文

GAP3D: Generative Alignment of VLM Latents to Patch-Level Embeddings for 3D Generation

GAP3D introduces a modular diffusion-based approach that aligns VLM-generated latents directly to the patch-level feature space of a pre-trained image encoder, enabling frozen generative models to use VLMs as prompt encoders while preserving spatial structure. It trains primarily on image-text pairs, avoids large-scale 3D data, and demonstrates zero-shot multimodal capabilities, though it currently prioritizes high-level semantics over fine-grained detail.

Article intelligence

EngineersAdvanced

Key points

  • GAP3D uses diffusion to align VLM latents to image encoder patch-level features.
  • Avoids large-scale 3D data by training on general image-text pairs.
  • Shows zero-shot multimodal understanding despite text-only training.
  • Prioritizes high-level semantics; fine-grained detail remains a challenge.

Why it matters

This matters because gAP3D uses diffusion to align VLM latents to image encoder patch-level features.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.28995] GAP3D: Generative Alignment of VLM Latents to Patch-Level Embeddings for 3D Generation

[Submitted on 27 May 2026]

Title:GAP3D: Generative Alignment of VLM Latents to Patch-Level Embeddings for 3D Generation

View a PDF of the paper titled GAP3D: Generative Alignment of VLM Latents to Patch-Level Embeddings for 3D Generation, by Polytimi Anna Gkotsi and 2 other authors

View PDF HTML (experimental)

Abstract:Recent approaches integrating vision-language models (VLMs) as prompt encoders for generative model conditioning typically rely on expensive end-to-end training or map features to compressed representations, discarding the dense spatial structure required for geometry-aware tasks like 3D asset generation. To address this, we propose GAP3D, a modular, diffusion-based approach that aligns VLM-generated latents directly to the complete, patch-level feature space of a pre-trained image encoder, enabling a frozen downstream generative model to utilize a VLM as prompt encoder while maintaining a spatially structured conditioning signal. Evaluated on 3D asset generation, our method bypasses the need for large-scale 3D data by training mainly on general-domain image-text pairs. It also exhibits emergent zero-shot capabilities for multimodal prompts, despite being trained exclusively on text input. Finally, while currently prioritizing high-level semantics over fine-grained detail, GAP3D demonstrates that the representation gap between VLM and image-encoder feature spaces can be partially bridged through diffusion-based alignment, taking the first steps towards a modular integration of foundation models through generative alignment to dense embedding spaces.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2605.28995 [cs.CV]

(or arXiv:2605.28995v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2605.28995

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Polytimi Anna Gkotsi [view email] [v1] Wed, 27 May 2026 18:53:09 UTC (10,193 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled GAP3D: Generative Alignment of VLM Latents to Patch-Level Embeddings for 3D Generation, by Polytimi Anna Gkotsi and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-05

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)