Duality AI

company

Verified

https://www.duality.ai

duality-robotics

Activity Feed Request to join this org

AI & ML interests

Embodied AI, synthetic data, AI vision

DualityAI-RebekahBogdanoff

posted an update about 2 months ago

Post

2843

Duality AI's latest Kaggle competition was our most difficult one yet! Contestants had to train for Multiclass object detection using data from FalconCloud (you can still use the scenarios for free here - https://tinyurl.com/5n7yhvha , https://tinyurl.com/38ktjfkn)

Duality partnered with @3LC and their software for creating better, smaller, faster AI models!

The following winners showed skill and perseverance, analyzing and generating targeted data that trains a model to works on real-world data 👏 👏 👏

🥇 1st place: A team consisting of: @Leo5566 and kaggle user "Ariel__" https://www.kaggle.com/gogoka

🥈 2nd place: @Moe153

🥉 3rd place: A team consisting of Kaggle users "Kostiantyn Kazanin" (https://www.kaggle.com/kostya876), "Yuriy Greben" (https://www.kaggle.com/yuriygreben), "Illya Movchan"(https://www.kaggle.com/illyamovchan), and "Maryna Borovska"(https://www.kaggle.com/marynaborovska)

Top 10 Honorable mentions include:
🏅@younesbenalia (top 10 2x in a row!)
🏅@MuhammadHaaris (also 2nd time in the top 10!)
...and more! View the entire leaderboard at - https://www.kaggle.com/competitions/multi-class-object-detection-challenge/leaderboard

Join our current Multi-Class Object Detection Synthetic2Real Kaggle competition here: https://www.kaggle.com/competitions/grocery-items-multi-class-object-detection

DualityAI-RebekahBogdanoff

posted an update about 2 months ago

Post

2783

New article just dropped!
"Accelerating Physical AI Deployment by Closing the Gen2Real Gap" - https://huggingface.co/blog/DualityAI-RebekahBogdanoff/accelerating-physical-ai-deployment

🏎️ Generative AI promises to fast-track deployable Physical AI — but turning that promise into reliable training data for robots, autonomous systems, and even embodied AI isn’t automatic.

⛓️‍💥 The missing link?
Bridging the 𝐆𝐞𝐧2𝐑𝐞𝐚𝐥 𝐆𝐚𝐩 — the distance between what generative models produce and how the real world behaves.

In our latest blog, Duality AI CEO Apurva Shah shares how lessons from closing the Sim2Real gap point the way forward for Gen2Real, including:

💡 Understanding the fundamentals of Implicit vs. Explicit world models.
🏗️ Designing hybrid synthetic data pipelines and agentic workflows that combine the strengths of simulated and generative approaches while minimizing their weaknesses.
📊 Applying rigorous metrics so synthetic data doesn’t just look real, but accurately predicts reality in areas vital for Physical AI training.

1 reply

·

DualityAI-RebekahBogdanoff

posted an update 2 months ago

Post

3539

🎉 Big congratulations to the winners of the "Synthetic 2 Real Object Detection Challenge 2", the second Kaggle challenge that Duality AI hosted. This competition was more fierce than the last one, but these users managed to clench the win!

🥇 1st place: @sergio-sanz-rodriguez (see the blog he produced with us outlining how he achieved his results: https://tinyurl.com/mreunr98)

🥈 2nd place: Kaggle user Diana Shilova - https://tinyurl.com/yjjz3szm

🥉 3rd place: Kaggle user 眉间尺 - https://tinyurl.com/ycxskfzv

View the entire leaderboard at - https://tinyurl.com/jm2ery7w

Join our current Multi-Class Object Detection Synthetic2Real Kaggle competition here: https://tinyurl.com/y224rttu

And we will soon be launching a new competition in a new domain! Hint: 🌄 🏠 🌳 ✈️

DualityAI-RebekahBogdanoff

posted an update 2 months ago

Post

3654

Shout out to the winners of the "Synthetic2Real Object Detection Challenge" Duality AI hosted earlier this year. Out of the 1000+ participants in our challenges, these users stood out above the rest.

🥇 1st place: @Eyl42

🥈 2nd place: @sergio-sanz-rodriguez

🥉 3rd place: @Nadiaaaaaaa

View the entire leaderboard at - https://tinyurl.com/38ebvcwf

Join our current Grocery Items: Multi-Class Object Detection Synthetic2Real Kaggle competition here: https://tinyurl.com/y224rttu

And be on the lookout for anther competition in the next couple weeks with a brand new domain!
hint: ✈️

DualityAI-RebekahBogdanoff

posted an update 3 months ago

Post

5005

We released a new competition! https://www.kaggle.com/competitions/grocery-items-multi-class-object-detection/overview

Join to:
💡 Learn from others
🤔 Develop your Sim2Real skills using simulation
📸 Generate custom data on the cloud to improve your model
✨ and more!

2 replies

·

DualityAI-RebekahBogdanoff

posted an update 4 months ago

Post

182

On the poll I posted last week, most people said they focused on getting targeted data over just large quantities of data. In response, I published Duality's blog "Is Your Model Bingeing on Junk Data?" here: https://huggingface.co/blog/DualityAI-RebekahBogdanoff/is-your-model-bingeing-on-junk-data

It covers key features of targeted data for successful synthetic data creation and model training.

This is part 1, is this useful to y'all? Would you like more articles like this or on other topics from our experts?

As always, you can start creating your own synthetic data for free on Falcon. It's not Gen AI, its data crafted from digital scenarios, designed to align with a target domain.

Create an account and start generating free data here: https://falcon.duality.ai/secure/scenarios?utm_source=huggingface&utm_medium=post&utm_campaign=blog

DualityAI-RebekahBogdanoff

posted an update 4 months ago

Post

2740

When you're looking for data, what's your focus (use the reactions below to vote):
🚀 Getting as many images as you can
🤯 Getting the right type of images (framing, domain, lighting, etc)

I know both are very important, but I'm curious what people would put as #1

3 replies

·

DualityAI-RebekahBogdanoff

posted an update 4 months ago

Post

2080

NEW ARTICLE: "Detecting Beyond Sight: Building AI-Enabled SAR Intelligence with Synthetic Data"

Synthetic Aperture Radar (SAR) reveals what optical sensors can’t. AI can turn that information into actionable intelligence—but only with the right training data.

In our latest blog, we explore how Falcon’s new virtual SAR sensor solves the SAR data bottleneck for AI development. As the newest addition to Falcon’s sensor library, it models radar returns with precision—including azimuth, range resolution, signal intensity, and noise. This Falcon-specific, GPU-accelerated raytraced SAR model is exposed via Falcon’s Python API, giving teams precise, control over radar wave propagation and enabling physically grounded, highly customizable, and user-friendly SAR simulation.

The result? High-fidelity, automatically labeled synthetic SAR imagery from any scenario—on demand. No custom setup. No external workflows. Just mission-ready data for building AI models across defense, disaster response, agriculture, intelligence, and beyond.

📡 Read how it works → https://huggingface.co/blog/DualityAI-RebekahBogdanoff/ai-enabled-sar-intelligence-synthetic-data

DualityAI-RebekahBogdanoff

posted an update 4 months ago

Post

829

Excuse the lag, it's from the real-time inference from the webcam 👀 . Did you know that YOLOv11 added Streamlit for live object detection straight from your webcam?

📸 Learn about live inference with YOLOv11 and the Streamlit Application -
https://docs.ultralytics.com/guides/streamlit-live-inference/

🥫 Join the mentioned Kaggle competition here -
https://www.kaggle.com/competitions/multi-class-object-detection-challenge/overview

👀 Checkout Duality AI -
https://www.duality.ai/?utm_source=hf&utm_medium=post&utm_campaign=video

🫡 Checkout 3LC.AI -
https://3lc.ai/

DualityAI-RebekahBogdanoff

posted an update 4 months ago

Post

3226

📢 Generate your own data in simulation using two new free and customizable data-generating Scenarios on Duality's FalconCloud service.
🙌 These multi-class Scenarios are designed to target model weaknesses for our recent Kaggle competition, but they are free to anyone for non-commercial use! Just create a free account.

📸 Control object and camera posing
👉 Select random variable ranges
🖼️ Set post-processing effects
➕ and more to create a robust dataset for strong model training.

Access the 2 Scenarios here:
💠 https://falcon.duality.ai/secure/scenarios/edit/9e90e036-8af9-41e4-8af0-1343b8e8f467?utm_source=Kaggle&utm_medium=post&utm_campaign=competition_4
💠 https://falcon.duality.ai/secure/scenarios/edit/e3294c19-49d4-4f64-9ca8-8373876c2c94?utm_source=Kaggle&utm_medium=post&utm_campaign=competition_4

DualityAI-RebekahBogdanoff

posted an update 4 months ago

Post

2619

📢 The Kaggle Synthetic-to-Real Object Detection Challenge is back, and it's a multi-class challenge 😎 !

💵This time we made a harder, multi-class challenge and are offering a larger prize pool. Sign up here: https://www.kaggle.com/competitions/multi-class-object-detection-challenge

🤝 Duality AI is partnering in this competition with 3LC.AI, a cutting-edge platform which enables users to capture per sample metrics and take meaningful action leading to better, faster, and smaller AI models.

Competitors will be challenged to:
✨ Create customized training data with Duality’s cloud-based scenario
✨Analyze data weaknesses and make calculated changes using 3LC’s robust software
✨Optimize data for peak model training

Compete for prizes, certificates, and recognition from peer competitors around the world. Whether you’re a student, researcher, or industry pro, this challenge offers hands-on experience customizing high-fidelity synthetic data for robust models.

Ready to bridge the Sim2Real gap? Join us and start building today!

Sign up here: https://www.kaggle.com/competitions/multi-class-object-detection-challenge

DualityAI-RebekahBogdanoff

posted an update 5 months ago

Post

2536

🤔 Ready to build better AI models with synthetic data, but don't know where to start? Why go at it alone?💡

👋 Join Duality AI’s Falcon community! It is one of the best resources for support, creativity, and growth as you move along your synthetic data journey.

➡️Our current Kaggle competition is the easiest way to get started: https://www.kaggle.com/competitions/multi-instance-object-detection-challenge

When you join, you'll meet some of the rising stars in our community, such as:

🌟 Sergio Sanz, @sergio-sanz-rodriguez , who took 1st and 2nd place in recent computer vision Kaggle competitions and shared his process of using R-CNN and Falcon-generated images in this article: https://www.duality.ai/blog/leveraging-synthetic-data-for-real-world-object-detection

🌟Mohana pavan Bezawada, @mohanapavan , who has risen in the ranks from the top 25 in the first competition all the way to top scorer in our current competition! His journey illustrates how dedication + Falcon can take you far in your AI journey.

🌟Nadia TRIKI, who delivered top-tier results in two of our recent Kaggle competitions and shared a detailed breakdown of her strategy - showcasing a deep command of AI training workflows and a commitment to helping others succeed.

Ángel Jacinto Sánchez Ruiz, @Sacus , who mastered FalconCloud to create targeted, high-performance datasets and provided crucial feedback and product requests that improved the data not only for him but for all of the current competitors.

🤩 Join our community today to partner with these super stars, and many more!

➡️ Sign up for a free Falcon subscription here: https://www.duality.ai/edu
➡️Join our Kaggle competition for hands on learning and a chance to win rewards and recognition! https://www.kaggle.com/competitions/multi-instance-object-detection-challenge

5 replies

·

DualityAI-RebekahBogdanoff

posted an update 5 months ago

Post

2209

Can AI models trained solely on 100% synthetic data achieve top-tier accuracy in real-world object detection?

👉 @sergio-sanz-rodriguez just proved it while winning Duality AI’s Synthetic-to-Real Object Detection Challenge using Falcon-generated imagery. His model achieved perfect real-world detection accuracy without a single real image in the training loop.

In this blog, Dr. Sanz walks us through his method, which includes the design and training of an advanced pipeline to achieve 100% detection accuracy.
His full technical breakdown covers:
📍 Synthetic-only training
📍 Data augmentation with an ensemble learning approach for better generalization
📍 Custom occlusion generation
📍 A Faster R-CNN model fine-tuned with Falcon generated data
📍 And much more!

The results speak for themselves!
📖 Read the blog here: https://www.duality.ai/blog/leveraging-synthetic-data-for-real-world-object-detection

Congratulations Sergio! We can't wait to see what you do next.

🔔 Ready to take on the next Synthetic-to-Real challenge? The third edition of our Kaggle competition—Multi-Instance Object Detection Challenge—is now live: https://www.kaggle.com/competitions/multi-instance-object-detection-challenge

2 replies

·

DualityAI-RebekahBogdanoff

posted an update 5 months ago

Post

2082

🗣️ 📢 New article alert!

"Integrity Threats in AI: When Data Poisoning Undermines Model Effectiveness" from Duality AI is now on HuggingFace here: https://huggingface.co/blog/DualityAI-RebekahBogdanoff/integrity-threats-in-ai

Significant threats to AI model performance aren’t always loud or obvious. Integrity violations—like subtle data poisoning attacks—can quietly erode your model’s reliability, long before anyone notices. These attacks can be surprisingly effective with minimal changes to the dataset.

At Duality, our work in high-stakes sectors like defense has driven us to tackle this threat head-on. In our latest blog from Duality's Director of Infrastructure and Security at Duality, David Strout, we unpack how data poisoning works, why it’s so dangerous, and how organizations can secure their AI pipelines with clear provenance, regular performance auditing, and a trusted synthetic data supply chain.

Whether you're building AI models for finance, healthcare, manufacturing, or national security—the integrity of these systems is a matter of public safety and security. Taking action today will mitigate fundamental business risks in the very near tomorrow.

DualityAI-RebekahBogdanoff

posted an update 5 months ago

Post

3619

As part of Duality AI’s recent Kaggle competition, we’ve released a free, fully customizable cloud scenario designed to help you create targeted datasets with YOLO-compatible labels.

The cloud simulation lets you customize the:
📸 camera distance
🎞️ film grain variation
🖼️background objects,
➕ and more!

Create the dataset that you need by following this link: https://falcon.duality.ai/secure/scenarios/edit/cca0bc47-265a-4f67-843f-a434b63271b3?utm_source=huggingface&utm_medium=social&utm_campaign=general

I’ve attached an instructional video we used for the competition, but this feature is free for anyone who has an account. https://vimeo.com/1091271731?share=copy

DualityAI-RebekahBogdanoff

posted an update 5 months ago

Post

2293

📢 Duality's Synthetic-to-Real Object Detection Kaggle competition is back!👏

Sign up here ➡️ ➡️ https://www.kaggle.com/competitions/multi-instance-object-detection-challenge/overview

This competition will test users' ability to train a model for multi-instance object detection. Users will:
✨Customize a cloud-based simulation
✨Output unique data for robust model training
✨Optimize training for peak model performance

Compete for cash prizes, certificates, and recognition from peer competitors around the world. Whether you’re a student, researcher, or industry pro, this challenge offers hands-on experience customizing high-fidelity synthetic data for robust models. Ready to bridge the Sim2Real gap? Join us and start building today!

DualityAI-RebekahBogdanoff

posted an update 7 months ago

Post

3867

We’re back—with higher stakes, new datasets, and more chances to stand out. Duality AI's Synthetic-to-Real Object Detection Challenge 2 is LIVE!🚦

✍ Sign up here: https://lnkd.in/g2avFP_X

After the overwhelming response to Challenge 1, we're pushing the boundaries even further in Challenge 2, where your object detection models will be put to the test in the real world after training only on synthetic data.

👉 Join our Synthetic-to-Real Object Detection Challenge 2 on Kaggle!

What’s Different This Time? Unlike our first challenge, we’re now diving deep into data manipulation. Competitors can:

🔹Access 4 new supplemental datasets via FalconCloud with varying lighting, occlusions, and camera angles.
🔹Generate your own synthetic datasets using FalconEditor to simulate edge cases.
🔹Mix, match, and build custom training pipelines for maximum mAP@50 performance

This challenge isn’t just about using synthetic data—it’s about mastering how to craft the right synthetic data.
Ready to test your skills?

🏆The Challenge
Train an object detection model using synthetic images created with Falcon—Duality AI's cutting-edge digital twin simulation software—then evaluate your model on real-world imagery.

The Twist?

📈Boost your model’s accuracy by creating and refining your own custom synthetic datasets using Falcon!

Win Cash Prizes & Recognition
🔹Earn cash and public shout-outs from the Duality AI accounts
Enhance Your Portfolio
🔹Demonstrate your real-world AI and ML expertise in object detection to prospective employers and collaborators.
🔹Expand Your Network
🔹Engage, compete, and collaborate with fellow ML engineers, researchers, and students.
🚀 Put your skills to the test and join our Kaggle competition today: https://lnkd.in/g2avFP_X

DualityAI-RebekahBogdanoff

posted an update 8 months ago

Post

1158

🔥 Duality AI released some new datasets this week! 🔥

Click here for the Multi Instance Object Detection dataset: duality-robotics/YOLOv8-Multi-Instance-Object-Detection-Dataset

Click here for the Single Class Object Detection dataset: duality-robotics/YOLOv8-Object-Detection-02-Dataset

You can also get larger datasets here: https://falcon.duality.ai/secure/documentation/ex4-dataset?sidebarMode=learn&utm_source=huggingface&utm_medium=dataset&utm_campaign=multiinstance

1 reply

·

DualityAI-RebekahBogdanoff

posted an update 8 months ago

Post

2576

Curious how Duality AI crafts synthetic data that can bridge the sim2real gap?

We just published an article here on HuggingFace outlining our process, with bonus dataset releases! Read it here: https://huggingface.co/blog/DualityAI-RebekahBogdanoff/training-yolov8-with-synthetic-data-from-falcon

1 reply

·

DualityAI-RebekahBogdanoff

published a dataset 8 months ago

duality-robotics/YOLOv8-Multi-Instance-Object-Detection-Dataset

Viewer • Updated Mar 27 • 20 • 32