BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Huntsville AI - ECPv6.8.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Huntsville AI
X-ORIGINAL-URL:https://hsv.ai
X-WR-CALDESC:Events for Huntsville AI
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20250309T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20251102T070000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20251001T180000
DTEND;TZID=America/Chicago:20251001T193000
DTSTAMP:20260405T123848
CREATED:20250929T120933Z
LAST-MODIFIED:20250929T120933Z
UID:2030-1759341600-1759347000@hsv.ai
SUMMARY:AI Workloads with Runpod
DESCRIPTION:I have just completed moving nearly all of transcribe.hsv.ai off of an AWS stack and over to a Runpod backend with the web ui hosted with DigitalOcean. The cost of AWS had been incrementally increasing over the years\, and we’ll take a look at what the residual hosting costs were when I shut it down. \nThis session will cover the types of serverless hosting (along with cost) provided by Runpod and discuss both the asynchronous and streaming versions of hosting. \nDepending on who is available at the session (I’m no expert!) – we will also talk about securing workloads that are running on non-traditional hosts. \nSo far\, the transition from AWS Fargate / Lambda has been super easy since I was using Docker images for both and the signature of the handling function is similar. \nFeedback Request: \nAlso – I could use your feedback on how to best communicate sessions that are open to the community versus sessions that we do in support of other organizations. Those are often open if people want to attend but not always. The best idea I have so far is to put “Supporting – ” before the event name. Scroll down to the Upcoming Schedule to see what this looks like.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks & Other Resources: \n\nServerless Documentation – https://docs.runpod.io/serverless/overview\n\nDetails: \n\nDate – 10/01/2025\nTime – 6:00 – 7:30 pm\nLocation – HudsonAlpha\nAddress – 601 Genome Way Northwest\, Huntsville\, AL 35806\nZoom – https://us02web.zoom.us/j/86596678663?pwd=59DMLkfpF1jfWz9x9drUdwLRO6uTcZ.1
URL:https://hsv.ai/event/ai-workloads-with-runpod/
LOCATION:HudsonAlpha\, 601 Genome Way Northwest\, Huntsville\, AL\, 35806
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/09/AI-Workloads-with-Runpod.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250917T180000
DTEND;TZID=America/Chicago:20250917T193000
DTSTAMP:20260405T123848
CREATED:20250906T124200Z
LAST-MODIFIED:20250906T124200Z
UID:2023-1758132000-1758137400@hsv.ai
SUMMARY:Lightning Talks
DESCRIPTION:We’ll have several of our folks give short talks about what they are working on or learning.
URL:https://hsv.ai/event/lightning-talks/
LOCATION:HudsonAlpha\, 601 Genome Way Northwest\, Huntsville\, AL\, 35806
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/09/Lightning-Talks.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250910T180000
DTEND;TZID=America/Chicago:20250910T193000
DTSTAMP:20260405T123848
CREATED:20250906T123102Z
LAST-MODIFIED:20250906T123102Z
UID:2020-1757527200-1757532600@hsv.ai
SUMMARY:Virtual Paper Review: Occupational Implications of Generative AI
DESCRIPTION:Join us virtually this Wednesday at 6 pm to continue our monthly Paper Review series! We will walk through a recent paper from Microsoft titled “Working with AI: Measuring the Occupational Implications of Generative AI”. This paper uses Microsoft’s unique position to analyze 200\,000 anonymized conversations with Microsoft Bing Copilot (now Microsoft Copilot) from U.S. users in 2024. \nThe basic premise of the paper is to evaluate how much Generative AI use overlaps with different occupations. \nMore specifically\, we will look at: \n\nDual Role Analysis: User Goals vs. AI Actions\nThe paper distinguishes between the tasks users want AI to help with and what the AI actually does\, enabling a nuanced view of augmentation versus automation.\nAI Applicability Score Framework\nBy integrating coverage\, success\, and scope metrics into an applicability score\, the study provides a quantitative\, occupation-level measure of AI relevance that aligns well with theoretical models.\nSocioeconomic Insights & Cautions on Impact Interpretation\nThe correlation with predicted models\, modest wage/education effects\, and the historical perspective on economic consequences underscore both the promise and the uncertainty of AI’s real-world occupational effects.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks: \n\nPaper – https://arxiv.org/pdf/2507.07935\n\nDetails: \n\nDate – 9/10/2025\nTime – 6-7:30pm\nLocation – VIRTUAL\nZoom –https://us02web.zoom.us/j/81918891827?pwd=fLpDXskTscvo37Mva45G90yKMhiLx1.1
URL:https://hsv.ai/event/virtual-paper-review-occupational-implications-of-generative-ai/
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/09/Occupational-Implications.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250903T180000
DTEND;TZID=America/Chicago:20250903T193000
DTSTAMP:20260405T123848
CREATED:20250901T224933Z
LAST-MODIFIED:20250901T224933Z
UID:2017-1756922400-1756927800@hsv.ai
SUMMARY:Midjourney - Beginner to Expert
DESCRIPTION:Join us this week to learn how to get the most of out Midjourney! David Showalter will be leading this session\, drawing on his experience with more than 75\,000 prompts. David has used Midjourney for personal creativity and exploration\, concept art for work projects and presentations\, and a few finished images for work. \nThis session will be a live demo covering the journey from getting started as a beginner to expert level tips for image and video creation: \n\nSignup and Costs\nGeneral prompt structure\nOverview of settings and commands\nPersonalization and mood boards\nEditing and Retexturing\nVideo\nAuto-prompt generation using other AI\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks & Other Resources: \n\nMidjourney – https://www.midjourney.com/home\nDocumentation and Guides – https://docs.midjourney.com/hc/en-us/categories/32013335627533-Documentation\nMidjourney TV – https://www.midjourney.tv/\nv7 SREF Catalog – https://www.playbook.com/s/cqdesigns/new-v7-sref-mining\n\nDetails: \n\nDate – 9/03/2025\nTime – 6:00 – 7:30 pm\nLocation – HudsonAlpha\nAddress – 601 Genome Way Northwest\, Huntsville\, AL 35806\nZoom – https://us02web.zoom.us/j/88395736080?pwd=yIVwcn6SfY0eBh4bEf9K2vzzvM648g.1
URL:https://hsv.ai/event/midjourney-beginner-to-expert/
LOCATION:HudsonAlpha\, 601 Genome Way Northwest\, Huntsville\, AL\, 35806
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/09/Midjourney-Prompting.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250820T180000
DTEND;TZID=America/Chicago:20250820T193000
DTSTAMP:20260405T123848
CREATED:20250818T194542Z
LAST-MODIFIED:20250818T194542Z
UID:2011-1755712800-1755718200@hsv.ai
SUMMARY:Group Project Roundup
DESCRIPTION:This week we are back at HudsonAlpha to talk about group projects. There are a few projects that we’ve worked in the past that I’ll bring up again to evaluate new possibilities due to advances in LLMs. \nThere are some other projects that folks in the community have been talking about\, so we’ll see if we can get a few people to present some ideas for those as well. We can also take a look to see if there are any running competitions that we might be interested in. \nWith the time left\, we’ll cover my recent experience with moving the transcription service from AWS Fargate\, over to AWS Lambda\, and then to Runpod.io. Also – as you can tell from the session schedule toward the bottom of the email\, we need to come up with some additional topics to cover.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks & Other Resources: \n\nBug Analysis project (a.k.a NLP before LLMs) – https://github.com/HSV-AI/bug-analysis\nProduct Recommendation – https://github.com/HSV-AI/product-recommendation\nHackathon Starter Kit – https://github.com/HSV-AI/hackathon-starterkit\n\nDetails: \n\nDate – 8/20/2025\nTime – 6:00 – 7:30 pm\nLocation – HudsonAlpha\nAddress – 601 Genome Way Northwest\, Huntsville\, AL 35806\nZoom – https://us02web.zoom.us/j/89675917660?pwd=EjfRXSrby7JbaR2GKwR6x0wBgrLufN.1
URL:https://hsv.ai/event/group-project-roundup/
LOCATION:HudsonAlpha\, 601 Genome Way Northwest\, Huntsville\, AL\, 35806
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/08/Group-Projects.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250813T180000
DTEND;TZID=America/Chicago:20250813T193000
DTSTAMP:20260405T123848
CREATED:20250515T000558Z
LAST-MODIFIED:20250809T031523Z
UID:1956-1755108000-1755113400@hsv.ai
SUMMARY:Virtual Paper Review - Agentic Memory for Autonomous Debugging
DESCRIPTION:Join us virtually this Wednesday at 6 pm to continue our monthly Paper Review series! We will examine SWE-Exp\, a study that equips code-repair agents with an “experience bank”\, a persistent memory that turns isolated fixes into reusable knowledge. \nAs usual we will split up the review into two segments. In the first half we will cover foundations for understanding the paper content and in the second we will cover the paper content in detail. \nFoundations\n\nWhy long-horizon bug fixes outgrow any context window\nHow agent trajectories can be converted into memories\nStorage choices for experience banks: vector DBs\, pruning\, and versioning\n\nPaper walkthrough & live prototype\n\nInstructor–Assistant roles and where memory is injected during MCTS search\nLive demo: spin up a minimal SWE-Exp prototype\, index two sample fixes\, and watch the agent retrieve and apply them in real time\nOpen questions: memory freshness\, cross-repo generalization\, and maintenance workflows\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks: \n\nPaper – https://arxiv.org/pdf/2507.23361\n\nDetails: \n\nDate – 8/13/2025\nTime – 6-7:30pm\nLocation – VIRTUAL\nZoom –https://us02web.zoom.us/j/88233490506?pwd=NwH4IuTbyVF7b4InCq7BRD3GNH7QP8.1
URL:https://hsv.ai/event/agentic-memory/
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250806T150000
DTEND;TZID=America/Chicago:20250806T170000
DTSTAMP:20260405T123848
CREATED:20250515T000954Z
LAST-MODIFIED:20250803T135556Z
UID:1958-1754492400-1754499600@hsv.ai
SUMMARY:SMD Field Trip
DESCRIPTION:This week we are taking a field trip to the Space & Missile Defense Symposium! Some of us will walk the exhibit hall floor on Tuesday and early Wednesday to compile a list of companies that have AI related projects on display. Then we’ll do a group walkthrough starting at 3pm on Wednesday to visit their booths and ask them to talk to us about their offerings\n \nAlso new this year – based on the SMD Symposium website\, the free admission to the exhibit space also includes the technical papers. These are worth your time if you can manage to take a few days off of work\, or are already at the conference. Some of the presenters are part of our Huntsville AI community\, so please show your support! You’ll find a link to the agenda below.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks & Other Resources: \n\nSMD Symposium Registration – https://smd.ud.net/register\nTech Track Agenda – https://smdsymposium.org/wp-content/uploads/2025/07/2025-Tech-Track-Agenda-v02.pdf\nVenue & Parking – https://smdsymposium.org/venue/\n\nDetails: \n\nDate – 8/06/2025\nTime – 3:00 – 5:00 pm\nLocation – Von Braun Center South Hall\nAddress – Monroe Street\, Huntsville\, AL 35801
URL:https://hsv.ai/event/smd-field-trip/
LOCATION:Von Braun Center\, 700 Monroe St SW\, Huntsville\, AL\, 35801\, United States
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/05/SMD-Symposium.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250723T180000
DTEND;TZID=America/Chicago:20250723T193000
DTSTAMP:20260405T123848
CREATED:20250515T002054Z
LAST-MODIFIED:20250721T020701Z
UID:1963-1753293600-1753299000@hsv.ai
SUMMARY:Replit AI Agent
DESCRIPTION:This week we’ll have Jack Francis as our guest speaker! He will be talking about Replit’s AI Agent for creating applications.  \n“This session demonstrates how to turn an idea into a functional application in minutes using Replit’s AI Agent. We’ll demystify the mechanics behind this powerful AI coding assistant\, tour the Replit platform\, and then build a complete application from scratch—all driven by simple prompts. You’ll learn how to leverage the Agent for rapid prototyping to get immediate feedback on your ideas. We will cover practical strategies for integrating this tool into your workflow\, whether you’re a seasoned developer looking to accelerate your process or a complete beginner eager to bring your creations to life.”\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks & Other Resources: \n\nReplit AI – https://replit.com/ai\n\nDetails: \n\nDate – 7/23/2025\nTime – 6:00 – 7:30 pm\nLocation – HudsonAlpha\nAddress – 601 Genome Way Northwest\, Huntsville\, AL 35806\nZoom – https://us02web.zoom.us/j/87872699213?pwd=1uu2hoca7RGaMTQO3NaIcp2YEqH3kI.1
URL:https://hsv.ai/event/replit-ai-agent/
LOCATION:HudsonAlpha\, 601 Genome Way Northwest\, Huntsville\, AL\, 35806
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/05/Replit-AI-Agent-.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250716T180000
DTEND;TZID=America/Chicago:20250716T193000
DTSTAMP:20260405T123848
CREATED:20250515T000330Z
LAST-MODIFIED:20250714T164604Z
UID:1954-1752688800-1752694200@hsv.ai
SUMMARY:Virtual Paper Review – Unifying Embeddings: From Words to Pixels
DESCRIPTION:Join us virtually this Wednesday as we crack open the magic behind modern multimodal embeddings and why they’re not just “text embeddings with pictures pasted on.” \nPart I – Foundations\n\n\nModality alignment 101 – How contrastive pre-training pulls text\, images\, and video frames into one joint space. \n\n\nVector anatomy – Why pixel patches\, temporal frame sequences\, and word tokens all reduce to the same dot-product math. \n\n\nEvaluation metrics – What “recall\,” “precision\,” and “rankability” really mean once your queries aren’t just strings. \n\n\nPart II – Deep Dive\nWe’ll explore two recent papers as our testbed for these concepts: \n\nJinaEmbed V4 – A single-path backbone unifying images\, video\, text\, and code.\nOn the Rankability of Visual Embeddings – Recovering numeric “more vs. less” axes with only two labeled examples.\n\nWe’ll finish by surveying how to turn these insights into a two-stage reranking pipeline from dense k-NN recall to lightweight LoRA heads or simple linear probes for precision uplift. \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks: \n\nJinaEmbed V4 (PDF): https://arxiv.org/abs/2506.18902\nRankability: https://arxiv.org/abs/2507.03683\n\nDetails: \n\nDate – 7/16/2025\nTime – 6-7:30pm\nLocation – VIRTUAL\nZoom –https://us02web.zoom.us/j/85067618698?pwd=lnLbLGFfcKMzjnSplzF9GdkyG9FOJU.1
URL:https://hsv.ai/event/unifying-embeddings/
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/05/Unifying-Embeddings-From-Words-to-Pixels.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250707T173000
DTEND;TZID=America/Chicago:20250707T193000
DTSTAMP:20260405T123848
CREATED:20250515T001829Z
LAST-MODIFIED:20250701T121224Z
UID:1961-1751909400-1751916600@hsv.ai
SUMMARY:Social Night!
DESCRIPTION:Join us for our summer social! This time we’ll be inside at the private room in Yellowhammer Brewing. There is good pizza available from Earth and Stone Pizza. We’ll also have part of the patio to ourselves if you miss the Alabama heat. The private room was only available for Monday\, so hopefully that doesn’t throw anyone off. We’ll be back on our normal Wednesday schedule after this. \nIf you have been looking for an easy time to get involved and meet others in the group – THIS IS IT! – I always have trouble keeping up with all of the conversations and connections that happen\, so please be sure to say hi to someone you don’t know. \nThis officially starts at 5:30pm\, but I’ll be there as soon as I can get out of the office – which is hopefully 5pm7
URL:https://hsv.ai/event/social-night/
LOCATION:Yellowhammer Brewing\, 2600 Clinton Ave W\, Huntsville\, AL\, 35805\, United States
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2022/05/220316-Social.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250625T180000
DTEND;TZID=America/Chicago:20250625T193000
DTSTAMP:20260405T123848
CREATED:20250512T032341Z
LAST-MODIFIED:20250621T032559Z
UID:1946-1750874400-1750879800@hsv.ai
SUMMARY:NVIDIA AI Certification Exams
DESCRIPTION:This week we’ll have Tom Plunkett as our guest speaker! His talk will describe how to study for NVIDIA’s AI certification exams. Specifically\, the NVIDIA-Certified Associate: Generative AI and LLMs\, Multimodal Generative AI\, and AI Infrastructure and Operations. You’ll find a link to these below. \nFrom NVIDIA: “Whether you’re a seasoned professional or just starting your journey in the industry\, certification is a valuable way to advance your career. Certifications serve as tangible evidence of your expertise\, proficiency\, and commitment to continuous learning.”\nBio: Thomas Plunkett recently passed seven AI certification exams: 3 NVIDIA exams\, 3 Oracle exams\, and 1 vendor-neutral exam. He is a consultant for Oracle\, where he focuses on AI and other emerging technologies.  He is a published author on AI\, Big Data\, Blockchain\, and other technologies.  He has taught  graduate-level computer science courses for Virginia Tech and Harrisburg University.  He is a member of the patent bar and has filed patents on AI inventions for Xerox’s Palo Alto Research Center\, Oracle\, and other organizations.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks & Other Resources: \n\nGenerative AI LLMs –\nhttps://www.nvidia.com/en-us/learn/certification/generative-ai-llm-associate/\nMultimodal Generative AI – https://www.nvidia.com/en-us/learn/certification/generative-ai-multimodal-associate/\nAI Infrastructure and Operations – https://www.nvidia.com/en-us/learn/certification/ai-infrastructure-operations-associate/\n\nDetails: \n\nDate – 6/25/2025\nTime – 6:00 – 7:30 pm\nLocation – HudsonAlpha\nAddress – 601 Genome Way Northwest\, Huntsville\, AL 35806\nZoom – https://us02web.zoom.us/j/85498016523?pwd=rj34zsZaC44iB8xtlrmWYEvttAeL9n.1
URL:https://hsv.ai/event/nvidia-ai-certification-exams/
LOCATION:HudsonAlpha\, 601 Genome Way Northwest\, Huntsville\, AL\, 35806
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/05/NVIDIA-AI-certification-exams.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250618T180000
DTEND;TZID=America/Chicago:20250618T193000
DTSTAMP:20260405T123848
CREATED:20250514T235821Z
LAST-MODIFIED:20250612T175536Z
UID:1952-1750269600-1750275000@hsv.ai
SUMMARY:Virtual Paper Review – Zero Trust for AI Agents
DESCRIPTION:Join us virtually this Wednesday at 6pm to continue our monthly Paper Review series! This month\, we’re diving into the critical topic of identity management for autonomous AI systems by reviewing the recent paper\, “A Novel Zero-Trust Identity Framework for Agentic AI: Decentralized Authentication and Fine-Grained Access Control.” \nAs AI agents become more autonomous\, traditional IAM solutions are proving insufficient. This session will explore a new architectural paradigm that fuses two powerful identity models\, workload identity and decentralized identity\, to create a robust\, verifiable\, and secure foundation for agent operations. \nOur discussion will follow a two-part format. In the first half\, we will cover the foundational concepts necessary to understand the paper’s contributions: \n\nWorkload Identity: The core principles of identifying software services using SPIFFE/SPIRE.\nDecentralized Identity: An introduction to Decentralized Identifiers (DIDs) and Verifiable Credentials (VCs) for portable\, logical identity.\nBridging Technologies: The role of OAuth 2.0 Token Exchange (RFC 8693) for delegation and Open Policy Agent (OPA) for fine-grained authorization.\n\nThe second half will be a deep dive into the paper itself\, analyzing its proposed framework and innovations: \n\nThe layered architecture for unifying workload and logical agent identities.\nDetailed review of the authentication and authorization flows\, particularly for human-to-agent delegation.\nStrategies for managing short-lived credentials and keys in dynamic environments.\nImplications for securing agents in complex\, non-Kubernetes deployments (e.g.\, Docker Compose\, systemd).\n\n\nThis session is ideal for security architects\, AI/ML engineers\, and practitioners interested in the next generation of secure infrastructure for artificial intelligence. \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks: \n\nMain Paper: A Novel Zero-Trust Identity Framework for Agentic AI: https://arxiv.org/abs/2505.19301\nSPIFFE: https://spiffe.io/\nW3C Decentralized Identifiers (DIDs): https://www.w3.org/TR/did-core/\nW3C Verifiable Credentials (VCs): https://www.w3.org/TR/vc-data-model/\nOAuth 2.0 Token Exchange: https://www.rfc-editor.org/rfc/rfc8693\n\nDetails: \n\nDate – 6/18/2025\nTime – 6-7:30pm\nLocation – VIRTUAL\nZoom –https://us02web.zoom.us/j/86865023053?pwd=CNErK8uoiWo0m49hiWVb0WIZC14tJs.1
URL:https://hsv.ai/event/zero-trust-for-ai-agents/
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/05/Zero-Trust-for-AI-Agents.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250611T180000
DTEND;TZID=America/Chicago:20250611T193000
DTSTAMP:20260405T123848
CREATED:20250512T032233Z
LAST-MODIFIED:20250609T165009Z
UID:1944-1749664800-1749670200@hsv.ai
SUMMARY:Vibe Coding Live!
DESCRIPTION:This week we’ll have several people in the room with various tools attempting to “Vibe Code” our transcription service. We’ll pass screen share around to see each person’s approach and do some evaluation of the output. This should be interesting to compare with our existing transcription service that was written entirely by hand. \nHere are some constraints to make sure it matches as much as possible to the tech stack: \n\nAWS for all hosting\nDocker Containers for everything\nFaster-Whisper for the speech to text model\nFlask back end\nReact front end\nStripe for payment processing\nLanguages are Python and Typescript\nBonus for CI/CD workflow in Github and Terraform deployment\n\nBasic requirements \n\nUser can upload a video or audio file\, and set their email address\nUser can pay\, which starts the transcription process\nApp updates the transcription live as it is being processed\nUser receives an email with the transcription when complete\nApp removes all containers used for processing as well as the file that was uploaded (a.k.a don’t keep any data)\nUser does not have to create an account or log in\n\nWe’ll see how that goes in a live setting. If anything\, it will be interesting to see how far some of these models have come.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks & Other Resources: \n\nTranscription Service – https://transcribe.hsv.ai/\n\nDetails: \n\nDate – 6/11/2025\nTime – 6:00 – 7:30 pm\nLocation – HudsonAlpha\nAddress – 601 Genome Way Northwest\, Huntsville\, AL 35806\nZoom – https://us02web.zoom.us/j/86524869531?pwd=XbB0GdpeC6lmmPv4yD4zSQsUbC5axo.1
URL:https://hsv.ai/event/vibe-code-live/
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/05/Vibe-Code-Live.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250528T180000
DTEND;TZID=America/Chicago:20250528T193000
DTSTAMP:20260405T123848
CREATED:20250527T040814Z
LAST-MODIFIED:20250527T040814Z
UID:1970-1748455200-1748460600@hsv.ai
SUMMARY:Cline - The Collaborative Coding Agent
DESCRIPTION:This week we’ll walk through an example of using the Cline plugin for Visual Studio Code connected through OpenRouter. It’s an agent that can help you as you work\, directly from Visual Studio Code – doing much more than just generating code. \nAfter working directly with the agent for development\, we’ll take a look at setting up Cline Rules and Workflows. Then we will cover Task Management and Context Management. \nThe session will also include an overview of OpenRouter\, which can be used to select from most of the popular models without having to manage accounts with Anthropic\, OpenAI\, Google\, etc.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks & Other Resources: \n\nCline Website – https://cline.bot/\nCline Docs: https://docs.cline.bot/getting-started/for-new-coders\nGitHub Repo: https://github.com/cline/cline\n\nDetails: \n\nDate – 5/28/2025\nTime – 6:00 – 7:30 pm\nLocation – HudsonAlpha\nAddress – 601 Genome Way Northwest\, Huntsville\, AL 35806\nZoom – https://us02web.zoom.us/j/89834209692?pwd=W5PHh5RBd6ODY61Bsag79Ia7qQM0II.1
URL:https://hsv.ai/event/cline-openrouter/
LOCATION:HudsonAlpha\, 601 Genome Way Northwest\, Huntsville\, AL\, 35806
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/05/Cline-OpenRouter.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250515T153000
DTEND;TZID=America/Chicago:20250515T163000
DTSTAMP:20260405T123848
CREATED:20250419T140339Z
LAST-MODIFIED:20250419T140339Z
UID:1921-1747323000-1747326600@hsv.ai
SUMMARY:AI 101 hosted by AI Huntsville
DESCRIPTION:This “Introduction to AI” workshop by Deloitte provides a clear and basic overview of artificial intelligence for professionals. This session explains key AI concepts like machine learning\, natural language processing\, and computer vision\, using real-world examples from industries such as healthcare\, finance\, and transportation. \nParticipants will learn about the ethical issues and challenges of AI\, and how Deloitte uses AI to help businesses. Through discussions and practical demos\, attendees will gain a basic understanding of AI and how it can be relevant to their work\, helping them to explore AI opportunities in their organizations. \nRegister Here – https://forms.gle/pcWMmJBQR1J8NTtu9
URL:https://hsv.ai/event/ai-101-hosted-by-ai-huntsville/
LOCATION:Huntsville/Madison County Chamber\, 225 Church St NW\, Huntsville\, AL\, 35801\, United States
ATTACH;FMTTYPE=image/jpeg:https://hsv.ai/wp-content/uploads/2025/04/051525-AI-101.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250514T180000
DTEND;TZID=America/Chicago:20250514T193000
DTSTAMP:20260405T123848
CREATED:20250512T032043Z
LAST-MODIFIED:20250512T032043Z
UID:1941-1747245600-1747251000@hsv.ai
SUMMARY:Virtual Paper Review - Google Prompt Engineering Guide (v7)
DESCRIPTION:This month we are looking at Google’s recent iteration on their Prompt Engineering guide as a vehicle to discuss the latest advancements in the field of prompting models. We will cover the core material of the paper and discuss the sort of the things that are left out of the current guidance\, and potential resources to deepen understanding of different prompt engineering components. \nThe focus of the discussion will prioritize programmatic control first\, however many concepts will also be useful for general users a well. \nTopics for the session will primarily focus on: \n\nCore components of a prompt\nKey Prompting Parameters (Temperature\, Top-p\, Top-k\, etc.)\nPrompting Techniques (Few-Shot\, Chain of Thought\, Self-Consistency\, Tree of Thoughts\, ReAct\, etc.)\nPrompting Modes (Structured Outputs\, Vision\, Tool Use\, Reasoning )\nPrompt Evaluation & Automating Prompt Engineering (DSPy\, etc)\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nDetails: \n\nDate – 5/14/2025\nTime – 6-7:30pm\nLocation – VIRTUAL\nZoom –https://us02web.zoom.us/j/89604082647?pwd=uIe4vVTBRuiOO11pPndvogZgSJDa2R.1
URL:https://hsv.ai/event/virtual-paper-review-google-prompt-engineering-guide-v7/
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/05/Google-Prompt-Engineering.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250507T180000
DTEND;TZID=America/Chicago:20250507T193000
DTSTAMP:20260405T123848
CREATED:20250505T022100Z
LAST-MODIFIED:20250505T022100Z
UID:1926-1746640800-1746646200@hsv.ai
SUMMARY:OpenHands Agents for Developing Code
DESCRIPTION:This week we’ll dive into our latest presentation\, OpenHands Agents for Developing Code\, where we’ll explore the full CodeAgent lifecycle—from architecture and history to hands-on workflows and GitHub Actions integration. \nThe frameworks and tools covered include: \n\nCodeAgent Architecture & Microservices\nCode Generation Agent\nTest Generation Agent\nCode Review Agent\nCustom Workflows via .openhands.yaml\nGitHub Actions Integration for automatic fixes\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks & Other Resources: \n\nOpenHands Docs: https://docs.all-hands.dev/\nGitHub Repo: https://github.com/All-Hands-AI/OpenHands\nPresentation Markdown: https://github.com/HSV-AI/presentations/blob/master/2025/250507_OpenHands.md\nGitHub Actions Example: https://github.com/HSV-AI/presentations/blob/master/.github/workflows/openhands-fix.yml\n\nDetails: \n\nDate – 5/7/2025\nTime – 6:00 – 7:30 pm\nLocation – HudsonAlpha\nAddress – 601 Genome Way Northwest\, Huntsville\, AL 35806\nZoom – https://us02web.zoom.us/j/89917715591?pwd=bbia3HSZgblSV4DbqfoJJhdp7PQbeE.1
URL:https://hsv.ai/event/openhands-agents-for-developing-code/
LOCATION:HudsonAlpha\, 601 Genome Way Northwest\, Huntsville\, AL\, 35806
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/05/Coding-Agent.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250425T100000
DTEND;TZID=America/Chicago:20250425T120000
DTSTAMP:20260405T123848
CREATED:20250407T042435Z
LAST-MODIFIED:20250419T135613Z
UID:1908-1745575200-1745582400@hsv.ai
SUMMARY:Supporting American Planning Association Lunch & Learn
DESCRIPTION:The State of AI: Innovations\, Applications and Impacts in Planning \nFor the last 2 years\, AI has been one of the trends recommended in APA’s Trend Report for planners to act and prepare for. The report notes that while the advancements in Gen AI have the potential to greatly enhance public services\, there are concerns about cybersecurity and privacy\, as well as the environmental impact of the computing power required to support supercomputers. In this event\, the status and extent of AI technology especially in North Alabama will be explored. The impact of AI on our local economy and communities will also be discussed. \nDate & Time: April 25\, 2025\, 10:00 am – 12:00 pm \nSpeakers: \n\n Langley\n\nFounder of Huntsville AI and Chief Technical Officer of CohesionForce\, Inc. \nDr. Vineetha Menon \nDirector of the Big Data Analytics lab in the University of Alabama in Huntsville
URL:https://hsv.ai/event/supporting-american-planning-association-lunch-learn/
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/04/American-Planning-Association.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250423T180000
DTEND;TZID=America/Chicago:20250423T193000
DTSTAMP:20260405T123848
CREATED:20250222T213946Z
LAST-MODIFIED:20250409T011758Z
UID:1875-1745431200-1745436600@hsv.ai
SUMMARY:Virtual Paper Review - Diffusion Transformers & Flow Matching (Wan 2.1 Technical Report)
DESCRIPTION:Join us virtually this Wednesday at 6pm to continue our monthly Paper Review series! This month we are looking at the concepts behind recent advancements in video generation. We will focus on Diffusion Transformers and Flow Matching techniques\, culminating in a review of the recent Wan 2.1 technical report. \nThis virtual session will follow our usual format. In the first half\, we will cover foundational concepts essential for understanding the paper and related techniques: \n\nVariational Autoencoders (VAEs)\nWhat is a latent space?\nCore principles of Diffusion Models\nDiffusion Transformers (DiTs) architecture\nRectified Flow / Flow Matching concepts\n\nThe second half will then review the Wan paper\, analyzing its components and contributions in the context of the concepts discussed: \n\nThe overall model architecture and innovations\nImplementation and role of the Spatio-Temporal VAE\nDataset construction and usage\nDetails of the Captioning Pipeline for text-to-video/image\nVideo Editing with Wan (VACE)\nExperiments in Video to Audio generation\n\n \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks: \n\nhttps://arxiv.org/abs/2503.20314 : Wan Technical Report\nhttps://arxiv.org/abs/2212.09748 : Diffusion Transformers\nhttps://arxiv.org/pdf/2210.02747 : Flow Matching for Generative Models\nhttps://arxiv.org/abs/1312.6114 : Variational Autoencoders\n\nDetails: \n\nDate – 4/23/2025\nTime – 6-7:30pm\nLocation – VIRTUAL\nZoom –https://us02web.zoom.us/j/87940486028?pwd=xfuet8FvR7hc63na4v3XyYEl2rWoAP.1
URL:https://hsv.ai/event/paper-review-wan/
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/02/Paper-Review-WAN.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250416T180000
DTEND;TZID=America/Chicago:20250416T193000
DTSTAMP:20260405T123848
CREATED:20250222T214152Z
LAST-MODIFIED:20250415T013155Z
UID:1877-1744826400-1744831800@hsv.ai
SUMMARY:Agent Frameworks
DESCRIPTION:This week we will continue our series on AI Agents\, based on the HuggingFace tutorials. We will also jump into some of the protocols such as MCP and A2A. \nThe frameworks covered include: \n\nsmolagents\nLlamaIndex\nLangGraph\n\nAI Huntsville Taskforce \nThe date for the Introduction to AI session has changed to May 15. The intent is to raise awareness of AI in Huntsville\, so it aligns closely with our mission here. I’ll forward more info to this distro next week. \nAmerican Planning Association \nI’m presenting an overview of AI and its application to city planning\, with some help from Josh. I believe there is room for additional seats if you are interested in attending. Just reply and let me know. \nMailing List Progress \nGood news and bad news. This list is now large enough to surpass the free tier of MailChimp! You can guess the bad news 🙂\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks & Other Events: \n\nHuggingFace Tutorial – https://huggingface.co/learn/agents-course/en/unit2/introduction\nMCP – https://github.com/modelcontextprotocol\nA2A – https://github.com/google/A2A\n\nDetails: \n\nDate – 4/16/2025\nTime – 6-7:30pm\nLocation – HudsonAlpha\nAddress –  601 Genome Way Northwest\, Huntsville\, AL 35806\nZoom –https://us02web.zoom.us/j/82537267316?pwd=whsvIokcMixZUhZzPczfU50Xaxo1cw.1
URL:https://hsv.ai/event/agent-frameworks/
LOCATION:HudsonAlpha\, 601 Genome Way Northwest\, Huntsville\, AL\, 35806
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/02/Agent-Frameworks.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250402T180000
DTEND;TZID=America/Chicago:20250402T193000
DTSTAMP:20260405T123848
CREATED:20250317T043747Z
LAST-MODIFIED:20250331T022539Z
UID:1897-1743616800-1743622200@hsv.ai
SUMMARY:AI for Video Generation
DESCRIPTION:It’s been a while since we covered Video Generation models\, actually February of last year. I dropped a link below from the email for last year that covers the list of models that we covered. I believe that Sora is the only one currently still in use. \nThis week we will focus on the Wan2.1 model that is getting a lot of warranted publicity. The following paper review next week will dive deeper into the Wan paper (linked below). We’ll also do a survey of publicly available tools for generating video. There’s a list of these tools below in the links. \nWe’ll end with a live demo of the Wan2.1 model running in hosted Rupod instance. It’s been a lot of fun this weekend getting this all set up and working. My definition of “fun” is different than most though 🙂 There are a few topics for later that I’ve run across in the process: \n\nRunpod for hosting AI workflows\nComfyUI\n\nAI Huntsville Taskforce \nThe taskforce is hosting a session on April 10 to cover an Introduction to AI\, presented by Deloitte. The intent is to raise awareness of AI in Huntsville\, so it aligns closely with our mission here. I’ll forward more info to this distro next week. \nAmerican Planning Association \nI’m presenting an overview of AI and its application to city planning\, with some help from Josh. I believe there is room for additional seats if you are interested in attending. Just reply and let me know.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks & Other Events: \n\n2024 Video Breakthroughs – https://mailchi.mp/842e92b8296d/240221-ai-video-breakthrough\nWan Paper – https://arxiv.org/abs/2503.20314\nhttps://hailuoai.video/\nhttps://app.klingai.com/\nhttps://app.runwayml.com/\nhttps://www.genmo.ai/play\nhttps://wan.video/wanxiang/videoCreation\n\nDetails: \n\nDate – 4/02/2025\nTime – 6-7:30pm\nLocation – HudsonAlpha\nAddress –  601 Genome Way Northwest\, Huntsville\, AL 35806\nZoom –https://us02web.zoom.us/j/88543069893?pwd=kfcxGybJ2QVOxeUObPa5AGp0MbNxPb.1
URL:https://hsv.ai/event/video-generation/
LOCATION:HudsonAlpha\, 601 Genome Way Northwest\, Huntsville\, AL\, 35806
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/03/Video-Generation.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250319T180000
DTEND;TZID=America/Chicago:20250319T193000
DTSTAMP:20260405T123848
CREATED:20250222T161602Z
LAST-MODIFIED:20250222T161602Z
UID:1866-1742407200-1742412600@hsv.ai
SUMMARY:Huntsville AI Social
DESCRIPTION:
URL:https://hsv.ai/event/huntsville-ai-social/
LOCATION:Stovehouse\, 3414 Governors Dr SW\, Huntsville\, AL\, 35805
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2024/10/Social.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250312T180000
DTEND;TZID=America/Chicago:20250312T193000
DTSTAMP:20260405T123848
CREATED:20250222T161916Z
LAST-MODIFIED:20250309T145736Z
UID:1868-1741802400-1741807800@hsv.ai
SUMMARY:Paper Review - Claude 3.7 Sonnet
DESCRIPTION:Join us virtually this Wednesday at 6pm to continue our monthly Paper Review series! This week will be a detailed review of the system card paper for Anthropic’s Claude 3.7 Sonnet. Claude 3.7 is a new hybrid reasoning model designed to enhance transparency in AI decision-making processes. \nThis virtual session will examine the technical aspects of Claude 3.7\, including its Extended Thinking Mode\, training methodologies using publicly available datasets\, human feedback\, and Constitutional AI principles. The discussion will explore the model’s performance across various tasks\, such as software engineering\, cybersecurity\, and autonomous agents\, highlighting strengths and addressing limitations. We will also look at the coding agent “Claude Code” released alongside 3.7 sonnet. Researchers\, practitioners\, and enthusiasts interested in recent advancements in AI reasoning\, code agents\, and transparency will benefit from the insights provided. \nThis event aims to offer a clear overview of Claude 3.7’s contributions\, implications for responsible AI development\, and directions for future research and experimentation.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks: \n\nClaude 3.7 System Card : https://assets.anthropic.com/m/785e231869ea8b3b/original/claude-3-7-sonnet-system-card.pdf\nAnthropic Responsible Scaling Policy : https://www.anthropic.com/news/anthropics-responsible-scaling-policy\nClaude Code : https://ai-claude.net/code/\nConstitutional Classifiers : https://www.anthropic.com/research/constitutional-classifiers\nCybench (Cyber Benchmark) : https://arxiv.org/abs/2408.08926\nMCP Servers : https://modelcontextprotocol.io/introduction\n\nDetails: \n\nDate – 3/12/2025\nTime – 6-7:30pm\nLocation – VIRTUAL\nZoom –https://us02web.zoom.us/j/83232316418?pwd=EnACbNMcgsoWnOVa1XKGjId19FtjuG.1
URL:https://hsv.ai/event/virtual-paper-review/
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/02/Paper-Series-Claude-3.7.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250305T180000
DTEND;TZID=America/Chicago:20250305T193000
DTSTAMP:20260405T123848
CREATED:20250222T161147Z
LAST-MODIFIED:20250303T052124Z
UID:1864-1741197600-1741203000@hsv.ai
SUMMARY:Agentic AI
DESCRIPTION:This week we will go through the AI Agents course offered by HuggingFace. The course consists of 4 units\, and the first two have been released so far. This is a self-paced course with a lot of good material and hands-on examples. There’s also a certificate when you finish if you are interested in that. \nSeveral of us have made it through portions of the course so far\, so the intent is to compare notes and give everyone an overview and tips on what parts to jump into. \nHudsonAlpha Tech Challenge \nWe’ll also review our experience with the HudsonAlpha Tech Challenge from this weekend. It was a lot of fun\, even though we didn’t place. I’m looking forward to see how this challenge progresses next year. There’s a link to our submission below. \nPaper Review Series \nThe next installment of the paper review series is planned for 3/12 to cover the Claude 3.7 and GPT 4.5 drops and dive into the system card papers for both of them. Lots of interesting topics around mechanistic interpretability (mainly related to Sparse Autoencoders) in the anthropic card.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks & Other Events: \n\n2025 HATCH Submission – https://devpost.com/software/deep-learning-microscopy-for-dummies\n2025 HATCH GitHub Repo – https://github.com/HSV-AI/hatch-2025\nHuggingFace AI Agents Course – https://huggingface.co/agents-course\n\nDetails: \n\nDate – 3/05/2025\nTime – 6-7:30pm\nLocation – HudsonAlpha\nAddress –  601 Genome Way Northwest\, Huntsville\, AL 35806\nZoom –https://us02web.zoom.us/j/85363006279?pwd=l27YI4usuybfL0bbaTQU7eYnIeXYLx.1
URL:https://hsv.ai/event/agentic-ai/
LOCATION:HudsonAlpha\, 601 Genome Way Northwest\, Huntsville\, AL\, 35806
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/02/Agentic-AI.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250301T000000
DTEND;TZID=America/Chicago:20250301T235959
DTSTAMP:20260405T123848
CREATED:20241216T013024Z
LAST-MODIFIED:20250222T160525Z
UID:1820-1740787200-1740873599@hsv.ai
SUMMARY:HudsonAlpha Tech Challenge
DESCRIPTION:
URL:https://hsv.ai/event/hudsonalpha-tech-challenge-2/
LOCATION:HudsonAlpha\, 601 Genome Way Northwest\, Huntsville\, AL\, 35806
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2024/12/hatch-1.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250219T180000
DTEND;TZID=America/Chicago:20250219T190000
DTSTAMP:20260405T123848
CREATED:20241216T012737Z
LAST-MODIFIED:20250219T211911Z
UID:1818-1739988000-1739991600@hsv.ai
SUMMARY:VIRTUAL ONLY - Deep Research Overview
DESCRIPTION:This week we will have Jack Francis provide an overview of Deep Research: \nWe will explore Google’s Gemini Deep Research\, OpenAI’s Deep Research\, and Open-Source Deep Research implementations. Deep Research is an LLM agent that uses reasoning to synthesize large amounts of online information and complete multi-step research tasks for you. We’ll dive into the mechanics of Deep Research\, discussing how these agents function and some of the benchmarks used to evaluate the models. \nWe will discuss the strengths and limitations of each approach\, provide examples for comparison\, and talk through Deep Research use cases\, such as market research! Deep Research is useful tool to add to your toolbox for market research\, decision analysis\, or any other task that requires significant amounts of “Googling” today. The goal of the presentation is to introduce Deep Research and provide an overview of current tools\, so that you can use it effectively for your own research tasks. \nPaper Review Series \nThanks to Josh for the great kickoff to the paper review series last week! You can find the recording\, links to papers\, and transcript here: \nhttps://hsv.ai/2025/02/12/ai-reasoning-reinforcement-learning-fundamental-papers-history/ \nIf you have a paper that you would like to see us review\, please let me know. We’ll post the date for March as soon as it’s finalized.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks & Other Events: \n\n2025 HATCH – https://hudsonalpha.org/techchallenge/\n2025 BSides – https://nac-issa.org/events/bsides/\n\nDetails: \n\nDate – 2/19/2025\nTime – 6-7:30pm\nLocation – VIRTUAL\nZoom –https://us02web.zoom.us/j/84476860693?pwd=D2UGBsfpb5ZKoJEGMiFZaroV9aEb28.1
URL:https://hsv.ai/event/deep-research-overview/
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2024/12/Deep-Research-Overview.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250212T180000
DTEND;TZID=America/Chicago:20250212T193000
DTSTAMP:20260405T123848
CREATED:20250209T145141Z
LAST-MODIFIED:20250209T145141Z
UID:1851-1739383200-1739388600@hsv.ai
SUMMARY:Virtual Paper Review - Reasoning
DESCRIPTION:Join us virtually this Wednesday at 6pm to kick off our monthly Paper Review series! We will be holding these sessions every 4 weeks on Zoom. The first one will be led by Josh Phillips: \nThis month we will be exploring the current evolution in AI reasoning models. We will start with a short review of the history of combining reinforcement learning with tree search for reasoning (AlphaGo/MuZero). Then we will cover the real start of the reasoning race with the chain-of-thought innovations highlighted by “Let’s Verify Step by Step.” And finally of course\, we’ll cover the most important insights from DeepSeek’s three recent papers that build on all of this prior foundation: \n\nDeepSeek-V3 – a highly efficient MoE-based approach (671B parameters\, only 37B active per token) powered by advanced CUDA/NCCL optimizations and low-precision (FP8) training\, making huge models tractable on constrained hardware.\nDeepSeek-R1 – the first open demonstration that an LLM can learn complex reasoning purely through RL rewards\, without any annotated examples (r1-zero)\nDeepSeekMath– which introduces GRPO (an alternative to PPO that simplifies training and removes the need for a separate value network).\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks: \n\nMastering Atari\, Go\, Chess and Shogi by Planning with a Learned Model (2019) :  https://arxiv.org/pdf/1911.08265\nLets Verify Step by Step (2023) : https://arxiv.org/abs/2305.20050\nDeepseek V3 Technical Report (2024): https://github.com/deepseek-ai/DeepSeek-V3/blob/main/DeepSeek_V3.pdf\nDeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning  (2025) https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf\nDeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models (2025): https://arxiv.org/pdf/2402.03300\n(Bonus) “We’ve got R1 at home” : https://unsloth.ai/blog/r1-reasoning\n\nDetails: \n\nDate – 2/12/2025\nTime – 6-7:30pm\nLocation – VIRTUAL\nZoom –https://us02web.zoom.us/j/86964741971?pwd=SXmv4xfY8M6TZbEOIXyYfLu5Y3FAil.1
URL:https://hsv.ai/event/virtual-paper-review-reasoning/
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2025/02/Paper-Series-Reasoning.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250205T180000
DTEND;TZID=America/Chicago:20250205T190000
DTSTAMP:20260405T123848
CREATED:20241216T012527Z
LAST-MODIFIED:20250203T052119Z
UID:1816-1738778400-1738782000@hsv.ai
SUMMARY:DeepSeek-R1 and Other Topics
DESCRIPTION:This week we will be back at HudsonAlpha in their classroom. This is a new room for us\, which I believe is on the opposite side from the large conference room we have been using. \nHudsonAlpha Tech Challenge \nWe should have Tyler Clark stop by for a few minutes to discuss some changes to HATCH and how we can get involved. Otherwise\, I can cover based on what I know. The main change from the past challenges is that this will be a one day challenge occurring on Saturday\, March 1st. \nDeepSeek-R1 \nWe’ll be discussing DeepSeek-R1\, which has been unavoidable in most conversations over the last week – and rightly so. We will cover the architecture\, the approach used for training\, as well as the distilled models based on the Llama and Qwen architectures. We have several folks in the group that already have DeepSeek-R1 running locally\, so if you need help getting it running or would like to connect directly please let me know. \nFor part of the discussion\, you may want to refer back to the Mixture of Experts talk that Josh Phillips led during one of our meetups in October 2023. You can find the link below. \nPaper Review Series \nThis year we are going to start a review series to look at published papers in-depth. These will be a monthly\, virtual-only meetup to start with but may shift based on interest. The first paper review will be on Wednesday\, February 12\, led by Josh Phillips to cover the DeepSeek-R1 paper (also linked below). \nSBIR/STTR Topics? \nThe next round of SBIR/STTR Topics are supposed to drop on Wednesday. Given the issues with funding being stopped for NSF grants and other changes driven by the new administration\, I don’t know if we will see new topics drop or not. \nAI Symposium \nWe’ll take a few minutes to talk about how the AI Symposium sessions went.  The organizers are interested in feedback for the quality of the sessions and any suggested changes for next year.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nLinks & Other Events: \n\nDeepSeek-R1 on GitHub – https://github.com/deepseek-ai/DeepSeek-R1?tab=readme-ov-file\nDeepSeek-R1 Paper – https://arxiv.org/pdf/2501.12948\nMixture of Experts Discussion – https://hsv.ai/2023/10/25/mixture-of-experts-harnessing-the-hidden-architecture-of-gpt4/\nIntroduction to AI Slides – https://github.com/HSV-AI/presentations/blob/master/2025/250116_Introduction_to_AI_LearningQuest.pdf\nUses of AI Slides – https://github.com/HSV-AI/presentations/blob/master/2025/250123_Uses_of_AI_LearningQuest.pdf?raw=true\n2025 HATCH – https://hudsonalpha.org/techchallenge/\n2025 BSides – https://nac-issa.org/events/bsides/\n\nDetails: \n\nDate – 2/05/2025\nTime – 6-7:30pm\nLocation – HudsonAlpha\nAddress –  601 Genome Way Northwest\, Huntsville\, AL 35806\nZoom –https://us02web.zoom.us/j/82283427713?pwd=PCuFpoeIIYQGhAWDain4YK4FoRbETU.1
URL:https://hsv.ai/event/deepseek-r1/
LOCATION:HudsonAlpha\, 601 Genome Way Northwest\, Huntsville\, AL\, 35806
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2024/12/DeepSeek-R1.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250130T130000
DTEND;TZID=America/Chicago:20250130T143000
DTSTAMP:20260405T123848
CREATED:20241216T011949Z
LAST-MODIFIED:20241216T011949Z
UID:1810-1738242000-1738247400@hsv.ai
SUMMARY:Intro to AI @ LearningQuest
DESCRIPTION:
URL:https://hsv.ai/event/intro-to-ai-learningquest-3/
LOCATION:Huntsville Madison County Library\, 915 Monroe St\, Huntsville\, AL\, 35801\, United States
ATTACH;FMTTYPE=image/png:https://hsv.ai/wp-content/uploads/2024/12/LearningQuest.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250128T000000
DTEND;TZID=America/Chicago:20250130T235959
DTSTAMP:20260405T123848
CREATED:20241216T012353Z
LAST-MODIFIED:20241216T012353Z
UID:1812-1738022400-1738281599@hsv.ai
SUMMARY:2025 AI Symposium: Automation Vs HITL
DESCRIPTION:
URL:https://hsv.ai/event/2025-ai-symposium-automation-vs-hitl/
LOCATION:Space & Rocket Center\, 1 Tranquility Base\, Huntsville\, AL\, 35805\, United States
ATTACH;FMTTYPE=image/jpeg:https://hsv.ai/wp-content/uploads/2024/12/SRC-AI-Symposium.jpg
END:VEVENT
END:VCALENDAR