Join R-Ladies Ottawa for a casual evening of programming on Tuesday, January 27th. We'll be participating in TidyTuesday, a weekly data visualization challenge organized by the R for Data Science community.

What is TidyTuesday?

Every week, a new dataset is posted online on the TidyTuesday GitHub repo, and folks from around the world create data visualizations using the dataset. It's an opportunity to put your programming skills into practice using real-world data in a way that's fun! It's also a great way for everyone to learn from each other, by sharing their visualizations and code.

What will the dataset be?

Even we don't know that (yet)! We'll have to wait until the day before the event to know what data we'll be working with. If you're interested in seeing some past datasets, take a look at the examples below, or visit the TidyTuesday GitHub repo to see all of the datasets dating back to 2018.

Examples from past TidyTuesdays:

• Donuts, Data, and D'oh - A Deep Dive into The Simpsons
• Pokemon
• What have we been watching on Netflix?

Do I have to use R?

No! You can use any programming language or visualization software that you want. In fact, Python users from around the globe participate in "TyDyTuesday" on a weekly basis.

Who is this event for?

No previous programming experience is required to participate, and we'll have experienced programmers in the room who can help you get started (or unstuck), if needed.

...But if you want to get the most out of the event, a good way to prepare is to watch the recording of the introduction to data visualization workshop we hosted back in 2024. :)

What should I bring?

• Please bring a laptop so you can code along. We recommend that you have RStudio or another IDE (such as VS Code or Positron) installed ahead of time, but we can help you get one installed if needed!
• Come ready to learn, share, and contribute to a safe and welcoming community!

How will this event work?

• First few minutes of the event: Introductions, and taking a look at the dataset together as a group.
• Time to create a data visualization using the language or software of your choice, either on your own or with a (new) friend! Grab a free snack while you're at it :)
• Last \~30 minutes of the event: Show and tell session for anyone who would like to share their creation with the group.

What else do I need to know?

This event (like all R-Ladies events) is totally FREE to attend.

The event will take place at Bayview Yards, which is located just a few steps away from the Bayview O-Train station. There is also a free parking lot available for those who are driving. You can find us in the "Training Room", which is on the second floor of the Bayview Yards building.

This is an in-person event with limited space! Please only RSVP if you are able to attend in-person!

***Please note that the mission of R-Ladies is to increase gender diversity in the R community. This event is intended to provide a safe space for women and gender minorities. We ask for male allies to be invited by and accompanied by a woman or gender minority.***

We’re grateful to be part of the Bayview Meetups initiative and extend our thanks to Bayview Yards for generously providing the venue space.

Please register here

Platform engineering teams often face a persistent challenge: fast, reliable access to high-quality test data. Production data is restricted, masking is slow, and manual dataset creation becomes a bottleneck across development, testing, and AI workflows. Agentic AI now makes it possible to automate this entire process and deliver synthetic data on demand in the exact formats your teams need.

Join synthetic data expert Mark Brocato as he demonstrates how Tonic Fabricate removes data friction by generating realistic, structured synthetic test data automatically. See how platform teams can use this capability to support developers and AI practitioners with quick, compliant, and self-service access to data, exported directly into supported databases or delivered as JSON, PDFs, DOCX, EML, and more.What you'll learn during the webinar:

• How to select the right approach to synthetic data: Compare rule-based synthesis, de-identification, and Agentic AI to determine which method best supports your platform and your teams.
• How to generate highly realistic, nuanced data: Learn how Agentic AI creates complex test data for development and testing, significantly reducing the need for deep domain expertise.
• Best practices and practical platform use cases: See how automated synthetic data fits into platform engineering responsibilities, including CI/CD pipelines, API mocking, developer self-service, test automation, and AI model development.

Speaker: Mark Brocato - Head of Engineering for Fabricate @ Tonic.ai

Mark Brocato is a software developer and entrepreneur best known as the founder of Mockaroo, one of the world’s leading synthetic data generators, launched in 2014. The idea for Mockaroo came while Mark was watching QA engineers struggle to test complex life science workflows at a startup called BioFortis, inspiring him to make realistic test data easier for everyone. With over two decades in software development, he’s built tools for developers at Sencha, Layer0, and beyond. In 2024, Mark launched Fabricate, the AI-powered synthetic data platform that was acquired by Tonic.ai in 2025, where Mark continues to lead its development. A Ruby, JavaScript, and Rust developer, he divides his time between Sparta, New Jersey, and Tallinn, Estonia.

Please register here

Platform engineering teams often face a persistent challenge: fast, reliable access to high-quality test data. Production data is restricted, masking is slow, and manual dataset creation becomes a bottleneck across development, testing, and AI workflows. Agentic AI now makes it possible to automate this entire process and deliver synthetic data on demand in the exact formats your teams need.

Join synthetic data expert Mark Brocato as he demonstrates how Tonic Fabricate removes data friction by generating realistic, structured synthetic test data automatically. See how platform teams can use this capability to support developers and AI practitioners with quick, compliant, and self-service access to data, exported directly into supported databases or delivered as JSON, PDFs, DOCX, EML, and more.What you'll learn during the webinar:

• How to select the right approach to synthetic data: Compare rule-based synthesis, de-identification, and Agentic AI to determine which method best supports your platform and your teams.
• How to generate highly realistic, nuanced data: Learn how Agentic AI creates complex test data for development and testing, significantly reducing the need for deep domain expertise.
• Best practices and practical platform use cases: See how automated synthetic data fits into platform engineering responsibilities, including CI/CD pipelines, API mocking, developer self-service, test automation, and AI model development.

Speaker: Mark Brocato - Head of Engineering for Fabricate @ Tonic.ai

Mark Brocato is a software developer and entrepreneur best known as the founder of Mockaroo, one of the world’s leading synthetic data generators, launched in 2014. The idea for Mockaroo came while Mark was watching QA engineers struggle to test complex life science workflows at a startup called BioFortis, inspiring him to make realistic test data easier for everyone. With over two decades in software development, he’s built tools for developers at Sencha, Layer0, and beyond. In 2024, Mark launched Fabricate, the AI-powered synthetic data platform that was acquired by Tonic.ai in 2025, where Mark continues to lead its development. A Ruby, JavaScript, and Rust developer, he divides his time between Sparta, New Jersey, and Tallinn, Estonia.

Please register here

Platform engineering teams often face a persistent challenge: fast, reliable access to high-quality test data. Production data is restricted, masking is slow, and manual dataset creation becomes a bottleneck across development, testing, and AI workflows. Agentic AI now makes it possible to automate this entire process and deliver synthetic data on demand in the exact formats your teams need.

Join synthetic data expert Mark Brocato as he demonstrates how Tonic Fabricate removes data friction by generating realistic, structured synthetic test data automatically. See how platform teams can use this capability to support developers and AI practitioners with quick, compliant, and self-service access to data, exported directly into supported databases or delivered as JSON, PDFs, DOCX, EML, and more.What you'll learn during the webinar:

• How to select the right approach to synthetic data: Compare rule-based synthesis, de-identification, and Agentic AI to determine which method best supports your platform and your teams.
• How to generate highly realistic, nuanced data: Learn how Agentic AI creates complex test data for development and testing, significantly reducing the need for deep domain expertise.
• Best practices and practical platform use cases: See how automated synthetic data fits into platform engineering responsibilities, including CI/CD pipelines, API mocking, developer self-service, test automation, and AI model development.

Speaker: Mark Brocato - Head of Engineering for Fabricate @ Tonic.ai

Mark Brocato is a software developer and entrepreneur best known as the founder of Mockaroo, one of the world’s leading synthetic data generators, launched in 2014. The idea for Mockaroo came while Mark was watching QA engineers struggle to test complex life science workflows at a startup called BioFortis, inspiring him to make realistic test data easier for everyone. With over two decades in software development, he’s built tools for developers at Sencha, Layer0, and beyond. In 2024, Mark launched Fabricate, the AI-powered synthetic data platform that was acquired by Tonic.ai in 2025, where Mark continues to lead its development. A Ruby, JavaScript, and Rust developer, he divides his time between Sparta, New Jersey, and Tallinn, Estonia.

Please register here

Platform engineering teams often face a persistent challenge: fast, reliable access to high-quality test data. Production data is restricted, masking is slow, and manual dataset creation becomes a bottleneck across development, testing, and AI workflows. Agentic AI now makes it possible to automate this entire process and deliver synthetic data on demand in the exact formats your teams need.

Join synthetic data expert Mark Brocato as he demonstrates how Tonic Fabricate removes data friction by generating realistic, structured synthetic test data automatically. See how platform teams can use this capability to support developers and AI practitioners with quick, compliant, and self-service access to data, exported directly into supported databases or delivered as JSON, PDFs, DOCX, EML, and more.What you'll learn during the webinar:

• How to select the right approach to synthetic data: Compare rule-based synthesis, de-identification, and Agentic AI to determine which method best supports your platform and your teams.
• How to generate highly realistic, nuanced data: Learn how Agentic AI creates complex test data for development and testing, significantly reducing the need for deep domain expertise.
• Best practices and practical platform use cases: See how automated synthetic data fits into platform engineering responsibilities, including CI/CD pipelines, API mocking, developer self-service, test automation, and AI model development.

Speaker: Mark Brocato - Head of Engineering for Fabricate @ Tonic.ai

Mark Brocato is a software developer and entrepreneur best known as the founder of Mockaroo, one of the world’s leading synthetic data generators, launched in 2014. The idea for Mockaroo came while Mark was watching QA engineers struggle to test complex life science workflows at a startup called BioFortis, inspiring him to make realistic test data easier for everyone. With over two decades in software development, he’s built tools for developers at Sencha, Layer0, and beyond. In 2024, Mark launched Fabricate, the AI-powered synthetic data platform that was acquired by Tonic.ai in 2025, where Mark continues to lead its development. A Ruby, JavaScript, and Rust developer, he divides his time between Sparta, New Jersey, and Tallinn, Estonia.

Please register here

Platform engineering teams often face a persistent challenge: fast, reliable access to high-quality test data. Production data is restricted, masking is slow, and manual dataset creation becomes a bottleneck across development, testing, and AI workflows. Agentic AI now makes it possible to automate this entire process and deliver synthetic data on demand in the exact formats your teams need.

Join synthetic data expert Mark Brocato as he demonstrates how Tonic Fabricate removes data friction by generating realistic, structured synthetic test data automatically. See how platform teams can use this capability to support developers and AI practitioners with quick, compliant, and self-service access to data, exported directly into supported databases or delivered as JSON, PDFs, DOCX, EML, and more.What you'll learn during the webinar:

• How to select the right approach to synthetic data: Compare rule-based synthesis, de-identification, and Agentic AI to determine which method best supports your platform and your teams.
• How to generate highly realistic, nuanced data: Learn how Agentic AI creates complex test data for development and testing, significantly reducing the need for deep domain expertise.
• Best practices and practical platform use cases: See how automated synthetic data fits into platform engineering responsibilities, including CI/CD pipelines, API mocking, developer self-service, test automation, and AI model development.

Speaker: Mark Brocato - Head of Engineering for Fabricate @ Tonic.ai

Mark Brocato is a software developer and entrepreneur best known as the founder of Mockaroo, one of the world’s leading synthetic data generators, launched in 2014. The idea for Mockaroo came while Mark was watching QA engineers struggle to test complex life science workflows at a startup called BioFortis, inspiring him to make realistic test data easier for everyone. With over two decades in software development, he’s built tools for developers at Sencha, Layer0, and beyond. In 2024, Mark launched Fabricate, the AI-powered synthetic data platform that was acquired by Tonic.ai in 2025, where Mark continues to lead its development. A Ruby, JavaScript, and Rust developer, he divides his time between Sparta, New Jersey, and Tallinn, Estonia.

A central challenge in knowledge transfer lies in the transfer of tacit knowledge. LLMs, capable of identifying latent patterns in data, present an interesting opportunity to address this issue. This paper explores the potential of LLMs to externalize experts’ tacit knowledge and aid its transfer to novices. Specifically, we examine three questions: RQ1: Can LLMs effectively externalize experts’ tacit knowledge? How to do so (e.g., prompting strategy)? RQ2: How can LLMs use externalized tacit knowledge to make effective decisions? RQ3: How can LLM-externalized tacit knowledge support novice learning? We explore these questions using real-world tutoring conversations collected by Wang et al. (2024).

Our findings suggest that LLMs may be capturing nuances from experts’ observed behavior that are different from the knowledge experts articulate. With carefully designed prompting strategies, LLMs may offer a practical and scalable means of externalizing and transferring tacit knowledge.

NASA Space Apps Challenge 2025 – Zurich second year edition.

For the second time, after succesful event in 2024, and more than 10 projects submitted locally, Switzerland in Zurich again will host the NASA Space Apps Challenge, where innovators, developers, scientists, designers, students, and creatives come together to solve real challenges on Earth and in space using open data from NASA and partner space agencies. Date: October 4–5, 2025 Location: Zurich (offline & online participation possible) Global Theme: Solving for Earth with Space

What is Space Apps?

NASA Space Apps is a 48-hour global hackathon that engages tens of thousands of participants across 150+ countries. Teams work on challenges covering areas such as:

• Earth observation & climate action
• Space exploration & robotics
• AI, data & technology for science
• Human health & future of life in space

Whether you’re a coder, designer, engineer, storyteller, or space enthusiast, you’ll find a challenge where your skills make a difference.

Why Join in Zurich?

• Be part of the first-ever Zurich edition
• Connect with a global community of innovators
• Collaborate in interdisciplinary teams
• Access NASA’s open data and resources
• Win local prizes & compete for global recognition by NASA

Who Can Join?

Everyone is welcome — from high school students to professionals, beginners to experts. No previous space or coding experience required — just curiosity, creativity, and teamwork!

How to Register

1. Click Register and create account at the platform www.spaceappschallenge.org
2. Chose Zurich location and fill small form there https://linkly.link/2E8Px Closer to the date, you’ll receive access to the official NASA Space Apps platform to select challenges and form teams.
3. After that you are all set for the hackathon!

Let’s solve for Earth and space — together in Zurich!

Learn more about the global program: www.spaceappschallenge.org

Venue update. The hackathon will be in Community event space, final awards at the big Conference hall. Registration for the hackathon at the official website, please create account and choose Zurich as your location :https://linkly.link/2E8Px. Registration is mandatory

Dear Community,

The new fiscal year is starting, and we are thrilled to begin our regular sessions featuring two interesting topics! Cast AI, together with DKB is sponsoring us and we gather at super cool DKB Code Factory.

For further information, check out the details below, and we look forward to having all of you with us!

===================================================

18:30 - Warming up and networking chat 18:45 - Intro by AWS UG Berlin 19:00 - 19:45 - Shahar Morag & Michael Walorski // How DKB Optimizes Cloud Infrastructure at Scale with Automation

Managing cloud infrastructure across multiple teams and environments is complex, especially when a single department is responsible for all infrastructure operations. In this talk, we’ll share how we addressed this challenge and improved our resource usage by integrating K8s automation into our existing workflows, enabling full onboarding across environments with minimal disruption.

19:45 - 20:05 - Network break with snacks & drinks

20:05 - 20:50 - Lisa Mischer // Serverless MCP Servers

The Model Context Protocol (MCP), introduced by Anthropic in late 2024, provides a standardized way for AI to interact with external resources. In the AWS context, this means users can manage S3 objects, query DynamoDB, retrieve RDS data, and trigger workflows simply by chatting with AI clients. In this session, I will show how to build custom and serverless MCP servers with AWS Lambda, as well as how to secure these servers through AWS Cognito authentication. You'll leave with practical knowledge of how to implement AI-powered AWS interactions while maintaining enterprise security standards.

20:50 - 21:00 - Closing Announcements & Networking

===================================================

Very Important: There is no "waitlist" for our regular sessions. However, there are limited seats available. If you want to make sure you can attend: Register yourself with your "full name" here at meetup.com Arrive on time - seats are first come, first serve.

As soon as there are seats available, you are welcome to join with your registration. In case there are no more seats available, we won't be able to let you join us this time.We thank you very much for your understanding!

===================================================

Additional Information

This event is wheelchair friendly. Help us spread the word, and invite your friends & colleagues! If you're attending with wheelchair and need assistance, please mail us: [email protected] for further details.

Would you like to host AWS UG Berlin events at your company? Register here Would you like to speak at AWS UG Berlin sessions? Submit your talk here

Are you getting ready for the NASA Space Apps Challenge 2025? 🚀

Whether it’s your very first hackathon or you’re aiming to take your project even further this year, this webinar will help you and your team start strong and stay on track.

We’re excited to introduce Alan Geirnaert – full-stack developer, aspiring scientific software engineer, and passionate space enthusiast. In 2024, Alan was part of CosmicClassroom, the Global Nominee team at NASA Space Apps in Zurich. This year, he returns as an Expert Mentor for the Swiss edition of Space Apps.

🌟 In this session, Alan will share practical strategies to help you succeed: ✨ How to prepare before the hackathon even begins ✨ Where to find reliable, high-quality datasets ✨ How to turn big ideas into a working solution in just 48 hours ✨ The most common pitfalls to avoid so your team stays focused

🌌 Join us on 30 August at 18:00 CET and walk away with a clear game plan to make the most of your NASA Space Apps Challenge 2025 journey. ✅ Register for the webinar: https://linkly.link/2E8VX

✅ How to Register for NASA Space Apps Challenge 2025:

1. Visit the official website and create your account: https://linkly.link/2E5gn
2. Select Switzerland and find the Zurich location
3. Click “Join this Location” and fill out the short registration form

📬 Once these steps are complete—you’re all set! 🌟 Stay Updated!

💡 Global Challenges: https://www.spaceappschallenge.org/ 💼 Connect with us on LinkedIn: https://linkly.link/2E5iJ

👍 Like, share, and comment to spread the word! 🛰️ Let’s innovate together - for Earth and beyond. May the force (and science) be with you! 🌌

SpaceApps2025 #NASA

In this episode of Hub & Spoken, Jason Foster, CEO & Founder of Cynozure, speaks with David Germain, portfolio Non-Executive Director and former senior technology and transformation leader in banking, financial services and insurance. Drawing on 30 years of global experience, David shares how sustainable business growth depends on more than just strategy and technology - it's rooted in inclusive leadership, organisational culture, and curiosity at every level. They explore why leadership teams must reflect their customer base, how to create psychological safety to encourage innovation, and why "constructive disruption" is essential for long-term success. David discusses the challenge of balancing today's operational pressures with the future ambitions of an organisation, and why trust, diversity of thought, and resilience are non-negotiables. The conversation also examines the role of technology, particularly AI, as both an enabler and a disruptor, and why leaders must prepare their people for the cultural and operational shifts it brings. If you're a business leader seeking practical ways to align people, culture, and technology for lasting impact, this episode offers clear, real-world perspectives. —— Cynozure is a leading data, analytics and AI company that helps organisations to reach their data potential. It works with clients on data and AI strategy, data management, data architecture and engineering, analytics and AI, data culture and literacy, and data leadership. The company was named one of The Sunday Times' fastest-growing private companies in both 2022 and 2023 and recognised as The Best Place to Work in Data by DataIQ in 2023 and 2024. Cynozure is a certified B Corporation. 

Join us for a series of virtual events focused on the most interesting and groundbreaking research presented at this year's CVPR conference!

When

July 10, 2025 at 9 AM Pacific

Where

Online. Register for the Zoom!

OFER : Occluded Face Expression Reconstruction

Reconstructing 3D face models from a single image is an inherently ill-posed problem, which becomes even more challenging in the presence of occlusions where multiple reconstructions can be equally valid. Despite the ubiquity of the problem, very few methods address its multi-hypothesis nature.

In this paper we introduce OFER, a novel approach for single-image 3D face reconstruction that can generate plausible, diverse, and expressive 3D faces by training two diffusion models to generate a shape and expression coefficients of face parametric model, conditioned on the input image. To maintain consistency across diverse expressions, the challenge is to select the best matching shape. To achieve this, we propose a novel ranking mechanism that sorts the outputs of the shape diffusion network based on predicted shape accuracy scores.

Paper: OFER: Occluded Face Expression Reconstruction

About the Speaker

Pratheba Selvaraju has a PhD from the University of Massachusetts, Amherst. Currently researcher at Max Planck Institute – Perceived systems. Research Interest is in 3D reconstruction and modeling problem, geometry processing and generative modeling. Currently also exploring the space of virtual try-ons combining vision and 3D techniques.

SmartHome-Bench: Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal LMMs

Video anomaly detection is crucial for ensuring safety and security, yet existing benchmarks overlook the unique context of smart home environments. We introduce SmartHome-Bench, a dataset of 1,203 smart home videos annotated according to a novel taxonomy of seven anomaly categories, such as Wildlife, Senior Care, and Baby Monitoring. We evaluate state-of-the-art closed- and open-source multimodal LLMs with various prompting techniques, revealing significant performance gaps. To address these limitations, we propose the Taxonomy-Driven Reflective LLM Chain (TRLC), which boosts detection accuracy by 11.62%.

About the Speaker

Xinyi Zhao is a fourth-year PhD student at the University of Washington, specializing in multimodal large language models and reinforcement learning for smart home applications. This work was conducted during her summer 2024 internship at Wyze Labs, Inc.

Interactive Medical Image Analysis with Concept-based Similarity Reasoning

What if you could tell an AI model exactly “𝘸𝘩𝘦𝘳𝘦 𝘵𝘰 𝘧𝘰𝘤𝘶𝘴” and “𝘸𝘩𝘦𝘳𝘦 𝘵𝘰 𝘪𝘨𝘯𝘰𝘳𝘦” on a medical image? Our work enables radiologists to interactively guide AI models at test time for more transparent and trustworthy decision-making. This paper introduces the novel Concept-based Similarity Reasoning network (CSR), which offers (i) patch-level prototype with intrinsic concept interpretation, and (ii) spatial interactivity. First, the proposed CSR provides localized explanation by grounding prototypes of each concept on image regions. Second, our model introduces novel spatial-level interaction, allowing doctors to engage directly with specific image areas, making it an intuitive and transparent tool for medical imaging.

Paper: Interactive Medical Image Analysis with Concept-based Similarity Reasoning

About the Speaker

Huy Ta is a PhD student at the Australian Institute for Machine Learning, The University of Adelaide, specializing in Explainable and Interactive AI for medical imaging. He brings with him four years of industry experience in medical imaging AI prior to embarking on his doctoral studies.

Multi-view Anomaly Detection: From Static to Probabilistic Modelling

The advent of 3D Gaussian Splatting has revolutionized and re-vitalized the interest in multi-view image data. Applications of these techniques to fields such as anomaly detection have been a logical next step. However, some of the limitations of these models may warrant a return to already applied probabilistic techniques. New approaches, difficulties and possibilities in this field will be explored in this talk.

About the Speaker

Mathis Kruse is a PhD student in the group of Bodo Rosenhahn in Hanover, Germany, where he studies anomaly detection (especially in images). He has a particular interest in multi-view data and its learning-based representations.

Join us for a series of virtual events focused on the most interesting and groundbreaking research presented at this year's CVPR conference!

When

July 10, 2025 at 9 AM Pacific

Where

Online. Register for the Zoom!

OFER : Occluded Face Expression Reconstruction

Reconstructing 3D face models from a single image is an inherently ill-posed problem, which becomes even more challenging in the presence of occlusions where multiple reconstructions can be equally valid. Despite the ubiquity of the problem, very few methods address its multi-hypothesis nature.

In this paper we introduce OFER, a novel approach for single-image 3D face reconstruction that can generate plausible, diverse, and expressive 3D faces by training two diffusion models to generate a shape and expression coefficients of face parametric model, conditioned on the input image. To maintain consistency across diverse expressions, the challenge is to select the best matching shape. To achieve this, we propose a novel ranking mechanism that sorts the outputs of the shape diffusion network based on predicted shape accuracy scores.

Paper: OFER: Occluded Face Expression Reconstruction

About the Speaker

Pratheba Selvaraju has a PhD from the University of Massachusetts, Amherst. Currently researcher at Max Planck Institute – Perceived systems. Research Interest is in 3D reconstruction and modeling problem, geometry processing and generative modeling. Currently also exploring the space of virtual try-ons combining vision and 3D techniques.

SmartHome-Bench: Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal LMMs

Video anomaly detection is crucial for ensuring safety and security, yet existing benchmarks overlook the unique context of smart home environments. We introduce SmartHome-Bench, a dataset of 1,203 smart home videos annotated according to a novel taxonomy of seven anomaly categories, such as Wildlife, Senior Care, and Baby Monitoring. We evaluate state-of-the-art closed- and open-source multimodal LLMs with various prompting techniques, revealing significant performance gaps. To address these limitations, we propose the Taxonomy-Driven Reflective LLM Chain (TRLC), which boosts detection accuracy by 11.62%.

About the Speaker

Xinyi Zhao is a fourth-year PhD student at the University of Washington, specializing in multimodal large language models and reinforcement learning for smart home applications. This work was conducted during her summer 2024 internship at Wyze Labs, Inc.

Interactive Medical Image Analysis with Concept-based Similarity Reasoning

What if you could tell an AI model exactly “𝘸𝘩𝘦𝘳𝘦 𝘵𝘰 𝘧𝘰𝘤𝘶𝘴” and “𝘸𝘩𝘦𝘳𝘦 𝘵𝘰 𝘪𝘨𝘯𝘰𝘳𝘦” on a medical image? Our work enables radiologists to interactively guide AI models at test time for more transparent and trustworthy decision-making. This paper introduces the novel Concept-based Similarity Reasoning network (CSR), which offers (i) patch-level prototype with intrinsic concept interpretation, and (ii) spatial interactivity. First, the proposed CSR provides localized explanation by grounding prototypes of each concept on image regions. Second, our model introduces novel spatial-level interaction, allowing doctors to engage directly with specific image areas, making it an intuitive and transparent tool for medical imaging.

Paper: Interactive Medical Image Analysis with Concept-based Similarity Reasoning

About the Speaker

Huy Ta is a PhD student at the Australian Institute for Machine Learning, The University of Adelaide, specializing in Explainable and Interactive AI for medical imaging. He brings with him four years of industry experience in medical imaging AI prior to embarking on his doctoral studies.

Multi-view Anomaly Detection: From Static to Probabilistic Modelling

The advent of 3D Gaussian Splatting has revolutionized and re-vitalized the interest in multi-view image data. Applications of these techniques to fields such as anomaly detection have been a logical next step. However, some of the limitations of these models may warrant a return to already applied probabilistic techniques. New approaches, difficulties and possibilities in this field will be explored in this talk.

About the Speaker

Mathis Kruse is a PhD student in the group of Bodo Rosenhahn in Hanover, Germany, where he studies anomaly detection (especially in images). He has a particular interest in multi-view data and its learning-based representations.

Join us for a series of virtual events focused on the most interesting and groundbreaking research presented at this year's CVPR conference!

When

July 10, 2025 at 9 AM Pacific

Where

Online. Register for the Zoom!

OFER : Occluded Face Expression Reconstruction

Reconstructing 3D face models from a single image is an inherently ill-posed problem, which becomes even more challenging in the presence of occlusions where multiple reconstructions can be equally valid. Despite the ubiquity of the problem, very few methods address its multi-hypothesis nature.

In this paper we introduce OFER, a novel approach for single-image 3D face reconstruction that can generate plausible, diverse, and expressive 3D faces by training two diffusion models to generate a shape and expression coefficients of face parametric model, conditioned on the input image. To maintain consistency across diverse expressions, the challenge is to select the best matching shape. To achieve this, we propose a novel ranking mechanism that sorts the outputs of the shape diffusion network based on predicted shape accuracy scores.

Paper: OFER: Occluded Face Expression Reconstruction

About the Speaker

Pratheba Selvaraju has a PhD from the University of Massachusetts, Amherst. Currently researcher at Max Planck Institute – Perceived systems. Research Interest is in 3D reconstruction and modeling problem, geometry processing and generative modeling. Currently also exploring the space of virtual try-ons combining vision and 3D techniques.

SmartHome-Bench: Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal LMMs

Video anomaly detection is crucial for ensuring safety and security, yet existing benchmarks overlook the unique context of smart home environments. We introduce SmartHome-Bench, a dataset of 1,203 smart home videos annotated according to a novel taxonomy of seven anomaly categories, such as Wildlife, Senior Care, and Baby Monitoring. We evaluate state-of-the-art closed- and open-source multimodal LLMs with various prompting techniques, revealing significant performance gaps. To address these limitations, we propose the Taxonomy-Driven Reflective LLM Chain (TRLC), which boosts detection accuracy by 11.62%.

About the Speaker

Xinyi Zhao is a fourth-year PhD student at the University of Washington, specializing in multimodal large language models and reinforcement learning for smart home applications. This work was conducted during her summer 2024 internship at Wyze Labs, Inc.

Interactive Medical Image Analysis with Concept-based Similarity Reasoning

What if you could tell an AI model exactly “𝘸𝘩𝘦𝘳𝘦 𝘵𝘰 𝘧𝘰𝘤𝘶𝘴” and “𝘸𝘩𝘦𝘳𝘦 𝘵𝘰 𝘪𝘨𝘯𝘰𝘳𝘦” on a medical image? Our work enables radiologists to interactively guide AI models at test time for more transparent and trustworthy decision-making. This paper introduces the novel Concept-based Similarity Reasoning network (CSR), which offers (i) patch-level prototype with intrinsic concept interpretation, and (ii) spatial interactivity. First, the proposed CSR provides localized explanation by grounding prototypes of each concept on image regions. Second, our model introduces novel spatial-level interaction, allowing doctors to engage directly with specific image areas, making it an intuitive and transparent tool for medical imaging.

Paper: Interactive Medical Image Analysis with Concept-based Similarity Reasoning

About the Speaker

Huy Ta is a PhD student at the Australian Institute for Machine Learning, The University of Adelaide, specializing in Explainable and Interactive AI for medical imaging. He brings with him four years of industry experience in medical imaging AI prior to embarking on his doctoral studies.

Multi-view Anomaly Detection: From Static to Probabilistic Modelling

The advent of 3D Gaussian Splatting has revolutionized and re-vitalized the interest in multi-view image data. Applications of these techniques to fields such as anomaly detection have been a logical next step. However, some of the limitations of these models may warrant a return to already applied probabilistic techniques. New approaches, difficulties and possibilities in this field will be explored in this talk.

About the Speaker

Mathis Kruse is a PhD student in the group of Bodo Rosenhahn in Hanover, Germany, where he studies anomaly detection (especially in images). He has a particular interest in multi-view data and its learning-based representations.

Join us for a series of virtual events focused on the most interesting and groundbreaking research presented at this year's CVPR conference!

When

July 10, 2025 at 9 AM Pacific

Where

Online. Register for the Zoom!

OFER : Occluded Face Expression Reconstruction

Reconstructing 3D face models from a single image is an inherently ill-posed problem, which becomes even more challenging in the presence of occlusions where multiple reconstructions can be equally valid. Despite the ubiquity of the problem, very few methods address its multi-hypothesis nature.

In this paper we introduce OFER, a novel approach for single-image 3D face reconstruction that can generate plausible, diverse, and expressive 3D faces by training two diffusion models to generate a shape and expression coefficients of face parametric model, conditioned on the input image. To maintain consistency across diverse expressions, the challenge is to select the best matching shape. To achieve this, we propose a novel ranking mechanism that sorts the outputs of the shape diffusion network based on predicted shape accuracy scores.

Paper: OFER: Occluded Face Expression Reconstruction

About the Speaker

Pratheba Selvaraju has a PhD from the University of Massachusetts, Amherst. Currently researcher at Max Planck Institute – Perceived systems. Research Interest is in 3D reconstruction and modeling problem, geometry processing and generative modeling. Currently also exploring the space of virtual try-ons combining vision and 3D techniques.

SmartHome-Bench: Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal LMMs

Video anomaly detection is crucial for ensuring safety and security, yet existing benchmarks overlook the unique context of smart home environments. We introduce SmartHome-Bench, a dataset of 1,203 smart home videos annotated according to a novel taxonomy of seven anomaly categories, such as Wildlife, Senior Care, and Baby Monitoring. We evaluate state-of-the-art closed- and open-source multimodal LLMs with various prompting techniques, revealing significant performance gaps. To address these limitations, we propose the Taxonomy-Driven Reflective LLM Chain (TRLC), which boosts detection accuracy by 11.62%.

About the Speaker

Xinyi Zhao is a fourth-year PhD student at the University of Washington, specializing in multimodal large language models and reinforcement learning for smart home applications. This work was conducted during her summer 2024 internship at Wyze Labs, Inc.

Interactive Medical Image Analysis with Concept-based Similarity Reasoning

What if you could tell an AI model exactly “𝘸𝘩𝘦𝘳𝘦 𝘵𝘰 𝘧𝘰𝘤𝘶𝘴” and “𝘸𝘩𝘦𝘳𝘦 𝘵𝘰 𝘪𝘨𝘯𝘰𝘳𝘦” on a medical image? Our work enables radiologists to interactively guide AI models at test time for more transparent and trustworthy decision-making. This paper introduces the novel Concept-based Similarity Reasoning network (CSR), which offers (i) patch-level prototype with intrinsic concept interpretation, and (ii) spatial interactivity. First, the proposed CSR provides localized explanation by grounding prototypes of each concept on image regions. Second, our model introduces novel spatial-level interaction, allowing doctors to engage directly with specific image areas, making it an intuitive and transparent tool for medical imaging.

Paper: Interactive Medical Image Analysis with Concept-based Similarity Reasoning

About the Speaker

Huy Ta is a PhD student at the Australian Institute for Machine Learning, The University of Adelaide, specializing in Explainable and Interactive AI for medical imaging. He brings with him four years of industry experience in medical imaging AI prior to embarking on his doctoral studies.

Multi-view Anomaly Detection: From Static to Probabilistic Modelling

The advent of 3D Gaussian Splatting has revolutionized and re-vitalized the interest in multi-view image data. Applications of these techniques to fields such as anomaly detection have been a logical next step. However, some of the limitations of these models may warrant a return to already applied probabilistic techniques. New approaches, difficulties and possibilities in this field will be explored in this talk.

About the Speaker

Mathis Kruse is a PhD student in the group of Bodo Rosenhahn in Hanover, Germany, where he studies anomaly detection (especially in images). He has a particular interest in multi-view data and its learning-based representations.

Join us for a series of virtual events focused on the most interesting and groundbreaking research presented at this year's CVPR conference!

When

July 10, 2025 at 9 AM Pacific

Where

Online. Register for the Zoom!

OFER : Occluded Face Expression Reconstruction

Reconstructing 3D face models from a single image is an inherently ill-posed problem, which becomes even more challenging in the presence of occlusions where multiple reconstructions can be equally valid. Despite the ubiquity of the problem, very few methods address its multi-hypothesis nature.

In this paper we introduce OFER, a novel approach for single-image 3D face reconstruction that can generate plausible, diverse, and expressive 3D faces by training two diffusion models to generate a shape and expression coefficients of face parametric model, conditioned on the input image. To maintain consistency across diverse expressions, the challenge is to select the best matching shape. To achieve this, we propose a novel ranking mechanism that sorts the outputs of the shape diffusion network based on predicted shape accuracy scores.

Paper: OFER: Occluded Face Expression Reconstruction

About the Speaker

Pratheba Selvaraju has a PhD from the University of Massachusetts, Amherst. Currently researcher at Max Planck Institute – Perceived systems. Research Interest is in 3D reconstruction and modeling problem, geometry processing and generative modeling. Currently also exploring the space of virtual try-ons combining vision and 3D techniques.

SmartHome-Bench: Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal LMMs

Video anomaly detection is crucial for ensuring safety and security, yet existing benchmarks overlook the unique context of smart home environments. We introduce SmartHome-Bench, a dataset of 1,203 smart home videos annotated according to a novel taxonomy of seven anomaly categories, such as Wildlife, Senior Care, and Baby Monitoring. We evaluate state-of-the-art closed- and open-source multimodal LLMs with various prompting techniques, revealing significant performance gaps. To address these limitations, we propose the Taxonomy-Driven Reflective LLM Chain (TRLC), which boosts detection accuracy by 11.62%.

About the Speaker

Xinyi Zhao is a fourth-year PhD student at the University of Washington, specializing in multimodal large language models and reinforcement learning for smart home applications. This work was conducted during her summer 2024 internship at Wyze Labs, Inc.

Interactive Medical Image Analysis with Concept-based Similarity Reasoning

What if you could tell an AI model exactly “𝘸𝘩𝘦𝘳𝘦 𝘵𝘰 𝘧𝘰𝘤𝘶𝘴” and “𝘸𝘩𝘦𝘳𝘦 𝘵𝘰 𝘪𝘨𝘯𝘰𝘳𝘦” on a medical image? Our work enables radiologists to interactively guide AI models at test time for more transparent and trustworthy decision-making. This paper introduces the novel Concept-based Similarity Reasoning network (CSR), which offers (i) patch-level prototype with intrinsic concept interpretation, and (ii) spatial interactivity. First, the proposed CSR provides localized explanation by grounding prototypes of each concept on image regions. Second, our model introduces novel spatial-level interaction, allowing doctors to engage directly with specific image areas, making it an intuitive and transparent tool for medical imaging.

Paper: Interactive Medical Image Analysis with Concept-based Similarity Reasoning

About the Speaker

Huy Ta is a PhD student at the Australian Institute for Machine Learning, The University of Adelaide, specializing in Explainable and Interactive AI for medical imaging. He brings with him four years of industry experience in medical imaging AI prior to embarking on his doctoral studies.

Multi-view Anomaly Detection: From Static to Probabilistic Modelling

The advent of 3D Gaussian Splatting has revolutionized and re-vitalized the interest in multi-view image data. Applications of these techniques to fields such as anomaly detection have been a logical next step. However, some of the limitations of these models may warrant a return to already applied probabilistic techniques. New approaches, difficulties and possibilities in this field will be explored in this talk.

About the Speaker

Mathis Kruse is a PhD student in the group of Bodo Rosenhahn in Hanover, Germany, where he studies anomaly detection (especially in images). He has a particular interest in multi-view data and its learning-based representations.

Join us for a series of virtual events focused on the most interesting and groundbreaking research presented at this year's CVPR conference!

When

July 10, 2025 at 9 AM Pacific

Where

Online. Register for the Zoom!

OFER : Occluded Face Expression Reconstruction

Reconstructing 3D face models from a single image is an inherently ill-posed problem, which becomes even more challenging in the presence of occlusions where multiple reconstructions can be equally valid. Despite the ubiquity of the problem, very few methods address its multi-hypothesis nature.

In this paper we introduce OFER, a novel approach for single-image 3D face reconstruction that can generate plausible, diverse, and expressive 3D faces by training two diffusion models to generate a shape and expression coefficients of face parametric model, conditioned on the input image. To maintain consistency across diverse expressions, the challenge is to select the best matching shape. To achieve this, we propose a novel ranking mechanism that sorts the outputs of the shape diffusion network based on predicted shape accuracy scores.

Paper: OFER: Occluded Face Expression Reconstruction

About the Speaker

Pratheba Selvaraju has a PhD from the University of Massachusetts, Amherst. Currently researcher at Max Planck Institute – Perceived systems. Research Interest is in 3D reconstruction and modeling problem, geometry processing and generative modeling. Currently also exploring the space of virtual try-ons combining vision and 3D techniques.

SmartHome-Bench: Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal LMMs

Video anomaly detection is crucial for ensuring safety and security, yet existing benchmarks overlook the unique context of smart home environments. We introduce SmartHome-Bench, a dataset of 1,203 smart home videos annotated according to a novel taxonomy of seven anomaly categories, such as Wildlife, Senior Care, and Baby Monitoring. We evaluate state-of-the-art closed- and open-source multimodal LLMs with various prompting techniques, revealing significant performance gaps. To address these limitations, we propose the Taxonomy-Driven Reflective LLM Chain (TRLC), which boosts detection accuracy by 11.62%.

About the Speaker

Xinyi Zhao is a fourth-year PhD student at the University of Washington, specializing in multimodal large language models and reinforcement learning for smart home applications. This work was conducted during her summer 2024 internship at Wyze Labs, Inc.

Interactive Medical Image Analysis with Concept-based Similarity Reasoning

What if you could tell an AI model exactly “𝘸𝘩𝘦𝘳𝘦 𝘵𝘰 𝘧𝘰𝘤𝘶𝘴” and “𝘸𝘩𝘦𝘳𝘦 𝘵𝘰 𝘪𝘨𝘯𝘰𝘳𝘦” on a medical image? Our work enables radiologists to interactively guide AI models at test time for more transparent and trustworthy decision-making. This paper introduces the novel Concept-based Similarity Reasoning network (CSR), which offers (i) patch-level prototype with intrinsic concept interpretation, and (ii) spatial interactivity. First, the proposed CSR provides localized explanation by grounding prototypes of each concept on image regions. Second, our model introduces novel spatial-level interaction, allowing doctors to engage directly with specific image areas, making it an intuitive and transparent tool for medical imaging.

Paper: Interactive Medical Image Analysis with Concept-based Similarity Reasoning

About the Speaker

Huy Ta is a PhD student at the Australian Institute for Machine Learning, The University of Adelaide, specializing in Explainable and Interactive AI for medical imaging. He brings with him four years of industry experience in medical imaging AI prior to embarking on his doctoral studies.

Multi-view Anomaly Detection: From Static to Probabilistic Modelling

The advent of 3D Gaussian Splatting has revolutionized and re-vitalized the interest in multi-view image data. Applications of these techniques to fields such as anomaly detection have been a logical next step. However, some of the limitations of these models may warrant a return to already applied probabilistic techniques. New approaches, difficulties and possibilities in this field will be explored in this talk.

About the Speaker

Mathis Kruse is a PhD student in the group of Bodo Rosenhahn in Hanover, Germany, where he studies anomaly detection (especially in images). He has a particular interest in multi-view data and its learning-based representations.

Join us for a series of virtual events focused on the most interesting and groundbreaking research presented at this year's CVPR conference!

When

July 10, 2025 at 9 AM Pacific

Where

Online. Register for the Zoom!

OFER : Occluded Face Expression Reconstruction

Reconstructing 3D face models from a single image is an inherently ill-posed problem, which becomes even more challenging in the presence of occlusions where multiple reconstructions can be equally valid. Despite the ubiquity of the problem, very few methods address its multi-hypothesis nature.

In this paper we introduce OFER, a novel approach for single-image 3D face reconstruction that can generate plausible, diverse, and expressive 3D faces by training two diffusion models to generate a shape and expression coefficients of face parametric model, conditioned on the input image. To maintain consistency across diverse expressions, the challenge is to select the best matching shape. To achieve this, we propose a novel ranking mechanism that sorts the outputs of the shape diffusion network based on predicted shape accuracy scores.

Paper: OFER: Occluded Face Expression Reconstruction

About the Speaker

Pratheba Selvaraju has a PhD from the University of Massachusetts, Amherst. Currently researcher at Max Planck Institute – Perceived systems. Research Interest is in 3D reconstruction and modeling problem, geometry processing and generative modeling. Currently also exploring the space of virtual try-ons combining vision and 3D techniques.

SmartHome-Bench: Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal LMMs

Video anomaly detection is crucial for ensuring safety and security, yet existing benchmarks overlook the unique context of smart home environments. We introduce SmartHome-Bench, a dataset of 1,203 smart home videos annotated according to a novel taxonomy of seven anomaly categories, such as Wildlife, Senior Care, and Baby Monitoring. We evaluate state-of-the-art closed- and open-source multimodal LLMs with various prompting techniques, revealing significant performance gaps. To address these limitations, we propose the Taxonomy-Driven Reflective LLM Chain (TRLC), which boosts detection accuracy by 11.62%.

About the Speaker

Xinyi Zhao is a fourth-year PhD student at the University of Washington, specializing in multimodal large language models and reinforcement learning for smart home applications. This work was conducted during her summer 2024 internship at Wyze Labs, Inc.

Interactive Medical Image Analysis with Concept-based Similarity Reasoning

What if you could tell an AI model exactly “𝘸𝘩𝘦𝘳𝘦 𝘵𝘰 𝘧𝘰𝘤𝘶𝘴” and “𝘸𝘩𝘦𝘳𝘦 𝘵𝘰 𝘪𝘨𝘯𝘰𝘳𝘦” on a medical image? Our work enables radiologists to interactively guide AI models at test time for more transparent and trustworthy decision-making. This paper introduces the novel Concept-based Similarity Reasoning network (CSR), which offers (i) patch-level prototype with intrinsic concept interpretation, and (ii) spatial interactivity. First, the proposed CSR provides localized explanation by grounding prototypes of each concept on image regions. Second, our model introduces novel spatial-level interaction, allowing doctors to engage directly with specific image areas, making it an intuitive and transparent tool for medical imaging.

Paper: Interactive Medical Image Analysis with Concept-based Similarity Reasoning

About the Speaker

Huy Ta is a PhD student at the Australian Institute for Machine Learning, The University of Adelaide, specializing in Explainable and Interactive AI for medical imaging. He brings with him four years of industry experience in medical imaging AI prior to embarking on his doctoral studies.

Multi-view Anomaly Detection: From Static to Probabilistic Modelling

The advent of 3D Gaussian Splatting has revolutionized and re-vitalized the interest in multi-view image data. Applications of these techniques to fields such as anomaly detection have been a logical next step. However, some of the limitations of these models may warrant a return to already applied probabilistic techniques. New approaches, difficulties and possibilities in this field will be explored in this talk.

About the Speaker

Mathis Kruse is a PhD student in the group of Bodo Rosenhahn in Hanover, Germany, where he studies anomaly detection (especially in images). He has a particular interest in multi-view data and its learning-based representations.

Join fellow Airflow enthusiasts and industry leaders at the Marriott Downtown for an evening of insightful talks, great food and drinks, and exclusive swag!

This event brings together seasoned pros to explore cutting-edge strategies for managing complex DAG codebases, orchestrating large-scale data workflows, and unlocking the powerful new capabilities of Apache Airflow 3. Don't miss this opportunity to connect, learn, and level up your Airflow expertise!

PRESENTATIONS

Contending with Complex DAG Codebases - a Codemodding Approach

• Speaker: Alex Tomic, Data Engineering Independent Contractor
• As Airflow adoption continues to increase, organizations are faced with a mounting challenge of maintaining projects over the long-term, while meeting the demand for new project onboarding. Codemodding, a process to automatically modify code, is a valuable new tool to empower project and platform teams to develop, manage and support ever more complex dag codebases and workflows.

Harmonizing Music Rights at Scale: Airflow for Ownership Resolution and Fair Royalties

• Speaker: Pei-Chi Chen, Lead Data Engineer, Create Music Group
• In this session, we’ll share how Create Music Group leverages Apache Airflow to resolve music rights ownership conflicts—an ongoing challenge that increases costs and disrupts operations. We’ll dive into our Airflow-driven approach for large-scale, vital data collection and discuss best practices we’ve adopted from Airflow Summit 2024 to combat zombie tasks, out-of-memory issues, and worker configuration tuning. We'll also showcase how these techniques have helped us distribute revenue more accurately and streamline daily operations. This session provides a real-world, production-level example of Airflow’s power in action.

Unlocking the Future of Data Orchestration: Introducing Apache Airflow® 3

• Speaker: Constance Martineau, Staff Product Manager, Astronomer
• Airflow 3 is here, bringing a new era of flexibility, scalability, and security to data orchestration. This release introduces powerful new capabilities to simplify pipeline management, enhance security, and enable seamless execution across diverse environments. In this session, we’ll explore key innovations, including an upgraded UI, DAG Versioning, scheduler-integrated backfills, stronger task isolation, and support for remote execution. Join us to discover how Airflow 3 is redefining orchestration and empowering teams to build and scale workflows like never before!

AGENDA

• 5:30-6PM: Arrivals, eat, drink, and network
• 6-7:40PM: Presentations
• 7:40-8PM: Networking

PyCon US 2025 is coming to Pittsburgh this May 14–22, and PyData Pittsburgh is thrilled to be part of it! We’re hosting the Hometown Heroes Hatchery track on Saturday, May 17—a half-day event inside the conference celebrating the incredible work of Python developers, researchers, educators, and technologists from across our city. As part of PyCon’s Hatchery initiative, this track will feature presentations and lightning talks that highlight the creativity and impact of Pittsburgh’s Python community.

If you're attending PyCon US 2025, we invite the PyData Pittsburgh community to join us at the Hometown Heroes track—come connect, engage, and help showcase the strength of our local tech scene.

Please note: you must be registered for PyCon US 2025 to attend this event, and all attendees and speakers are responsible for securing their own tickets. You can find registration details for the Conference here:https://us.pycon.org/2025/attend/information/.

HOMETOWN HEROES HATCHERY PROGRAM - May 17th

TALK SCHEDULE:

Decoding Spatial Biology with Python: Multi-Modal Insights into Breast Cancer Progression Time: 01:45 PM - 02:15 PM Speakers: Alex C. Chang, CMU-Pitt (Graduate Student PhD, Computational Biology ) and Brent Schlegel, University of Pittsburgh School of Medicine (Graduate Student PhD, Integrative Systems Biology)

Python has rapidly become a cornerstone of scientific computing, computational biology, and bioinformatics due to its ease of use and scalability for handling large datasets—qualities that are critical in today’s “big data” era of clinical and translational research. As computational resources and data collection methods continue to expand, we are now empowered to ask larger and more clinically relevant questions that enable us to dissect complex biological systems with unprecedented detail. However, this surge in data complexity brings new challenges, from the integration of diverse data modalities to the need for sophisticated analytical methods capable of untangling intricate biological signals from background noise. In this talk, we describe how Python not only meets these challenges but also drives innovation through the development of novel bioinformatics tools like CITEgeist—a case study in harnessing Python’s capabilities for multi-modal spatial transcriptomics. Biological datasets often face challenges of high sparsity and noise. CITEgeist harnesses Python’s robust ecosystem to provide an efficient, scalable pipeline that deconvolutes messy spatial signals into actionable, clinically relevant features.

Exploring Energy Burden in Pittsburgh Neighborhoods with Python Time: 02:30 PM - 03:00 PM Speakers: Ling Almoubayyed, SmithGroup, Inc. (Project Manager) and Husni Almoubayyed, Carnegie Learning

National-level energy studies consistently find that energy burdens are a significant challenge, and that lower-income neighborhoods sometimes end up paying more for energy in cities including Pittsburgh. Using Python, we were able to extract and analyze data on energy consumption in the City of Pittsburgh, along with real-estate and geographic information system (GIS) data to compare trends in energy usage and burden across Pittsburgh neighborhoods, and across different housing types. We present statistical analyses and Python visualizations describing these trends across different features such as housing price, size, and neighborhood.

Bottling Tesla's Solar: A Solar Dashboard with Python Time: 03:15 PM - 03:45 PM Speaker: Christopher Pitstick (Sr. SWE)

Tesla's Powerwall/Inverter solar ecosystem are powerful yet notoriously opaque. For home labbers, extracting meaningful data can be daunting—but not impossible. In this talk, I'll share my journey of developing a custom solar dashboard using Grafana and PyPowerwall, navigating the quirks and closed nature of Tesla's ecosystem along the way. The backend is all Python, so I will demo my server code and dashboard to show how I was able find hundreds of kilowatt hours in lost solar production. In this talk, we'll do a deep dive into the way I altered the Python server code to be able to query multiple inverters at the same time with complex iptable rules. This presentation may conclude with the value of installing solar on your home, and how self-monitoring is a critical component of every nerd's arsenal.

Strategies for Eliciting Structured Ouputs from LLMs Time: 03:50 PM - 03:55 PM Speaker: Utkarsh Tripathi, Solventum (Machine Learning Engineer)

This lightning talk will provide a concise yet comprehensive overview of techniques for extracting structured, predictable outputs from Large Language Models. I will compare and demonstrate multiple state-of-the-art libraries (such as BAML, Instructor, Langchain, SGLang etc. + how they work under the hood), utilize pydantic / dataclass / etc. to get structured outputs. We will explore practical examples of JSON schema enforcement, markdown formatting directives, and template-based approaches that dramatically improve downstream processing capabilities. The presentation will include code snippets and prompt templates that participants can immediately implement in their own projects.

Does Generative AI Know Statistics? Time: 03:55 PM - 04:00 PM Speaker: Louis Luangkesorn, Highmark Health (Lead Data Scientist)

Generative AI has promise to impact many fields of endeavor. But experience has shown that it often has problems with nuance and context. This talk discusses some experiences using Generative AI as an aid in applied analytics and walks through an example that illustrates working around its weaknesses and taking advantage of its capabilities.

Demystifying How Animal Behavior Affects Disease Spread Using Python Time: 04:00 PM - 04:05 PM Speaker: Carolyn Tett, University of Pittsburgh (Research Technician)

Not all individuals contribute equally to disease spread. During COVID-19, social distancing reduced transmission for some, while high-contact individuals increased disease spread. Preventative measures for massive disease outbreaks, however, cannot rely solely on data from rare epidemic events. Instead, disease ecologists study animal models to understand how host behavior theoretically drives disease outbreaks. Tracking animal movement and interactions is essential for identifying transmission-relevant behaviors. In lab experiments, video recordings provide an abundance of behavioral data, now efficiently processed through automation, and coding languages like Python enable large-scale data analysis. The Stephenson Lab at the University of Pittsburgh uses Raspberry Pis to autonomously record guppies infected with an ectoparasite. These parasites transmit primarily through instances of close contact between hosts. Through autonomous video recordings, we generated 1,300 hours of footage—equivalent to 54 consecutive days of observation. Given that each video captures six guppies, manually tracking behavior would take tens of billions of days. Instead, animal tracking software reduces this processing time to a mere few months.

The Many-Colored Functions of Async Python Time: 04:15 PM - 04:45 PM Speaker: Bryan C. Mills, Duolingo (Senior Software Engineer)

You might think of functions in async Python in terms of “synchronous” and “async”, but the possibility of binding objects (such as Locks) to the asyncio event loop adds a whole new dimension to consider. We'll examine six vibrant kinds of functions and how they interact! This talk will examine code examples of how to adapt each kind of function to call other kinds, suggest design patterns that minimize the complexity of dealing with different kinds (such as non-blocking context managers), and examine patterns or libraries to safely synchronize concurrent calls involving multiple kinds of function.

Automated Dependency Inference and its Applications Time: 05:00 PM - 05:30 PM Speaker: Jason R. Coombs, Microsoft (Principal Software Engineer)

Last summer, I launched the Coherent Software Development System (https://bit.ly/coherent-system) with the principal that one should not have to repeat themselves when developing more than one Python project. One of the key innovations of that system is coherent.deps, a system for deriving package dependencies from the imports that a project or script uses. I'll explore some of the background motivations from Google's monorepo, some prior art at Meta, and some of the approaches that failed (AI-based inference) before going into the details of the implementation (AST parsing, world-readable MongoDB database, Big Table query to PyPI downloads). I'll additionally talk about some of the applications of this generalized library (coherent.build, pip-run), some of the maintenance challenges (expensive query, refresh interval), and possible other applications (on-demand dependency loader).

SPEAKER BIOS:

Alex C. Chang Alexander Chih-Chieh Chang is a fourth-year MSTP student in the CMU-Pitt Computational Biology Ph.D. Program, mentored by Drs. Lee and Oesterreich. He earned a BS/BA in Chemical and Biomolecular Engineering/Sociology from Johns Hopkins University in 2021. Previously, during his undergraduate research in the lab of Rong Li, Ph.D., he conducted large-scale genomic screens to study proteomic dysregulation and spent a gap year in the lab of Manish Aghi, MD. PhD., studying breast cancer metastasis to the brain. Currently, as a computational biologist and medical student, he coordinates the Hope for OTHERS tissue donation program in the Lee-Oesterreich Lab and computational research projects in breast cancer metastasis and genomic evolution. Brent Schlegel Brent Schlegel is a first-year PhD student in Integrative Systems Biology at the University of Pittsburgh School of Medicine, co-mentored by Drs. Adrian Lee and Steffi Oesterreich. He earned his AS in Mathematics and Sciences from CCAC (2019) and a BS in Computational Biology from Pitt (2021). Most recently, he worked as a Bioinformatics Analyst at the UPMC Children’s Hospital of Pittsburgh, where he specialized in the integrative analysis of large, complex biomedical datasets. Now, Brent combines data science, computational modeling, and multi-omic integration to tackle the systems biology of invasive lobular breast cancer, using patient-derived organoid models and leveraging “big data” to uncover hidden patterns and drive innovation in diagnosis and treatment.

Ling Almoubayyed Ling is an experienced architecture and urban designer with extensive project management expertise. Specializing in urban design, planning, community engagement, and spatial analysis, she has successfully led projects ranging from individual buildings to comprehensive urban districts. Ling uses evidence-based design with data gathered through stakeholder engagement to identify the best design solutions to create built environments. She is currently a Project Manager with SmithGroup. Husni Almoubayyed Husni Almoubayyed is the Director of AI at Pittsburgh-based education technology company Carnegie Learning. Husni uses machine learning and data science methods to conduct research in education, specifically in topics such as personalization, equity, and predictive analytics. Prior to his work in education technology, Husni acquired a Ph.D. in Astrophysics from Carnegie Mellon University, where he worked on mitigating biases in astronomical data to advance understanding of dark energy. Needless to say, Python is Husni's favorite programming language, and PyCon is one of his favorite events of the year!

Christopher Pitstick Christopher, a passionate software engineer who installed solar panels on his home in 2024, quickly immersed himself in system analysis to optimize performance—expertise that directly inspired this presentation. His programming journey began at age 12 with QBasic, igniting a lifelong passion that led to roles at industry giants including Microsoft, Amazon, and Argo AI before joining his current position at Latitude. Throughout his career, Christopher has mastered multiple programming languages from C++ to Perl and Python, approaching coding both as a profession and personal passion. As a dedicated neurodiversity advocate, he regularly shares his experiences through public speaking engagements, raising awareness and empowering others in the tech community.

Utkarsh Tripathi Utkarsh Tripathi is a Machine Learning Engineer at Solventum, Inc., where he works on Solventum™ Fluency Align™ and Solventum™ Fluency Direct™ : AI-powered clinical documentation tools that leverage conversational and generative AI, along with ambient intelligence, to automate medical documentation. These solutions help reduce administrative work and physician burnout, while improving the overall patient care experience. Utkarsh holds degrees in Electrical Engineering, Chemistry, and Computer Science from BITS Pilani and the University of Chicago.

Louis Luangkesorn Dr. Louis Luangkesorn is a Lead Data Scientist at Highmark Health where he works on projects applying statistical, predictive, operations research, and Generative AI models in use cases involving human resources and healthcare. He has contributed code to Scipy and a book appendix porting a simulation textbook's examples to Simpy.

Carolyn Tett Carolyn is an ecologist that specializes in animal behavior and disease ecology. She works with guppies and their ectoparasites to better understand how host contact rate and physiological status impact disease spread. She captures guppy behaviors on video and uses Python to automate the video processing. Using these outputs, she quantifies guppy social metrics and runs statistical models to predict behavior-mediated parasite spread.

Bryan C. Mills Bryan maintains Python core services at Duolingo, and was formerly a maintainer on the Go project at Google.

Jason R. Coombs Jason's been a passionate contributor to Python and open source software since the 90's, is a core contributor to Python, and maintains hundreds of packages in PyPI.