# KODA: Contrastive Representation Comparison and Alignment for Vision-Language Foundation Models

arXiv: https://arxiv.org/abs/2606.04180 · HTML: https://mlsanity.com/paper/2606.04180/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 35 of its 52 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 30 of 35)

- [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)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [The Vendi Score: A Diversity Evaluation Metric for Machine Learning](https://mlsanity.com/paper/2210.02410/) (2022)
- [Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models](https://mlsanity.com/paper/2306.04675/) (2023)
- [On the Error of Random Fourier Features](https://mlsanity.com/paper/1506.02785/) (2015)
- [Towards a Scalable Reference-Free Evaluation of Generative Models](https://mlsanity.com/paper/2407.02961/) (2024)
- [An Interpretable Evaluation of Entropy-based Novelty of Generative Models](https://mlsanity.com/paper/2402.17287/) (2024)
- [Unveiling Differences in Generative Models: A Scalable Differential Clustering Approach](https://mlsanity.com/paper/2405.02700/) (2024)
- [Scendi Score: Prompt-Aware Diversity Evaluation via Schur Complement of CLIP Embeddings](https://mlsanity.com/paper/2412.18645/) (2024)
- [Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms](https://mlsanity.com/paper/2412.17622/) (2024)
- [SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE Score](https://mlsanity.com/paper/2506.10173/) (2025)
- [A Multi-Armed Bandit Approach to Online Selection and Evaluation of Generative Models](https://mlsanity.com/paper/2406.07451/) (2024)
- [PAK-UCB Contextual Bandit: An Online Learning Approach to Prompt-Aware Selection of Generative Models and LLMs](https://mlsanity.com/paper/2410.13287/) (2024)
- [Streaming Kernel PCA with tildeO(√n) Random Features](https://mlsanity.com/paper/1808.00934/) (2018)
- [Consistent Distributed Ranking of Generative Models via Kernel Distances](https://mlsanity.com/paper/2310.11714/) (2023)
- [Towards an Explainable Comparison and Alignment of Feature Embeddings](https://mlsanity.com/paper/2506.06231/) (2025)
- [Streaming Kernel Principal Component Analysis](https://mlsanity.com/paper/1512.05059/) (2015)
- [When is an Embedding Model More Promising than Another?](https://mlsanity.com/paper/2406.07640/) (2024)

## Built on by (most cited first, 2 of 2)

- [Exploring More to Solve More: Boosting Diversity in Text Diffusion Models via Entropy-Based Guidance](https://mlsanity.com/paper/2608.00024/) (2026)
- [Kernel-Based Steering of CLIP with Vision-Language Model Preferences](https://mlsanity.com/paper/2609.32203/) (2026)

## Abstract (arXiv)

Vision-language foundation models such as CLIP and SigLIP provide widely used representations for multimodal learning systems. While these models are typically compared through downstream performance, such evaluations often do not explain how their representations differ structurally. In this work, we study this problem through the task of Contrastive Embedding Clustering: identifying sample subsets that are weakly clustered under one representation but strongly clustered under another. We propose Kernel Optimization for Discrepancy Analysis (KODA), a kernel-based framework for contrastive representation comparison and alignment. KODA constructs unified multimodal kernels through modality-wise kernel composition and formulates discrepancy discovery as a constrained optimization problem that searches for coherent structures in one representation while suppressing coherence in a reference representation. This yields interpretable discrepancy directions associated with specific sample subsets and modality interactions. To scale KODA to large vision-language datasets, we develop randomized low-dimensional approximations of joint kernels using random projections, including Random Fourier Features for shift-invariant kernels. Empirically, KODA identifies consistent and interpretable discrepancy structures across vision-language representations and provides sample subsets for representation alignment. The code is available at https://github.com/yokiwuuu/KODA.