nvidia/nv-tesseract-ad-diffusion

NV-Tesseract-AD 2.0 Overview

Description:

NVIDIA NV-Tesseract-AD-2.0 provides anomaly detection functionality. Rather than relying only on transformers, it introduces diffusion modeling, stabilized through curriculum learning, and pairs it with adaptive thresholding methods in a model purpose-built for anomaly detection. Together, these elements address some of the most challenging issues in the field: noisy, high-dimensional signals that drift over time and contain rare, irregular events.

This model is for research and development only.

License/Terms of Use:

Governing Terms: Model: The model is provided under the Apache License, Version 2.0.

Deployment Geography:

Global

Use Case:

Companies, organizations, research hubs looking to do anomaly detection on temporal data.

Release Date:

29th June 2026 via https://huggingface.co/nvidia/nv-tesseract-ad-diffusion

Reference(s):

Segmented Confidence Sequences and Multi-Scale Adaptive Confidence Segments for Anomaly Detection in Nonstationary Time Series
ImDiffusion

Model Architecture:

Architecture Type: Diffusion based transformer

Network Architecture: ResNet34

Number of model parameters: 2 million

The NV-Tesseract-AD-2.0 is a diffusion-based model for time-series imputation and anomaly detection.

Input:

Input Type(s): Tabular numeric
Input Format(s): Tabular Pandas DataFrame or CSV/JSON
Input Parameters: Two-Dimensional (2D)
Other Properties Related to Input: Pre-Processing Needed
Anomaly detection: Contains timestamp column and one or more numeric value columns.

Output:

Output Type(s): Tabular numeric
Output Format: Tabular Pandas DataFrame
Output Parameters: Two-Dimensional (2D)
Other Properties Related to Output: Post-Processing Needed
Anomaly detection: Contains timestamp, value, and anomaly label columns.

Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.

Software Integration:

Runtime Engine(s):
PyTorch

Supported Hardware Microarchitecture Compatibility:
NVIDIA Ampere
NVIDIA Hopper

[Preferred/Supported] Operating System(s):
Linux

The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.

Model Version(s):

NV-Tesseract-AD-2.0

Training & Testing Datasets:

80/20 split per dataset.

Data Modality: Other: Numeric time series

Training Data Size: 3 million data points

TSB-AD-M

Data Collection Method by dataset Hybrid: Synthetic, Automatic/Sensors, Human
Labeling Method by dataset Hybrid: Synthetic, Automatic/Sensors, Human
Properties: The TSB-AD-M benchmark includes a public category containing 18 previously proposed datasets with a total of 1980 multi-variate time series. These time series span different domains and exhibit a high variability of anomaly types, ratios, and sizes.

Evaluation Datasets:

Detecting Anomalies in Wafer Manufacturing

Data Collection Method by dataset Hybrid: Synthetic, Automatic/Sensors, Human
Labeling Method by dataset Hybrid: Synthetic, Automatic/Sensors, Human
Properties: 151 inline process-control traces recorded by semiconductor sensors during wafer fabrication.

CalIt2 Building People Counts

Data Collection Method by dataset Hybrid: Synthetic, Automatic/Sensors, Human
Labeling Method by dataset Hybrid: Synthetic, Automatic/Sensors, Human
Properties: People-count sensor at the main entrance of UC-Irvine's CalIt2 building (15 weeks, 48 half-hour slots per day)

Network Traffic

Data Collection Method by dataset Hybrid: Synthetic, Automatic/Sensors, Human
Labeling Method by dataset Hybrid: Synthetic, Automatic/Sensors, Human
Properties: This dataset contains network traffic data generated for the purpose of anomaly detection in embedded systems, specifically targeting security threats such as malicious activities. It includes both normal and anomalous (malicious) behavior, which are labeled accordingly for supervised learning tasks.

Genesis Demonstrator

Data Collection Method by dataset Hybrid: Synthetic, Automatic/Sensors, Human
Labeling Method by dataset Hybrid: Synthetic, Automatic/Sensors, Human
Properties: The Genesis Demonstrator was created during the OPAK Project and further revised during the European IMPROVE project. It is a portable pick-and-place demonstrator which uses an air tank to supply all the gripping and storage units. It records 5(+4) continuous signals, 13 discrete signals and 1 Unix Timestamp.

Falling People

Data Collection Method by dataset Hybrid: Synthetic, Automatic/Sensors, Human
Labeling Method by dataset Hybrid: Synthetic, Automatic/Sensors, Human
Properties: This data set was used during a thesis to develop safer smart environments. The origin is a care independent smart home environment to detect the falling of elderly people.

Inference:

Engine: PyTorch, Transformer Engine
Test Hardware:

• A100 (8 GPUs; each is 74 GB)
  
• H100 (8 GPUs; each is 80 GB)

Ethical Considerations:

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns here.