deel-ai · Agustin-Picard · Aug 6, 2026 · Aug 6, 2026 · Aug 6, 2026 · Aug 6, 2026
diff --git a/README.md b/README.md
@@ -5,10 +5,10 @@
 
 <div align="center">
     <a href="#">
-        <img src="https://img.shields.io/badge/Python-3.10, 3.11, 3.12, 3.13, 3.14-efefef">
+        <img src="https://img.shields.io/badge/Python-3.10, 3.11, 3.12, 3.13-efefef">
     </a>
     <a href="#">
-        <img src="https://img.shields.io/badge/Tensorflow-2.5, ..., 2.15-00008b">
+        <img src="https://img.shields.io/badge/Tensorflow-2.18, 2.19, 2.20-00008b">
     </a>
     <a href="https://github.com/deel-ai/xplique/actions/workflows/python-lints.yml">
         <img alt="PyLint" src="https://github.com/deel-ai/xplique/actions/workflows/python-lints.yml/badge.svg">
@@ -45,26 +45,23 @@
   ·
   <a href="https://deel-ai.github.io/xplique/latest/api/attributions/metrics/api_metrics/">Metrics</a>
   .
-  <a href="api/example_based/api_example_based/">Example-based</a>
+  <a href="https://deel-ai.github.io/xplique/latest/api/example_based/api_example_based/">Example-based</a>
 </p>
 
-> [!IMPORTANT]  
-> With the release of Keras 3.X since TensorFlow 2.16, some methods may not function as expected. We are actively working on a fix. In the meantime, we recommend using TensorFlow 2.15 or earlier versions for optimal compatibility.
+> [!NOTE]
+> **What's new in v2.0.0:** Holistic CRAFT can extract and attribute concepts from classification and object detection models through `HolisticCraftTf` and `HolisticCraftTorch`. The release also introduces framework-specific latent extractors, `LayeredModelExtractorBuilder`, `PartialExplainer`, and `EncodedData`. Xplique 2.0.0 supports Python 3.10-3.13, TensorFlow 2.18-2.20, and optional PyTorch 2.5-2.10. Detector-specific adapters are under construction in the DEEL AI organization and will be pip-installable soon.
 
 The library is composed of several modules, the _Attributions Methods_ module implements various methods (e.g Saliency, Grad-CAM, FEM, Integrated-Gradients...), with explanations, examples and links to official papers.
 The _Feature Visualization_ module allows to see how neural networks build their understanding of images by finding inputs that maximize neurons, channels, layers or compositions of these elements.
-The _Concepts_ module allows you to extract human concepts from a model and to test their usefulness with respect to a class.
-Finally, the _Metrics_ module covers the current metrics used in explainability. Used in conjunction with the _Attribution Methods_ module, it allows you to test the different methods or evaluate the explanations of a model.
+The _Concepts_ module allows you to extract human concepts from a model and to test their usefulness with respect to a class. Holistic CRAFT extends concept extraction to full activation maps, including object detection models.
+Finally, the _Metrics_ module covers the current metrics used in explainability. Used in conjunction with the _Attribution Methods_ module, it allows you to test the different methods or evaluate the explanations of a model. The _Example-based_ module explains predictions by retrieving relevant examples from a dataset.
 
 <p align="center" width="100%">
     <img width="95%" src="./docs/assets/modules.png">
 </p>
 
 <br>
 
-> [!NOTE]  
-> We are proud to announce the release of the _Example-based_ module! This module is dedicated to methods that explain a model by retrieving relevant examples from a dataset. It includes methods that belong to different families: similar examples, contrastive (counter-factuals and semi-factuals) examples, and prototypes (as concepts based methods have a dedicated sections).
-
 ## 🔥 Tutorials
 
 <details>
@@ -109,6 +106,8 @@ Finally, the _Metrics_ module covers the current metrics used in explainability.
 - [**Concepts Methods**: CRAFT: Getting started on Pytorch](https://colab.research.google.com/drive/16Jn2pQy4gi2qQYZFnuW6ZNtVAYiNyJHO)
 <sub> [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/16Jn2pQy4gi2qQYZFnuW6ZNtVAYiNyJHO) </sub>
 
+- [**Concepts Methods**: Holistic CRAFT (TensorFlow and PyTorch)](https://deel-ai.github.io/xplique/latest/api/concepts/holistic_craft/)
+
 <p align="center" width="100%">
     <a href="https://colab.research.google.com/drive/1jmyhb89Bdz7H4G2KfK8uEVbSC-C_aht_">
         <img width="95%" src="./docs/assets/craft.jpeg">
@@ -133,12 +132,18 @@ included. We will try to cover all the possible usage of the library, feel free
 
 ## 🚀 Quick Start
 
-Xplique requires a version of python higher than 3.7 and several libraries including Tensorflow and Numpy. Installation can be done using Pypi:
+Xplique supports Python 3.10 through 3.13 and several libraries including TensorFlow and NumPy. Installation can be done using PyPI:
 
 ```python
 pip install xplique
 ```
 
+For PyTorch models and concept methods, install the optional dependencies:
+
+```bash
+pip install "xplique[torch]"
+```
+
 Now that Xplique is installed, here are basic examples of what you can do with the available modules.
 
 <details>
@@ -229,6 +234,41 @@ craft.plot_concepts_crops(nb_crops=10)
 
 More information in the [CRAFT documentation](https://deel-ai.github.io/xplique/latest/api/concepts/craft/).
 
+### Holistic CRAFT
+
+Holistic CRAFT works directly with full activation maps and can be used with classification models through the built-in layered extractor. Object-detection-specific extractor adapters are under construction and will be pip-installable soon.
+
+```python
+from xplique.concepts import HolisticCraftTf
+from xplique.concepts.tf.layered_model_latent_extractor import LayeredModelExtractorBuilder
+
+latent_extractor = LayeredModelExtractorBuilder.build(
+    model,
+    split_layer=-3,
+    batch_size=8,
+)
+craft = HolisticCraftTf(latent_extractor, number_of_concepts=10)
+craft.fit(images)
+```
+
+For object detection, use the architecture-specific extractor builders from the companion `xplique-adapters` package when it becomes available:
+
+```python
+# xplique-adapters is under construction and will be pip-installable soon.
+from xplique.concepts import HolisticCraftTorch
+from xplique_adapters.concepts.torch.latent_data_retinanet import RetinanetExtractorBuilder
+
+latent_extractor = RetinanetExtractorBuilder.build(
+    model,
+    device="cuda",
+    nb_classes=91,
+    extraction_location="resnet",
+    extraction_layer=-1,
+)
+craft = HolisticCraftTorch(latent_extractor, number_of_concepts=10, device="cuda")
+craft.fit(images, class_id=class_id)
+```
+
 </details>
 
 <details>
@@ -283,7 +323,7 @@ Want to know more ? Check the [PyTorch documentation](https://deel-ai.github.io/
 
 ## 📦 What's Included
 
-There are 4 modules in Xplique, [Attribution methods](https://deel-ai.github.io/xplique/latest/api/attributions/api_attributions/), [Attribution metrics](https://deel-ai.github.io/xplique/latest/api/attributions/metrics/api_metrics/), [Concepts](https://deel-ai.github.io/xplique/latest/api/concepts/cav/), and [Feature visualization](https://deel-ai.github.io/xplique/latest/api/feature_viz/feature_viz/). In particular, the attribution methods module supports a huge diversity of tasks:[Classification](https://deel-ai.github.io/xplique/latest/api/attributions/classification/), [Regression](https://deel-ai.github.io/xplique/latest/api/attributions/regression/), [Object Detection](https://deel-ai.github.io/xplique/latest/api/attributions/object_detection/), and [Semantic Segmentation](https://deel-ai.github.io/xplique/latest/api/attributions/semantic_segmentation/). For diverse data types: [Images, Time Series, and Tabular data](https://deel-ai.github.io/xplique/latest/api/attributions/api_attributions/). The methods compatible with such task are highlighted in the following table:
+There are 5 modules in Xplique: [Attribution methods](https://deel-ai.github.io/xplique/latest/api/attributions/api_attributions/), [Attribution metrics](https://deel-ai.github.io/xplique/latest/api/attributions/metrics/api_metrics/), [Concepts](https://deel-ai.github.io/xplique/latest/api/concepts/cav/), [Feature visualization](https://deel-ai.github.io/xplique/latest/api/feature_viz/feature_viz/), and [Example-based methods](https://deel-ai.github.io/xplique/latest/api/example_based/api_example_based/). In particular, the attribution methods module supports a huge diversity of tasks:[Classification](https://deel-ai.github.io/xplique/latest/api/attributions/classification/), [Regression](https://deel-ai.github.io/xplique/latest/api/attributions/regression/), [Object Detection](https://deel-ai.github.io/xplique/latest/api/attributions/object_detection/), and [Semantic Segmentation](https://deel-ai.github.io/xplique/latest/api/attributions/semantic_segmentation/). For diverse data types: [Images, Time Series, and Tabular data](https://deel-ai.github.io/xplique/latest/api/attributions/api_attributions/). Holistic CRAFT additionally supports concept-based explanations for object detection models. The methods compatible with such task are highlighted in the following table:
 
 
 <details>
@@ -341,7 +381,6 @@ OD : [Object Detection](https://deel-ai.github.io/xplique/latest/api/attribution
 | Sparseness              | TF, PyTorch** | Complexity       | [Paper](https://proceedings.mlr.press/v119/chalasani20a.html) |
 | RandomLogitMetric       | TF, PyTorch** | Randomization    | [Paper](https://arxiv.org/abs/1810.03292) |
 | ModelRandomizationMetric| TF, PyTorch** | Randomization    | [Paper](https://arxiv.org/abs/1810.03292) |
-| (WIP) e-robustness      |
 
 TF : Tensorflow compatible
 
@@ -358,12 +397,12 @@ TF : Tensorflow compatible
 | Testing CAV (TCAV)              | TF            | [Paper](https://arxiv.org/pdf/1711.11279.pdf) | |
 | CRAFT Tensorflow | TF | [Paper](https://arxiv.org/pdf/2211.10154.pdf) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1jmyhb89Bdz7H4G2KfK8uEVbSC-C_aht_) |
 | CRAFT PyTorch  | PyTorch** | [Paper](https://arxiv.org/pdf/2211.10154.pdf) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/16Jn2pQy4gi2qQYZFnuW6ZNtVAYiNyJHO) |
-| (WIP) Robust TCAV               |               | | |
-| (WIP) Automatic Concept Extraction (ACE)        | | |
+| Holistic CRAFT TensorFlow | TF | [Holistic paper](https://arxiv.org/pdf/2306.07304.pdf) | [Documentation](https://deel-ai.github.io/xplique/latest/api/concepts/holistic_craft/) |
+| Holistic CRAFT PyTorch | PyTorch** | [Holistic paper](https://arxiv.org/pdf/2306.07304.pdf) | [Documentation](https://deel-ai.github.io/xplique/latest/api/concepts/holistic_craft/) |
 
 TF : Tensorflow compatible
 
-** : See the [Xplique for Pytorch documentation](https://deel-ai.github.io/xplique/latest/pytorch/), and the [**PyTorch's model**: Getting started](https://colab.research.google.com/drive/1bMlO29_0K3YnTQBbbyKQyRfo8YjvDbhe)<sub> [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1bMlO29_0K3YnTQBbbyKQyRfo8YjvDbhe) </sub> notebook
+** : See the [Xplique for PyTorch documentation](https://deel-ai.github.io/xplique/latest/api/attributions/pytorch/), and the [**PyTorch's model**: Getting started](https://colab.research.google.com/drive/1bMlO29_0K3YnTQBbbyKQyRfo8YjvDbhe)<sub> [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1bMlO29_0K3YnTQBbbyKQyRfo8YjvDbhe) </sub> notebook
 
 </details>
 
@@ -385,7 +424,7 @@ TF : Tensorflow compatible
 
 </details>
 
-Even though we are only at the early stages, we have also recently added an [Example-based methods](api/example_based/api_example_based/) module. Do not hesitate to give us feedback! Currently, the methods available are summarized in the following table:
+The [Example-based methods](https://deel-ai.github.io/xplique/latest/api/example_based/api_example_based/) module provides several families of example-based explanations. Feedback and contributions are welcome. The currently available methods are summarized in the following table:
 
 <details>
 <summary><b>Table of example-based methods available</b></summary>

diff --git a/TUTORIALS.md b/TUTORIALS.md
@@ -58,7 +58,7 @@ Here is the lists of the available tutorial for now:
 | Fidelity      | Average Drop/Increase/Gain | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1nGP13qiQrsJMBx8TXgA69D-5ALoP3l9p) |
 | Complexity    | Complexity             | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/13boAsXGVKS0LaNzslOdjSkYIrpBJdh7K) |
 | Randomization | Randomization          | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/13lNkZqKajRJ63XllkQddgrPOYF1Xv9-Y) |
-| Stability     | AverageStability       | **(WIP)**                                                                                                                                                          |
+| Stability     | AverageStability       | [Documentation](docs/api/attributions/metrics/avg_stability.md)                                                                                                  |
 
 ## PyTorch Wrapper
 
@@ -72,7 +72,13 @@ Here is the lists of the available tutorial for now:
 
 ## Concepts extraction
 
-**WIP**
+| Category      | **Tutorial Name**      | Documentation / Notebook                                                                                                                                          |
+|:------------- | :--------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+| Labelled concept methods | CAV + TCAV           | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1iuEz46ZjgG97vTBH8p-vod3y14UETvVE) |
+| Automatic concept extraction | CRAFT TensorFlow | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1jmyhb89Bdz7H4G2KfK8uEVbSC-C_aht_) |
+| Automatic concept extraction | CRAFT PyTorch | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/16Jn2pQy4gi2qQYZFnuW6ZNtVAYiNyJHO) |
+| Automatic concept extraction | Holistic CRAFT TensorFlow | [Documentation](docs/api/concepts/holistic_craft.md) |
+| Automatic concept extraction | Holistic CRAFT PyTorch | [Documentation](docs/api/concepts/holistic_craft.md) |
 
 ## Feature Visualization
 

diff --git a/docs/api/attributions/object_detection.md b/docs/api/attributions/object_detection.md
@@ -2,6 +2,9 @@
 
 [Attributions: Object Detection tutorial](https://colab.research.google.com/drive/1X3Yq7BduMKqTA0XEheoVIpOo3IvOrzWL) <sub> [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1X3Yq7BduMKqTA0XEheoVIpOo3IvOrzWL) </sub>
 
+!!! tip "Concept-based object detection explanations"
+    For concept-level explanations of object detection models, see [Holistic CRAFT](../concepts/holistic_craft.md). Its architecture-specific extractors cover RetinaNet, Faster R-CNN, FCOS, SSD, YOLO, and DETR through the companion `xplique-adapters` package, which is currently under construction and will be pip-installable soon.
+
 
 
 
@@ -241,4 +244,4 @@ explainer = Saliency(model, operator=custom_operator)
 ...  # All following steps are the same as the examples
 ```
 
-[^1] [Black-box Explanation of Object Detectors via Saliency Maps (2021)](https://arxiv.org/pdf/2006.03204.pdf)
+[^1] [Black-box Explanation of Object Detectors via Saliency Maps (2021)](https://arxiv.org/pdf/2006.03204.pdf)
diff --git a/docs/api/attributions/pytorch.md b/docs/api/attributions/pytorch.md
@@ -6,6 +6,8 @@
 
 - Other tutorials applying Xplique to PyTorch models: [Attributions: Object Detection](https://colab.research.google.com/drive/1X3Yq7BduMKqTA0XEheoVIpOo3IvOrzWL), [Attributions: Semantic Segmentation](https://colab.research.google.com/drive/1AHg7KO1fCOX5nZLGZfxkZ2-DLPPdSfbX)
 
+- For concept-based explanations of PyTorch models, see [Holistic CRAFT](../concepts/holistic_craft.md), including its object detection support.
+
 !!!note
     We should point out that what we did with PyTorch should be possible for other frameworks. Do not hesitate to give it a try and to make a PR if you have been successful!
 
@@ -44,7 +46,7 @@ score_saliency = metric(explanations)
 
 ## Does it work for every module?
 
-It has been tested on both the `attributions` and the `metrics` modules.
+It has been tested on the `attributions`, `metrics`, and `concepts` modules. Holistic CRAFT adds a native PyTorch path for concept extraction, including object detection models.
 
 
 
@@ -82,6 +84,10 @@ Not yet, but it works for most of them (even for gradient-based ones!):
 
 It works for all tasks covered by Xplique, see [the tasks covered and how to specify them](api_attributions.md#the-tasks-covered).
 
+### Concept-based explanations
+
+PyTorch classification and object detection models can be explained with `HolisticCraftTorch` through the latent extractor builders described in the [Holistic CRAFT documentation](../concepts/holistic_craft.md). Detector-specific builders are provided by the `xplique-adapters` companion package, which is under construction and will be pip-installable soon.
+
 
 
 

diff --git a/docs/api/concepts/cav.md b/docs/api/concepts/cav.md
@@ -25,6 +25,10 @@ cav = cav_renderer(positive_examples, random_examples)
 
 ```
 
+## Related concept methods
+
+For automatic concept extraction, see [CRAFT](craft.md) and [Holistic CRAFT](holistic_craft.md).
+
 {{xplique.concepts.cav.Cav}}
 
 [^1]: [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) (2018).](https://arxiv.org/abs/1711.11279)
diff --git a/docs/api/concepts/craft.md b/docs/api/concepts/craft.md
@@ -32,6 +32,9 @@ The concepts will be extracted from this latent space.
 !!!warning
     Please keep in mind that the activations must be positives (after relu or any positive activation function)
 
+!!! tip "When to use Holistic CRAFT"
+    Regular CRAFT extracts concepts from image crops and is a good fit for classification datasets. For object detection, scenes with multiple objects, or models where global spatial context matters, use [Holistic CRAFT](holistic_craft.md), which factorizes full activation maps instead.
+
 
 ## Example