diff --git a/docs/models/embeddinggemma/model-card-v1.md b/docs/models/embeddinggemma/model-card-v1.md
index c218f82..2f75cec 100644
--- a/docs/models/embeddinggemma/model-card-v1.md
+++ b/docs/models/embeddinggemma/model-card-v1.md
@@ -51,7 +51,7 @@ For more technical details, refer to our paper:
### Citation
-```python
+```bibtex
@article{embedding_gemma_2025,
title={EmbeddingGemma: Powerful and Lightweight Text Representations},
publisher={Google DeepMind},
diff --git a/docs/models/embeddinggemma/model-card-v2.md b/docs/models/embeddinggemma/model-card-v2.md
index c159207..78f4bfe 100644
--- a/docs/models/embeddinggemma/model-card-v2.md
+++ b/docs/models/embeddinggemma/model-card-v2.md
@@ -4,16 +4,19 @@ description: "Model card for EmbeddingGemma 2: architecture, multimodal capabili
models: [embeddinggemma-2]
source_url: "https://ai.google.dev/gemma/docs/embeddinggemma/model_card_2.md.txt"
---
-# EmbeddingGemma 2 model card
+
**EmbeddingGemma 2** is an open multimodal embedding model built by Google DeepMind which maps text (incl. code), images, video, and audio inputs---and combinations thereof---into a single, unified 768-dimensional vector space. The model has 740M total parameters, combining a 270M parameter text model with modular vision (170M) and audio (300M) encoders.
@@ -62,12 +65,12 @@ EmbeddingGemma 2 was evaluated across text, code, vision, visual document, video
|---|---|---|---|---|
| *Text* | Massive Text Embedding Benchmark (MTEB, multilingual, v2) | Mean(Task), Multiple | 61.36 | 61.15 |
| | Massive Text Embedding Benchmark (MTEB, code, v1) | Mean(Task), NDCG@10 | 78.68 | 68.76 |
-| *Image* | Massive Image Embedding Benchmark (MIEB, lite) | Mean(TaskType), Multiple | 64.64 | - |
+| *Image* | Massive Image Embedding Benchmark (MIEB, lite) | Mean(TaskType), Multiple | 65.67 | - |
| | Massive Multimodal Embedding Benchmark (MMEB v2 - Image) | Mean(Task), Hit@1 | 57.28 | - |
| | Massive Multimodal Embedding Benchmark (MMEB v2 - VisDoc) | Mean(Task), NDCG@5 | 67.84 | - |
| *Video* | Massive Multimodal Embedding Benchmark (MMEB v2 - Video) | Mean(Task), Hit@1 | 50.67 | - |
| *Audio* | Massive Sound Embedding Benchmark (MSEB, Retrieval) | Mean(Task), MRR@10 | 69.54 | - |
-| | Massive Audio Embedding Benchmark (MAEB) *Hugging Face* | Mean(Task), Multiple | 49.39 | - |
+| | Massive Audio Embedding Benchmark (MAEB) *Hugging Face* | Mean(Task), Multiple | 49.87 | - |
### Evaluation Results with Vector Truncation
@@ -76,10 +79,10 @@ With this, model users can reduce storage requirements, with minimal quality imp
| Output Dimension | Compression Ratio | MTEB *(multilingual, v2) Mean(Task)* | MTEB *(eng, v2) Mean(Task)* | MTEB *(code, v1) Mean(Task)* | MIEB *(lite) Mean(TaskType)* | MMEB (v2) *Overall* | MSEB *(Retrieval) Mean(Task)* | MAEB *Mean(Task)* |
|---|---|---|---|---|---|---|---|---|
-| 768d (Full) | 1:1 | 61.36 | 68.46 | 78.68 | 64.64 | 59.01 | 69.54 | 49.39 |
-| 512d | 1:1.5 | 61.17 | 68.41 | 77.24 | 64.32 | 58.38 | 69.18 | 49.21 |
-| 256d | 1:3 | 60.41 | 67.78 | 76.18 | 63.13 | 56.24 | 66.76 | 48.91 |
-| 128d | 1:6 | 57.89 | 65.68 | 71.41 | 59.06 | 45.65 | 56.71 | 46.92 |
+| 768d (Full) | 1:1 | 61.36 | 68.46 | 78.68 | 65.67 | 59.01 | 69.54 | 49.87 |
+| 512d | 1:1.5 | 61.17 | 68.41 | 77.24 | 65.34 | 58.38 | 69.18 | 49.76 |
+| 256d | 1:3 | 60.41 | 67.78 | 76.18 | 64.16 | 56.24 | 66.76 | 49.13 |
+| 128d | 1:6 | 57.89 | 65.68 | 71.41 | 59.97 | 45.65 | 56.71 | 47.28 |
## Quick Start
@@ -316,4 +319,19 @@ EmbeddingGemma 2 is among the strongest multimodal embedding models under 1B par
The model is designed from the ground up for responsible AI development, like other Gemma-family models.
+## **Citation**
+
+If you find our work helpful, please consider citing it:
+
+```bibtex
+@misc{embeddinggemma2_2026,
+ title={EmbeddingGemma 2: Unified and Efficient Multimodal Representations},
+ author={Schechter Vera, Henrique and Dua, Sahil and Team, EmbeddingGemma},
+ year={2026},
+ eprint={2610.37364},
+ archivePrefix={arXiv},
+ primaryClass={cs.LG},
+ url={https://arxiv.org/abs/2610.37364}
+}
+```
--8<-- "glossary.md"
diff --git a/docs/models/gemma-1/index.md b/docs/models/gemma-1/index.md
index 62ec84d..591beba 100644
--- a/docs/models/gemma-1/index.md
+++ b/docs/models/gemma-1/index.md
@@ -41,7 +41,7 @@ state of the art AI models and helping foster innovation for everyone.
### Citation
-```python
+```bibtex
@article{gemma_2024,
title={Gemma},
url={https://www.kaggle.com/m/3301},
diff --git a/docs/models/gemma-2/index.md b/docs/models/gemma-2/index.md
index 3c984a6..ff09aab 100644
--- a/docs/models/gemma-2/index.md
+++ b/docs/models/gemma-2/index.md
@@ -41,7 +41,7 @@ state of the art AI models and helping foster innovation for everyone.
### Citation
-```python
+```bibtex
@article{gemma_2024,
title={Gemma},
url={https://www.kaggle.com/m/3301},
diff --git a/docs/models/gemma-3/index.md b/docs/models/gemma-3/index.md
index 1946b00..6a8e063 100644
--- a/docs/models/gemma-3/index.md
+++ b/docs/models/gemma-3/index.md
@@ -50,7 +50,7 @@ for everyone.
### Citation
-```python
+```bibtex
@article{gemma_2025,
title={Gemma 3},
url={https://arxiv.org/abs/2503.19786},
diff --git a/docs/models/gemma-3n/model-card.md b/docs/models/gemma-3n/model-card.md
index 2c45758..89d2712 100644
--- a/docs/models/gemma-3n/model-card.md
+++ b/docs/models/gemma-3n/model-card.md
@@ -54,7 +54,7 @@ page.
### Citation
-```python
+```bibtex
@article{gemma_3n_2025,
title={Gemma 3n},
url={https://ai.google.dev/gemma/docs/gemma-3n},
diff --git a/docs/models/gemma-4/model-card.md b/docs/models/gemma-4/model-card.md
index 42064f1..d6a3f1a 100644
--- a/docs/models/gemma-4/model-card.md
+++ b/docs/models/gemma-4/model-card.md
@@ -375,7 +375,7 @@ responsible AI development compared to similarly sized models.
If you find our work helpful, please consider citing it:
-```python
+```bibtex
@misc{gemmateam2026gemma4,
title={Gemma 4 Technical Report},
author={Gemma Team},
diff --git a/docs/models/paligemma/model-card-v1.md b/docs/models/paligemma/model-card-v1.md
index 4330b0f..eb6d427 100644
--- a/docs/models/paligemma/model-card-v1.md
+++ b/docs/models/paligemma/model-card-v1.md
@@ -50,7 +50,7 @@ PaliGemma is trained following the PaLI-3 recipes.
#### Citation
-```python
+```bibtex
@article{
title={PaliGemma: A versatile 3B VLM for transfer},
author={Lucas Beyer and Andreas Steiner and André Susano Pinto and Alexander Kolesnikov and Xiao Wang* and Daniel Salz and Maxim Neumann and Ibrahim Alabdulmohsin and Michael Tschannen and Emanuele Bugliarello and Thomas Unterthiner and Daniel Keysers and Skanda Koppula and Fangyu Liu and Adam Grycner and Alexey Gritsenko and Neil Houlsby and Manoj Kumar and Keran Rong and Julian Eisenschlos and Rishabh Kabra and Matthias Bauer and Matko Bošnjak and Xi Chen and Matthias Minderer and Paul Voigtlaender and Ioana Bica and Ivana Balazevic and Joan Puigcerver and Pinelopi Papalampidi and Olivier Henaff and Xi Xiong and Radu Soricut and Jeremiah Harmsen and Xiaohua Zhai},
diff --git a/docs/models/paligemma/model-card-v2.md b/docs/models/paligemma/model-card-v2.md
index e5c6e9a..cc5a3c7 100644
--- a/docs/models/paligemma/model-card-v2.md
+++ b/docs/models/paligemma/model-card-v2.md
@@ -51,7 +51,7 @@ Similar to the original PaliGemma model, PaliGemma 2 is trained following the
#### Citation
-```python
+```bibtex
@article{
title={PaliGemma 2: A Family of Versatile VLMs for Transfer},
author={Andreas Steiner and André Susano Pinto and Michael Tschannen and Daniel Keysers and Xiao Wang and Yonatan Bitton and Alexey Gritsenko and Matthias Minderer and Anthony Sherbondy and Shangbang Long and Siyang Qin and Reeve Ingle and Emanuele Bugliarello and Sahar Kazemzadeh and Thomas Mesnard and Ibrahim Alabdulmohsin and Lucas Beyer and Xiaohua Zhai},
diff --git a/docs/models/recurrentgemma/model-card.md b/docs/models/recurrentgemma/model-card.md
index c943fef..9b3dee2 100644
--- a/docs/models/recurrentgemma/model-card.md
+++ b/docs/models/recurrentgemma/model-card.md
@@ -39,7 +39,7 @@ Gemma and achieves faster inference when generating long sequences.
#### Citation
-```python
+```bibtex
@article{recurrentgemma_2024,
title={RecurrentGemma},
url={},
diff --git a/docs/models/shieldgemma/model-card-v1.md b/docs/models/shieldgemma/model-card-v1.md
index 9643f57..07aa282 100644
--- a/docs/models/shieldgemma/model-card-v1.md
+++ b/docs/models/shieldgemma/model-card-v1.md
@@ -94,7 +94,7 @@ filtering).
### Citation
-```python
+```bibtex
@misc{zeng2024shieldgemmagenerativeaicontent,
title={ShieldGemma: Generative AI Content Moderation Based on Gemma},
author={Wenjun Zeng and Yuchi Liu and Ryan Mullins and Ludovic Peran and Joe Fernandez and Hamza Harkous and Karthik Narasimhan and Drew Proud and Piyush Kumar and Bhaktipriya Radharapu and Olivia Sturman and Oscar Wahltinez},
diff --git a/docs/models/shieldgemma/model-card-v2.md b/docs/models/shieldgemma/model-card-v2.md
index 4de8bf7..c4e397e 100644
--- a/docs/models/shieldgemma/model-card-v2.md
+++ b/docs/models/shieldgemma/model-card-v2.md
@@ -74,7 +74,7 @@ Does the image violate the above policy? Your Answer must start with 'Yes' or 'N
### Citation
-```python
+```bibtex
@misc{zeng2025shieldgemma2robusttractable,
title={ShieldGemma 2: Robust and Tractable Image Content Moderation},
author={Wenjun Zeng and Dana Kurniawan and Ryan Mullins and Yuchi Liu and Tamoghna Saha and Dirichi Ike-Njoku and Jindong Gu and Yiwen Song and Cai Xu and Jingjing Zhou and Aparna Joshi and Shravan Dheep and Mani Malek and Hamid Palangi and Joon Baek and Rick Pereira and Karthik Narasimhan},
diff --git a/docs/resources/index.md b/docs/resources/index.md
index d8ee3d9..cf9965a 100644
--- a/docs/resources/index.md
+++ b/docs/resources/index.md
@@ -14,7 +14,7 @@ and the model collections worth bookmarking.
Gemmaverse ↗
Explore the interactive ecosystem of Gemma models, visual explainers, and research.
-
+
{{ icon('lucide/notebook-pen') }}
Gemma Cookbook ↗
Official Jupyter notebooks covering inference, fine-tuning, RAG and function calling.