talk-data.com

We're excited to invite you to our next Meetup, co-hosted with the London Java Community!

Join fellow graph enthusiasts, Neo4j developers, and members of the Java community as we explore how graphs, knowledge graphs, and context engineering can unlock smarter applications and better answers. We’ll also uncover how AI-generated code can be weaponized, exposing hidden vulnerabilities in the software we trust. Whether you’re curious about building with graph-powered AI or safeguarding your projects from new threats, this meetup will give you insights you can put into practice.

Session 1: Black Friday Brilliance: Managing a Billion Transactions with Tech, Tactics, and Teamwork by Jamie Colmans

The Black Friday and Cyber Monday period is one of the busiest times in the retail calendar, both in stores and online, and here at Loqate our customers rely on our infrastructure to support their businesses at this crucial time. Over the four-day BFCM period in 2023 we processed over 1 billion requests to our APIs, and we managed this with greater than 99.99% availability! We've seen our request volume increase over 100x in the last 10 years, and managing this requires the right technologies, careful planning, and a great team of people.

With insightful commentary from a cross-section of our brilliant Dev team, I’ll talk you through how we scale our infrastructure to support these increases in traffic, and some of the technologies and processes we use. I’ll also give some insights into how the team works together over this busy period to keep everything running smoothly.

Session 2: WhatsThat? Using graphs and AI to make sense of your friends WhatsApp group by Martin O'Hanlon

Communication, messaging, and memory are complicated. How are you supposed to keep up with it all? It's difficult for you to keep up with the constant stream of messages you get. How can we expect an LLM to do the same? Let's look at how we can use graphs and AI to summarise the complex streams of messages you get in that oddly titled WhatsApp group.

We look forward to connecting with the community to exchange ideas on graphs, tech, and AI - join the discussion!

This talk presents a technical case study of applying agentic AI systems to automate community operations at PyCon DE & PyData, treated as an open-source testbed. The key lesson is simple: AI only works when put on a leash. Reliable results required good architecture, a clear plan, and structured data models — from YAML and Pydantic schemas to reproducible pipelines with GitHub Actions. With that foundation, LLM agents supported logistics, FAQs, video processing, and scheduling; without it, they failed. By contrasting successes and failure modes across different coding agents, the talk demonstrates that robust design, validation, and controlled context are prerequisites for making agentic AI usable in real-world workflows.

Today, I'm chatting with Stuart Winter-Tear about AI product management. We're getting into the nitty-gritty of what it takes to build and launch LLM-powered products for the commercial market that actually produce value. Among other things in this rich conversation, Stuart surprised me with the level of importance he believes UX has in making LLM-powered products successful, even for technical audiences.

After spending significant time on the forefront of AI’s breakthroughs, Stuart believes many of the products we’re seeing today are the result of FOMO above all else. He shares a belief that I’ve emphasized time and time again on the podcast–product is about the problem, not the solution. This design philosophy has informed Staurt’s 20-plus year-long career, and it is pivotal to understanding how to best use AI to build products that meet users’ needs.

Highlights/ Skip to 

Why Stuart was asked to speak to the House of Lords about AI (2:04) The LLM-powered products has Stuart been building recently (4:20) Finding product-market fit with AI products (7:44) Lessons Stuart has learned over the past two years working with LLM-power products (10:54)  Figuring out how to build user trust in your AI products (14:40) The differences between being a digital product manager vs. AI product manager (18:13) Who is best suited for an AI product management role (25:42) Why Stuart thinks user experience matters greatly with AI products (32:18) The formula needed to create a business-viable AI product (38:22)  Stuart describes the skills and roles he thinks are essential in an AI product team and who he brings on first (50:53) Conversations that need to be had with academics and data scientists when building AI-powered products (54:04) Final thoughts from Stuart and where you can find more from him (58:07)

Quotes from Today’s Episode

“I think that the core dream with GenAI is getting data out of IT hands and back to the business. Finding a way to overlay all this disparate, unstructured data and [translate it] to the human language is revolutionary. We’re finding industries that you would think were more conservative (i.e. medical, legal, etc.) are probably the most interested because of the large volumes of unstructured data they have to deal with. People wouldn’t expect large language models to be used for fact-checking… they’re actually very powerful, especially if you can have your own proprietary data or pipelines. Same with security–although large language models introduce a terrifying amount of security problems, they can also be used in reverse to augment security. There’s a lovely contradiction with this technology that I do enjoy.” - Stuart Winter-Tear (5:58) “[LLM-powered products] gave me the wow factor, and I think that’s part of what’s caused the problem. If we focus on technology, we build more technology, but if we focus on business and customers, we’re probably going to end up with more business and customers. This is why we end up with so many products that are effectively solutions in search of problems. We’re in this rush and [these products] are [based on] FOMO. We’re leaving behind what we understood about [building] products—as if [an LLM-powered product] is a special piece of technology. It’s not. It’s another piece of technology. [Designers] should look at this technology from the prism of the business and from the prism of the problem. We love to solutionize, but is the problem the problem? What’s the context of the problem? What’s the problem under the problem? Is this problem worth solving, and is GenAI a desirable way to solve it? We’re putting the cart before the horse.” - Stuart Winter-Tear (11:11) “[LLM-powered products] feel most amazing when you’re not a domain expert in whatever you’re using it for. I’ll give you an example: I’m terrible at coding. When I got my hands on Cursor, I felt like a superhero. It was unbelievable what I could build. Although [LLM products] look most amazing in the hands of non-experts, it’s actually most powerful in the hands of experts who do understand the domain they’re using this technology. Perhaps I want to do a product strategy, so I ask [the product] for some assistance, and it can get me 70% of the way there. [LLM products] are great as a jumping off point… but ultimately [they are] only powerful because I have certain domain expertise.” - Stuart Winter-Tear (13:01) “We’re so used to the digital paradigm. The deterministic nature of you put in X, you get out Y; it’s the same every time. Probabilistic changes every time. There is a huge difference between what results you might be getting in the lab compared to what happens in the real world. You effectively find yourself building [AI products] live, and in order to do that, you need good communities and good feedback available to you. You need these fast feedback loops. From a pure product management perspective, we used to just have the [engineering] timeline… Now, we have [the data research timeline]. If you’re dealing with cutting-edge products, you’ve got these two timelines that you’re trying to put together, and the data research one is very unpredictable. It’s the nature of research. We don’t necessarily know when we’re going to get to where we want to be.” - Stuart Winter-Tear (22:25) “I believe that UX will become the #1 priority for large language model products. I firmly believe whoever wins in UX will win in this large language model product world.  I’m against fully autonomous agents without human intervention for knowledge work. We need that human in the loop. What was the intent of the user? How do we get that right push back from the large language model to understand even the level of the person that they’re dealing with? These are fundamental UX problems that are going to push UX to the forefront… This is going to be on UX to educate the user, to be able to inject the user in at the right time to be able to make this stuff work. The UX folk who do figure this out are going to create the breakthrough and create the mass adoption.” - Stuart Winter-Tear (33:42)

Welcome to the PyData Berlin March meetup!

We would like to welcome you all starting from 18:45. There will be food and drinks. The talks begin around 19.30 and the doors will close at 19:30. Make sure to arrive on time!

*** Important!! *** Please keep in mind that there is a BVG strike on this day, affecting U-Bahn, trams, and buses. S-Bahn and regional trains will work.

Please provide your first and last name for the registration because this is required for the venue's entry policy. If you cannot attend, please cancel your spot so others are able to join as the space is limited.

Host: Bonial is excited to welcome you to this month's version of PyData. ************************************************************************** The Lineup for the evening

Talk 1: Extract structured product & deal information from PDFs on scale via LLM Abstract: Bonial shows hundreds of thousands of offers from local brick-and-mortar retailers on its platform, a subset of this content is retrieved from PDF files. In this talk I’ll explain how we leverage LLM to parse unstructured PDF files to create content on our platform.

Speaker: Philipp Johannis has been part of Bonial for 12 years. He established and leads the Data Department, which consists of multiple Analytics, Engineering & Data Science teams, and is currently serving as Head of Data. He focuses on improving the data platform and enabling and supporting the development of various data driven products such as personalisation and traffic management.

Talk 2: Airweave, an Open-Source Tool To Turn Any App Into Accessible Agent Knowledge Abstract: The talk will be an introduction to Airweave, which is an open-source Python tool that helps agent developers turn app data into accessible knowledge for AI agents. It connects to any app, database, URL, or API and structures the data for retrieval. Airweave automates authentication, ingestion, enrichment, mapping, and syncing to vector stores and graph databases of choice. It has a search layer for agents out-of-the-box and allows extension of the platform with minimal code. Developers can use Airweave via our web UI, REST API, or SDKs.

Speakers: Lennert Jansen and Rauf Akdemir are the creators of Airweave AI. Lennert is an AI Engineer & Researcher with a background in Applied Statistics and Deep Learning for NLP. Before Airweave, he worked on AI & Bayesian Statistics at Amazon, IBM, and the University of Amsterdam. Rauf is a CS graduate from Technical University of Delft, with strong engineering experience in productionising ML & data infrastructure in both start-ups and enterprise.

Lightning talks There will be slots for 2-3 Lightning Talks (3-5 Minutes for each). Kindly let us know if you would like to present something at the start of the meetup :)

*** NumFOCUS Code of Conduct THE SHORT VERSION Be kind to others. Do not insult or put down others. Behave professionally. Remember that harassment and sexist, racist, or exclusionary jokes are not appropriate for NumFOCUS. All communication should be appropriate for a professional audience including people of many different backgrounds. Sexual language and imagery are not appropriate. NumFOCUS is dedicated to providing a harassment-free community for everyone, regardless of gender, sexual orientation, gender identity, and expression, disability, physical appearance, body size, race, or religion. We do not tolerate harassment of community members in any form. Thank you for helping make this a welcoming, friendly community for all. If you haven't yet, please read the detailed version here: https://numfocus.org/code-of-conduct ***

Are you prepared for the hidden UX taxes that AI and LLM features might be imposing on your B2B customers—without your knowledge? Are you certain that your AI product or features are truly delivering value, or are there unseen taxes that are working against your users and your product / business? In this episode, I’m delving into some of UX challenges that I think need to be addressed when implementing LLM and AI features into B2B products.

While AI seems to offer the change for significantly enhanced productivity, it also introduces a new layer of complexity for UX design. This complexity is not limited to the challenges of designing in a probabilistic medium (i.e. ML/AI), but also in being able to define what “quality” means. When the product team does not have a shared understanding of what a measurably better UX outcome means, improved sales and user adoption are less likely to follow. 

I’ll also discuss aspects of designing for AI that may be invisible on the surface. How might AI-powered products change the work of B2B users? What are some of the traps I see some startup clients and founders I advise in MIT’s Sandbox venture fund fall into?

If you’re a product leader in B2B / enterprise software and want to make sure your AI capabilities don’t end up creating more damage than value for users,  this episode will help!  

Highlights/ Skip to 

Improving your AI model accuracy improves outputs—but customers only care about outcomes (4:02) AI-driven productivity gains also put the customer’s “next problem” into their face sooner. Are you addressing the most urgent problem they now have—or used to have? (7:35) Products that win will combine AI with tastefully designed deterministic-software—because doing everything for everyone well is impossible and most models alone aren’t products (12:55) Just because your AI app or LLM feature can do ”X” doesn't mean people will want it or change their behavior (16:26) AI Agents sound great—but there is a human UX too, and it must enable trust and intervention at the right times (22:14) Not overheard from customers: “I would buy this/use this if it had AI” (26:52) Adaptive UIs sound like they’ll solve everything—but to reduce friction, they need to adapt to the person, not just the format of model outputs (30:20) Introducing AI introduces more states and scenarios that your product may need to support that may not be obvious right away (37:56)

Quotes from Today’s Episode

Product leaders have to decide how much effort and resources you should put into model improvements versus improving a user’s experience. Obviously, model quality is important in certain contexts and regulated industries, but when GenAI errors and confabulations are lower risk to the user (i.e. they create minor friction or inconveniences), the broader user experience that you facilitate might be what is actually determining the true value of your AI features or product. Model accuracy alone is not going to necessarily lead to happier users or increased adoption. ML models can be quantifiably tested for accuracy with structured tests, but because they’re easier to test for quality vs. something like UX doesn’t mean users value these improvements more. The product will stand a better chance of creating business value when it is clearly demonstrating it is improving your users’ lives. (5:25) When designing AI agents, there is still a human UX - a beneficiary - in the loop. They have an experience, whether you designed it with intention or not. How much transparency needs to be given to users when an agent does work for them? Should users be able to intervene when the AI is doing this type of work?  Handling errors is something we do in all software, but what about retraining and learning so that the future user experiences is better? Is the system learning anything while it’s going through this—and can I tell if it’s learning what I want/need it to learn? What about humans in the loop who might interact with or be affected by the work the agent is doing even if they aren’t the agent’s owner or “user”? Who’s outcomes matter here? At what cost? (22:51) Customers primarily care about things like raising or changing their status, making more money, making their job easier, saving time, etc. In fact,I believe a product marketed with GenAI may eventually signal a negative / burden on customers thanks to the inflated and unmet expectations around AI that is poorly implemented in the product UX. Don’t think it’s going to be bought just because it using  AI in a novel way. Customers aren’t sitting around wishing for “disruption” from your product; quite the opposite. AI or not, you need to make the customer the hero. Your AI will shine when it delivers an outsized UX outcome for your users (27:49) What kind of UX are you delivering right out of the box when a customer tries out your AI product or feature? Did you design it for tire kicking, playing around, and user stress testing? Or just an idealistic happy path? GenAI features inside b2b products should surface capabilities and constraints particularly around where users can create value for themselves quickly.  Natural hints and well-designed prompt nudges in LLMs for example are important to users and to your product team: because you’re setting a more realistic expectation of what’s possible with customers and helping them get to an outcome sooner. You’re also teaching them how to use your solution to get the most value—without asking them to go read a manual. (38:21)

Create LLM-powered autonomous agents and intelligent assistants tailored to your business and personal needs. From script-free customer service chatbots to fully independent agents operating seamlessly in the background, AI-powered assistants represent a breakthrough in machine intelligence. In AI Agents in Action, you'll master a proven framework for developing practical agents that handle real-world business and personal tasks. Author Micheal Lanham combines cutting-edge academic research with hands-on experience to help you: Understand and implement AI agent behavior patterns Design and deploy production-ready intelligent agents Leverage the OpenAI Assistants API and complementary tools Implement robust knowledge management and memory systems Create self-improving agents with feedback loops Orchestrate collaborative multi-agent systems Enhance agents with speech and vision capabilities You won't find toy examples or fragile assistants that require constant supervision. AI Agents in Action teaches you to build trustworthy AI capable of handling high-stakes negotiations. You'll master prompt engineering to create agents with distinct personas and profiles, and develop multi-agent collaborations that thrive in unpredictable environments. Beyond just learning a new technology, you'll discover a transformative approach to problem-solving. About the Technology Most production AI systems require many orchestrated interactions between the user, AI models, and a wide variety of data sources. AI agents capture and organize these interactions into autonomous components that can process information, make decisions, and learn from interactions behind the scenes. This book will show you how to create AI agents and connect them together into powerful multi-agent systems. About the Book In AI Agents in Action, you’ll learn how to build production-ready assistants, multi-agent systems, and behavioral agents. You’ll master the essential parts of an agent, including retrieval-augmented knowledge and memory, while you create multi-agent applications that can use software tools, plan tasks autonomously, and learn from experience. As you explore the many interesting examples, you’ll work with state-of-the-art tools like OpenAI Assistants API, GPT Nexus, LangChain, Prompt Flow, AutoGen, and CrewAI. What's Inside Knowledge management and memory systems Feedback loops for continuous agent learning Collaborative multi-agent systems Speech and computer vision About the Reader For intermediate Python programmers. About the Author Micheal Lanham is a software and technology innovator with over 20 years of industry experience. He has authored books on deep learning, including Manning’s Evolutionary Deep Learning. Quotes This is about to become the hottest area of applied AI. Get a head start with this book! - Richard Davies, author of Prompt Engineering in Practice Couldn’t put this book down! It’s so comprehensive and clear that I felt like I was learning from a master teacher. - Radhika Kanubaddhi, Amazon An enlightening journey! This book transformed my questions into answers. - Jose San Leandro, ACM-SL Expertly guides through creating agent profiles, using tools, memory, planning, and multi-agent systems. Couldn’t be more timely! - Grigory Sapunov author of JAX in Action

Hello Testers,

After the passionate response on one of our past offline events in other cities, we’re here to bring you all together in Berlin.

We’ve brought The Test Tribe 1st Berlin Meetup to all of you!

Excited To Know When It’s Happening? Date: 27th Septemper 2024 Time: 06:00 PM to 08:00 PM CET Venue: The Cooks Connection-Berlin · Sophie-Charlotten-Straße 50, 14059 Berlin

Session #1: The 5E Mental Model for LLM-Assisted Pluralistic Testing GenAI, specifically the Large Language Models, are the new shiny thing. Like others, testers are also amused by this new technology. Alas, most such amusement is confined to shallow experiments and those too confined to raw prompting at the web GUI interface layer for the said models like ChatGPT. Of course, the results seen by most testers are superficial accordingly. Many such testers become disinterested in the LLMs because of this experience, although a deeper look could have changed their minds.

This talk explores many more opportunities with the discussion based on The 5E Model for using LLMs in testing, developed by Rahul Verma. LLMs, with the inherent limitations of non-determinism and other flaws, can still be put to practical use in many activities in testing. The 5E model to think about LLMs right from a simple start to the very complex organisational situations.

About Speaker:

Rahul Verma, Senior Consultant and Coach at trendig technology services GmbH

Rahul Verma is an awarded thought leader for his contributions to the testing community. He is a Senior Coach and Consultant with trendig technology services gmbh. He is the creator of Arjuna – a free, open-source Python based modern test automation framework. He is a contributing author and reviewer for various certification bodies including Artificial Intelligence United, Selenium United, ISTQB and CMAP. His software testing experience includes using LLMs for test design and reviews, building test automation frameworks in Python and Java, web security, white box testing and web performance testing. His research work focuses on object oriented design patterns as applied to test automation and extending them into general purpose models.

He has presented, published articles and educated thousands of testers in the said areas. His testing ideas and work are deeply influenced by his deep interest in poetry and spirituality.

What to Expect?

• A solid session on "The 5E Mental Model for LLM-Assisted Pluralistic Testing" by a Seasoned expert.
• Meeting like minded people and fellow testers in Berlin
• Informal discussions on latest testing tools & topics
• Talking about the challenges facing as a testers
• Chat over snacks with a cup of coffee/tea.

Who can attend? Software Testers who want to learn about the usage of AI in Testing and/or want to network with fellow testers in Berlin.

What should you bring? We need you, your attention, your mind and your note taking tool which could be a notebook, an i-pad, your phone, laptop anything.

This is an in-person meetup and completely free to attend including Snacks and Beverages.

About The Test Tribe: The Test Tribe is the World’s Largest Software Testing Community turned EdTech Startup. Started in 2018 with a mission to give Testing Craft the glory it deserves while we co-create Smarter, prouder, and confident Testers.

We take pride in solving upskilling and growth for global Testing professionals through our unique offerings like Expert Courses, Membership, Cohorts, Offline Mixers, online Community spaces, and a lot of global Events.

Our offerings enable Software Testers globally to collaborate, learn, and grow together. With around 270+ Software Testing Events like Conferences, Hackathons, Meetups, Webinars, etc., and with other Community initiatives, we have reached a global footprint of over 120K+ Testers from 130+ Countries. We intend to provide life-altering growth to every single Testing professional on the planet through community and technology.

Join thousands of other Testers in the community - Discord Community

By RSVPing this event, you agree to have read our Terms and Conditions and the Privacy Policy and also agree to be contacted by us and BrowserStack, with whom we are collaborating for this event.

External registration required at nyhackr.org.

Long-time meetup member and repeat NYR speaker Bryan Lewis returns for a talk about LLMs.

After the talk we will randomly select two attendees (both in-person and virtual) to receive free tickets to The New York R Conference taking place May 16-17.

Thank you to NYU for hosting us.

Everybody attending must RSVP through the registration form at nyhackr.org. There is a charge for in-person and virtual tickets are free. Space is extremely limited and in-person registration closes at 2 PM the day of the talk.

About the Talk: Oh no, not another talk on *that* topic. No fear: We will discuss (experimental) ways to think of data like time-series that fit in to the LLM zeitgeist from a training/set up perspective only. Along the way we'll advertise some criminally under-utilized R packages.

About Bryan: A mathematician well-known to open-source software communities, Bryan was the chief data scientist for Revolution Analytics and the SciDB database project. He has worked with Intel, Microsoft, DARPA, and many others on projects in computational finance, genomics, and other fields. Bryan is a coauthor of the CRC Press textbook "A Computational Approach to Statistical Learning."

Bryan lives in Appalachia, teaches math at his local community college, and is a whitewater kayaker, amateur mycologist and forager.

The venue doors open at 5:30 PM America/New_York where we will continue enjoying pizza together (we encourage the virtual audience to have pizza as well). The talk, and livestream, begins at 6:00 PM America/New_York.

Remember, register at nyhackr.org.

Please join Charlottesville Data Science for RAGtime, an event all about one of the hottest topics in applied AI — retrieval-augmented generation (RAG)! We'll be gathering in person at the Center for Open Science, just off the Downtown Mall. This event will be a double-feature:

• Tyler Hutcherson, senior applied AI engineer at Redis, will present the talk RAGs to Riches: Extracting Gems from Your Data with LLMs
• Scott Stults, co-founder and relevance engineer at OpenSource Connections, will present the talk Measuring and Improving the R in RAG

How to find us

The Center for Open Science is located in the Downtown Business Center, which is connected to the Omni Hotel on the Downtown Mall. If you're driving, you can park in the Omni Hotel parking garage and the Center for Open Science will validate parking. Please proceed to the lobby and follow the signs to the Center for Open Science office in Suite 500. If you’re facing the front desk, proceed past the front desk to the left, pass the ballrooms on your right, and proceed through to double doors to the business center. If you have any issues, feel free to ask for directions to the Center for Open Science at the front desk in the lobby.

About RAGs to Riches: Extracting Gems from Your Data with LLMs

LLMs are making a huge surge in the ecosystem, but how can we put them to work with private, domain-specific data? The goal of this session is to cut through the noise/hype of Generative AI and learn a core technique — Retrieval Augmented Generation (RAG). RAG is used to combine insights from data with LLMs in order to automate search and question-answering through the vehicle of conversational AI.

Whether it’s building a customer support chatbot or an internal knowledge discovery tool, RAG is a common technique employed to ground LLMs in factual data (mitigating hallucinations). This session will explore the technical underpinnings of information retrieval, foundational models, production RAG system architecture, and common scaling challenges.

About Measuring and Improving the R in RAG

The quality of text generated by a RAG system is limited by the quality of the text chunks it uses for context. The textbook way to measure the quality of these chunks is for a human expert to give each pair a judgement. Of course, this is expensive, time-consuming, and impossible in practice for any sizable corpus.

An attractive alternative is to use an LLM to learn from the experts and generate these judgements as-needed. From there we can tune our retrieval and ultimately improve the quality of our generated responses.

This talk will cover how OpenSource Connections is currently doing this for a client, as well as what our plans are for future development.

Advances in LLM technology and the semantic layer have made AI-powered data analytics easy. Nothing special. Par for the course.

Wait, you haven't seen yet? Don't worry, we'll show you. But I gotta warn you, it's pretty boring stuff. You just ask for whatever data you want, and then the computer gets it for you. Yes, seriously!

So what is still impressive in October 2023? Well, good old fashioned human ingenuity and improvisational skill. Computers may have gotten pretty good at crunching the numbers, but you still can't replace good old fashioned meat and bone when it comes time to present those numbers to the big boss.

In this session, Izzy Miller and Matt David put that to the test with a live game of Dashboard Karaoke— with an AI twist. Random audience members take turns using Hex's Magic AI to generate entire analytical reports on datasets of their choosing. Then, our handpicked data practitioners have to improvise a compelling presentation of the results on the spot, explaining the intricacies and trends of data they've never seen. And of course, there will be plenty of time for audience questions ;)

Speakers: Izzy Miller, Developer Advocate, Hex; Matt David, Product Marketing Lead, Hex

Register for Coalesce at https://coalesce.getdbt.com

Zoom Link

https://voxel51.com/computer-vision-events/ai-ml-data-science-meetup-sept-7/

Monitoring Large Language Models (LLMs) in Production

Just like with all machine learning models, once you put an LLM in production you’ll probably want to keep an eye on how it’s performing. Observing key language metrics about user interaction and responses can help you craft better prompt templates and guardrails for your applications. This talk will take a look at what you might want to be looking at once you deploy your LLMs.

Sage Elliott is a Technical Evangelist – Machine Learning & MLOps at WhyLabs. He enjoys breaking down the barrier to AI observability and talking to amazing people in the AI community.

Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos

The success of the Neural Radiance Fields (NeRFs) for modeling and free-view rendering static objects has inspired numerous attempts on dynamic scenes.Current techniques that utilize neural rendering for facilitating freeview videos (FVVs) are restricted to either offline rendering or are capable of processing only brief sequences with minimal motion. In this paper, we present a novel technique, Residual Radiance Field or ReRF, as a highly compact neural representation to achieve real-time FVV rendering on long-duration dynamic scenes.

Minye Wu – Postdoctoral researcher, KU Leuven

Egoschmema: A Dataset for Truly Long-Form Video Understanding

Introducing EgoSchema, a very long-form video question-answering dataset, and benchmark to evaluate long video understanding capabilities of modern vision and language systems. Derived from Ego4D, EgoSchema consists of over 5000 human curated multiple choice question answer pairs, spanning over 250 hours of real video data, covering a very broad range of natural human activity and behavior.

Karttikeya is a PhD student in Computer Science at the Department of Electrical Engineering & Computer Sciences (EECS) at University of California, Berkeley advised by Prof. Jitendra Malik. Earlier, he held a visiting researcher position at Meta AI where he collaborated with Dr. Christoph Feichtenhofer and team.

Zoom Link

https://voxel51.com/computer-vision-events/ai-ml-data-science-meetup-sept-7/

Monitoring Large Language Models (LLMs) in Production Just like with all machine learning models, once you put an LLM in production you’ll probably want to keep an eye on how it’s performing. Observing key language metrics about user interaction and responses can help you craft better prompt templates and guardrails for your applications. This talk will take a look at what you might want to be looking at once you deploy your LLMs.

Sage Elliott is a Technical Evangelist – Machine Learning & MLOps at WhyLabs. He enjoys breaking down the barrier to AI observability and talking to amazing people in the AI community.

Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos

The success of the Neural Radiance Fields (NeRFs) for modeling and free-view rendering static objects has inspired numerous attempts on dynamic scenes.Current techniques that utilize neural rendering for facilitating freeview videos (FVVs) are restricted to either offline rendering or are capable of processing only brief sequences with minimal motion. In this paper, we present a novel technique, Residual Radiance Field or ReRF, as a highly compact neural representation to achieve real-time FVV rendering on long-duration dynamic scenes.

Minye Wu – Postdoctoral researcher, KU Leuven

Egoschmema: A Dataset for Truly Long-Form Video Understanding

Introducing EgoSchema, a very long-form video question-answering dataset, and benchmark to evaluate long video understanding capabilities of modern vision and language systems. Derived from Ego4D, EgoSchema consists of over 5000 human curated multiple choice question answer pairs, spanning over 250 hours of real video data, covering a very broad range of natural human activity and behavior.

Karttikeya is a PhD student in Computer Science at the Department of Electrical Engineering & Computer Sciences (EECS) at University of California, Berkeley advised by Prof. Jitendra Malik. Earlier, he held a visiting researcher position at Meta AI where he collaborated with Dr. Christoph Feichtenhofer and team.

Zoom Link

https://voxel51.com/computer-vision-events/ai-ml-data-science-meetup-sept-7/

Monitoring Large Language Models (LLMs) in Production

Just like with all machine learning models, once you put an LLM in production you’ll probably want to keep an eye on how it’s performing. Observing key language metrics about user interaction and responses can help you craft better prompt templates and guardrails for your applications. This talk will take a look at what you might want to be looking at once you deploy your LLMs.

Sage Elliott is a Technical Evangelist – Machine Learning & MLOps at WhyLabs. He enjoys breaking down the barrier to AI observability and talking to amazing people in the AI community.

Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos

The success of the Neural Radiance Fields (NeRFs) for modeling and free-view rendering static objects has inspired numerous attempts on dynamic scenes.Current techniques that utilize neural rendering for facilitating freeview videos (FVVs) are restricted to either offline rendering or are capable of processing only brief sequences with minimal motion. In this paper, we present a novel technique, Residual Radiance Field or ReRF, as a highly compact neural representation to achieve real-time FVV rendering on long-duration dynamic scenes.

Minye Wu – Postdoctoral researcher, KU Leuven

Egoschmema: A Dataset for Truly Long-Form Video Understanding

Introducing EgoSchema, a very long-form video question-answering dataset, and benchmark to evaluate long video understanding capabilities of modern vision and language systems. Derived from Ego4D, EgoSchema consists of over 5000 human curated multiple choice question answer pairs, spanning over 250 hours of real video data, covering a very broad range of natural human activity and behavior.

Karttikeya is a PhD student in Computer Science at the Department of Electrical Engineering & Computer Sciences (EECS) at University of California, Berkeley advised by Prof. Jitendra Malik. Earlier, he held a visiting researcher position at Meta AI where he collaborated with Dr. Christoph Feichtenhofer and team.

Zoom Link

https://voxel51.com/computer-vision-events/ai-ml-data-science-meetup-sept-7/

Monitoring Large Language Models (LLMs) in Production Just like with all machine learning models, once you put an LLM in production you’ll probably want to keep an eye on how it’s performing. Observing key language metrics about user interaction and responses can help you craft better prompt templates and guardrails for your applications. This talk will take a look at what you might want to be looking at once you deploy your LLMs.

Sage Elliott is a Technical Evangelist – Machine Learning & MLOps at WhyLabs. He enjoys breaking down the barrier to AI observability and talking to amazing people in the AI community.

Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos

The success of the Neural Radiance Fields (NeRFs) for modeling and free-view rendering static objects has inspired numerous attempts on dynamic scenes.Current techniques that utilize neural rendering for facilitating freeview videos (FVVs) are restricted to either offline rendering or are capable of processing only brief sequences with minimal motion. In this paper, we present a novel technique, Residual Radiance Field or ReRF, as a highly compact neural representation to achieve real-time FVV rendering on long-duration dynamic scenes.

Minye Wu – Postdoctoral researcher, KU Leuven

Egoschmema: A Dataset for Truly Long-Form Video Understanding

Introducing EgoSchema, a very long-form video question-answering dataset, and benchmark to evaluate long video understanding capabilities of modern vision and language systems. Derived from Ego4D, EgoSchema consists of over 5000 human curated multiple choice question answer pairs, spanning over 250 hours of real video data, covering a very broad range of natural human activity and behavior.

Karttikeya is a PhD student in Computer Science at the Department of Electrical Engineering & Computer Sciences (EECS) at University of California, Berkeley advised by Prof. Jitendra Malik. Earlier, he held a visiting researcher position at Meta AI where he collaborated with Dr. Christoph Feichtenhofer and team.