# Geometry-Preserving Unsupervised Alignment for Heterogeneous Foundation Models

arXiv: https://arxiv.org/abs/2606.04385 · HTML: https://mlsanity.com/paper/2606.04385/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 40 of its 54 references that are in the map.
- First posted on arXiv 3 Jun 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 30 of 40)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023)
- [Exploiting Similarities among Languages for Machine Translation](https://mlsanity.com/paper/1309.4168/) (2013)
- [MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining](https://mlsanity.com/paper/2208.12262/) (2022)
- [SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference](https://mlsanity.com/paper/2312.01597/) (2023)
- [A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings](https://mlsanity.com/paper/1805.06297/) (2018)
- [Efficient Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2403.18293/) (2024)
- [SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing](https://mlsanity.com/paper/2312.12856/) (2023)
- [ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2408.04883/) (2024)
- [Unsupervised Alignment of Embeddings with Wasserstein Procrustes](https://mlsanity.com/paper/1805.11222/) (2018)
- [CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation](https://mlsanity.com/paper/2312.12359/) (2023)
- [DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment](https://mlsanity.com/paper/2412.16334/) (2024)
- [CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor](https://mlsanity.com/paper/2312.07661/) (2023)
- [On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?](https://mlsanity.com/paper/2405.02266/) (2024)
- [Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models](https://mlsanity.com/paper/2403.17589/) (2024)
- [Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2411.19331/) (2024)
- [Black Box Few-Shot Adaptation for Vision-Language models](https://mlsanity.com/paper/2304.01752/) (2023)
- [Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models](https://mlsanity.com/paper/2410.12790/) (2024)
- [Frustratingly Easy Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2405.18330/) (2024)

## Abstract (arXiv)

Foundation models have driven rapid progress in computer vision, yet the two dominant paradigms, vision-language foundation models (VLMs) and vision-only foundation models (VFMs), remain only partially compatible. VLMs offer language-grounded semantic alignment but are often visually coarse, while VFMs learn discriminative perceptual geometry but lack semantic grounding. We propose GPUA (Geometry-Preserving Unsupervised Alignment), a framework that integrates the complementary strengths of VFMs and VLMs. Inspired by cross-lingual alignment, GPUA treats VFM features as a visual language and learns an orthogonal mapping that translates the VFM space into the VLM semantic space, preserving geometry and narrowing the modality gap without labels or model parameter updates. GPUA is task-agnostic and requires only feature-level access to pretrained models. Experiments across diverse benchmarks demonstrate improved cross-model compatibility and strong gains in downstream zero-shot recognition and segmentation with negligible overhead. Code is available at https://github.com/Yuteam14/GPUA