Update model card

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},

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
+<div class="model-card-header" markdown>
 
 ![EmbeddingGemma 2 banner](../../assets/embeddinggemma/embeddinggemma2_banner.png)
 
-[Hugging Face](https://huggingface.co/google/embeddinggemma-2) |
-[GitHub](https://github.com/google-gemma) |
-[Launch Blog](https://blog.google/innovation-and-ai/technology/developers-tools/embeddinggemma-2) |
-[Documentation](index.md)
+[Hugging Face](https://huggingface.co/google/embeddinggemma-2) \|
+[GitHub](https://github.com/google-gemma) \|
+[Launch Blog](https://blog.google/innovation-and-ai/technology/developers-tools/embeddinggemma-2) \|
+[Documentation](index.md) \|
+[Technical Report](https://arxiv.org/abs/2610.37364)
 
-**License** : [Apache 2.0](../../resources/apache-2.md) | **Authors** : [Google DeepMind](https://deepmind.google/models/gemma/)
+**License** : [Apache 2.0](https://gemma.ai/resources/apache-2) \| **Authors** : [Google DeepMind](https://deepmind.google/models/gemma/)
+
+</div>
 
 **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"

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},

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},

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},

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},

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},

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},

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},

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={},

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},

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},

docs/resources/index.md

@@ -14,7 +14,7 @@ and the model collections worth bookmarking.
   <div class="card-title">Gemmaverse <span class="card-ext">↗</span></div>
   <p class="card-desc">Explore the interactive ecosystem of Gemma models, visual explainers, and research.</p>
 </a>
-<a class="card" href="https://github.com/google-gemma/gemma-cookbook" target="_blank" rel="noopener">
+<a class="card" href="https://github.com/google-gemma/cookbook" target="_blank" rel="noopener">
   <span class="card-icon">{{ icon('lucide/notebook-pen') }}</span>
   <div class="card-title">Gemma Cookbook <span class="card-ext">↗</span></div>
   <p class="card-desc">Official Jupyter notebooks covering inference, fine-tuning, RAG and function calling.</p>