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

arXiv: https://arxiv.org/abs/2605.28995 · HTML: https://mlsanity.com/paper/2605.28995/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 25 of its 31 references that are in the map.
- First posted on arXiv 27 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset](https://mlsanity.com/paper/2505.09568/) (2025)
- [DreamLLM: Synergistic Multimodal Comprehension and Creation](https://mlsanity.com/paper/2309.11499/) (2023)
- [Generating Images with Multimodal Language Models](https://mlsanity.com/paper/2305.17216/) (2023)
- [T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation](https://mlsanity.com/paper/2307.06350/) (2023)
- [Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias](https://mlsanity.com/paper/2101.07296/) (2021)
- [3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion](https://mlsanity.com/paper/2409.12957/) (2024)
- [LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation](https://mlsanity.com/paper/2403.12019/) (2024)
- [GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling](https://mlsanity.com/paper/2403.19655/) (2024)
- [UNIMO-G: Unified Image Generation through Multimodal Conditional Diffusion](https://mlsanity.com/paper/2401.13388/) (2024)
- [Progressive Compositionality in Text-to-Image Generative Models](https://mlsanity.com/paper/2410.16719/) (2024)
- [I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models](https://mlsanity.com/paper/2502.10458/) (2025)
- [An Empirical Study and Analysis of Text-to-Image Generation Using Large Language Model-Powered Textual Representation](https://mlsanity.com/paper/2405.12914/) (2024)
- [FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation](https://mlsanity.com/paper/2506.16806/) (2025)

## Abstract (arXiv)

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.