- prep festa, raccolta oggetti demo

PyVenice

Ci troviamo in #presenza giovedì 15 ottobre alle ore 19:30.

La scaletta prevede uno speech seguito da discussione.

E dopo\, per chi vuole\, resteremo in zona per \( 🍸 \| 🍺 \) e \( 🍕 \| 🍔 \)

📽 E se avete piacere di condividere idee, progetti, argomenti, o proporvi come prossimi speaker, lascio un form Google e la pagina Sessionize !

Rome AI, Machine Learning and Computer Vision Meetup

Time, Place and Location

Oct 15, 2026

Online. Register for the Zoom!

Testing AI Systems in Production: Data Quality, Drift, and Model Evaluation

AI systems can pass offline evaluation and still fail in production when real-world data changes, features become stale, labels or feedback signals are incomplete, or model behavior drifts away from expected outcomes. This talk shares practical patterns for testing and evaluating AI systems after deployment, including data quality checks, drift detection, online/offline metric comparison, model monitoring, and rollback analysis.

Using personalization and recommendation systems as examples, we will examine how teams can build evaluation workflows that catch quality issues before users do. Attendees will leave with a practical checklist for making AI-backed systems easier to evaluate, debug, and operate as data changes over time.

About the Speaker

Jayakumar Ramalingam is a Staff Software Engineer and Cloud Architect at SiriusXM with over 16 years of experience building cloud-native platforms, real-time data pipelines, resilient APIs, and AI/ML-enabled applications at production scale.

Where Should Your Model Live? A Framework for Tiering Computer Vision Deployments

Where should a computer vision model actually run - on-device, near the edge, or in the cloud? It's a decision that looks simple until requirements like latency, cost, connectivity, and update cadence start pulling in different directions, often revealing themselves only after deployment.

Drawing on hands-on experience developing and deploying CV models across Hailo, Nvidia, Qualcomm and AWS platforms, this talk introduces a practical framework for tiering computer vision deployments based on real project requirements and constraints. Discussion will include what changes at each tier - from development to deployment to monitoring and update strategy - with relevant industry examples.

Attendees will leave with a set of questions or a framework they can use to place their own CV projects into the right tier.

About the Speaker

Ajaykumaar Sivacoumare is an AI Software Engineer specializing in computer vision and edge AI, with production experience developing and deploying CV models across Nvidia, Hailo, Qualcomm and AWS-based platforms.

From 2D Slices to 3D Tumors: Lightweight Volumetric Detection Without Heavy 3D Networks

Slice-wise 2D detectors are fast and scalable, but they struggle to produce reliable 3D bounding boxes from volumetric medical data. This talk presents YOLO-PVC, a lightweight post-processing framework that consolidates slice-wise YOLO detections into coherent 3D bounding boxes using percentile-based geometric aggregation and a minimal MLP calibration module.

This talk demonstrates consistent improvements in volumetric IoU across three liver tumor categories i.e., HCC, CCA, and Mixed, without requiring dense 3D annotations or memory-intensive architectures. The talk covers the clinical motivation, the technical approach, and practical lessons from deploying computer vision on real hospital MRI data.

About the Speaker

Talha Waqas is a second-year PhD student at ESME Research Lab, Paris and LISSI, Université Paris-Est, working on computer vision applied to medical imaging, with a focus on tumor classification, detection, and segmentation in multi-phase liver MRI.

The Two-Loop Architecture for Voice AI

Building responsive voice AI requires balancing latency with intelligence. This talk introduces a practical architecture that separates real-time conversation from asynchronous reasoning, enabling richer interactions without slowing the user experience. The session covers reusable design patterns drawn from production-inspired conversational AI systems.

About the Speaker

Abhinav Tushar is an ML engineer and researcher specializing in Conversational AI and Speech Technology.

GRUSP

Il POuL propone la terza edizione dei corsi di programmazione per Android.

Tre giornate per avviarsi verso lo sviluppo di un'app, partendo da zero.

• Chiediamo ai partecipanti di leggere questa

lezioni con tutti i software e le configurazioni corrette.*

Il corso offre un'introduzione pratica allo sviluppo Android moderno.

Verranno affrontati i fondamenti del linguaggio Kotlin, per poi vedere i fondamenti di Android e alcuni suoi API,

Alla fine del corso sarà anche possibile partecipare ad un workshop dedicato alle tecniche di reverse engineering in

Per partecipare compila questo

La registrazione è

Il corso sarà tenuto completamente in italiano e sarà disponibile anche

nostro canale Telegram qualche minuto prima

Hacklab Cormano

Coding Bunker

Per Hacktoberfest, Coding Bunker cambia formato: niente evento basato solo su talk e slide, ma un Hack Day hands-on dedicato alla creazione di progetti con tecnologie open source, open-source AI e modelli open-weight.

Non serve arrivare con un progetto già pronto. Anzi: secondo le regole ufficiali dell'Hacktoberfest Hack Day, il lavoro sul progetto presentato deve iniziare durante l'evento.

Come funzionerà

Durante l'Hack Day:

• Formazione dei team: potrai partecipare con altre persone, trovare un team direttamente durante l'evento o lavorare sulla tua idea
• Ideazione: scegliete un problema concreto da affrontare e definite il progetto
• Build: avrete diverse ore per progettare, sviluppare, testare e migliorare la vostra soluzione
• Open Source AI: i progetti utilizzeranno tecnologie open source e/o modelli AI open-weight
• Mentoring e confronto: durante la giornata potrai confrontarti con gli altri partecipanti e condividere approcci, problemi e soluzioni
• Project submission: al termine dell'Hack Day i team presenteranno il proprio progetto attraverso la piattaforma ufficiale OrganizerHQ Challenges
• Demo e judging: chiuderemo la giornata mostrando ciò che è stato costruito e valutando i progetti partecipanti

Non cerchiamo necessariamente il progetto più complesso.

Hacktoberfest Challenges

Coding Bunker partecipa al formato ufficiale Hacktoberfest Hack Day di Major League Hacking.

I dettagli delle challenge e degli eventuali premi verranno comunicati ai partecipanti prima o durante l'Hack Day.

Chi può partecipare?

Non importa se sei:

• developer
• QA / Quality Engineer
• DevOps / Platform Engineer
• architect
• data o AI engineer
• designer
• contributor open source
• oppure semplicemente curioso di sperimentare

Non è necessario essere esperti di AI o contribuire abitualmente a progetti open source.

Porta il tuo laptop, la voglia di costruire e qualche idea.

Programma

Il programma dettagliato sarà pubblicato a breve.

9:00 Accredito e check-in

9:45 Presentazione delle challenge e delle regole

10:15 Hack time

16:30 Demo dei progetti e judging

17:30 Networking

Registrazione

Come previsto dalle linee guida ufficiali Hacktoberfest, registrazione e check-in dei partecipanti verranno gestiti tramite OrganizerHQ.

Cos'è Hacktoberfest?

Hacktoberfest è un'iniziativa internazionale dedicata alla crescita e alla collaborazione nell'ecosistema open source.

Il Coding Bunker Hack Day fa parte del formato Hacktoberfest Hack Day, una giornata in presenza dedicata alla realizzazione di progetti attraverso un approccio da mini-hackathon.

Coding Bunker

Coding Bunker è una community dedicata alla Software Engineering e alla condivisione di esperienze concrete tra professionisti.

Questa volta, però, invece di parlarne soltanto...

Link Telegram

https://t.me/codingbunker

Nota legale

Partecipando all'evento, l'utente autorizza gli organizzatori a effettuare riprese fotografiche e video e a utilizzare il materiale raccolto per finalità di comunicazione, promozione e documentazione delle attività legate a Coding Bunker, Hacktoberfest e alla community.

Milano Cybersecurity Meetup

Six amazing speakers will explore this transformation from four different perspectives: the ethical hacker, the enterprise, financial fraud, and the cybersecurity technology ecosystem.

Andrea Nadelle — Ethical Hacker, Bug Bounty Hunter & Red Team Leader, ex Hackerone

Stefano Sella, Fabrizio De Luca, Stefano Sali — Senior Security Architects, Broadcom

Another special guest speaker to be announced soon !!

Can defenders keep pace with machine-speed attacks?

The K!nd4SUS CTF Players Team of the University of Milan (UniMi) will introduce our speakers and guide the audience through the different sessions.

“Zero-Day Is Dead. Welcome to Zero-Minute”

Agenda

• Talk #1 — From Sword to Gun

For years, penetration testers and red teamers were the swordsmen of offensive security, warriors forged through knowledge, experience and years of close-combat practice. Commercial, open-source and custom-built tools were their weapons, extending their own capabilities and allowing expertise to become execution.

• Talk #2 — Are We Ready for AI Risk?

Artificial intelligence is rapidly moving from being a tool used by employees to becoming an active participant in the enterprise. What new risks emerge? From data exposure and cyber attacks to hallucinations, autonomy and accountability — who is responsible when the machine makes the wrong decision? And ultimately, how much control are we willing to give AI?

• Talk #3 — The Fraud Machine

Giovanni Bruner, NEXI — Head of Fraud COE

• Talk #4 — AI at the Cyber Frontier

AI is changing cybersecurity on both sides of the battlefield — attacker and defenders. The time from vulnerability discovery to exploitation is shrinking, while the growing volume of CVEs is making traditional vulnerability management increasingly difficult. AI can chain vulnerabilities into attack paths, turning individually low-risk weaknesses into critical cumulative threats, while analyzing open-source code and accelerating the development of exploits, malware and adaptive attacks. At the same time, AI does not face the same friction as a human attacker: it does not get tired, does not need to sleep and can operate at machine speed. As one of the organizations invited to test Mythos through Project Glasswing, Broadcom explores how frontier AI is changing attack and defense — and why organizations need to rethink vulnerability management, patching and cyber defense.

Registration

Free access (registration required)

Participation is subject to confirmation, as spots are limited.

Photos may be taken during the event and shared on social media. By attending, you consent to their use.

PyData Venice

We’ll meet #InPresence on Thursday, October 22 at 7:00 PM.

👥 We’ll have two interesting sessions, in English 🇬🇧:

🗣 Andrij David will show us how #MultiArmedBandits can reduce the cost of #ABTesting by balancing exploration and exploitation. Through #Python simulations, we’ll see when it makes sense to move beyond traditional A/B tests and when they remain the right choice.

And afterwards\, for those who want\, we’ll stay there for \( 🍸 \| 🍺 \) & \( 🍕 \| 🍔 \) and #networking until late ‼️

📽 And if you’d like to share ideas, projects, topics, or propose yourself as the next speaker, here’s the usual Google form or Sessionize

Rome AI, Machine Learning and Computer Vision Meetup

Date, Time and Location

Oct 22, 2026

Online. Register for the Zoom!

Multi-Agent Communication: A framework, diagnostic and mechanistic perspective

Multi-agent LLM systems are increasingly used for collaborative reasoning, debate, and consensus, yet their communication dynamics remain poorly understood. This talk presents a framework for studying multi-agent communication through diagnostic and mechanistic perspectives.

I will discuss CONSENSAGENT, which improves consensus by mitigating sycophancy, alongside our diagnostic work on communication patterns and failure modes in real-world multi-agent debates. I will then present ongoing work that moves toward a mechanistic understanding of how these interaction patterns arise internally, with the broader goal of making multi-agent systems more interpretable, reliable, and controllable.

About the Speaker

Priya Pitre I am an Ph.D student in the Computer Science Department at Virginia Tech (VT), co-advised by Dr. Xuan Wang and Dr. Naren Ramakrishnan.

Exposing and Improving Fine-Grained Visual Grounding Abilities of Lightweight Multimodal LLMs

Lightweight multimodal LLMs can localize whole objects effectively, yet often struggle when a query targets a small object part or fine-grained visual detail. This talk presents a reasoning-guided framework that teaches compact models to ground parts through an explicit coarse-to-fine process: first locating the parent object, then identifying the requested part.

A part-aware reinforcement-learning objective provides stage-wise rewards for object accuracy, part containment, and the consistency of the model’s self-critique. Using these techniques, a compact 4B-parameter model achieves state-of-the-art zero-shot part grounding while preserving its object-level performance.

These advances can be used to enable lightweight MLLMs to support detail-oriented tasks in biology and robotics.

About the Speaker

Kazi Mehrab I a CS PhD candidate at Virginia Tech, where I currently focus on multimodal LLMs and computer vision tasks, including visual perception, reasoning and grounding.

Understanding Visual Generative Models for Precise Control

Despite remarkable progress in image and video generation, translating user intent into precise and consistent visual outputs remains a challenge. This talk explores how understanding the representations within generative models can enable finer control over what they create.

It connects semantic image editing with compositional generation, examining how visual concepts can be isolated, manipulated, and combined while preserving their identity and surrounding content. Building on these insights, structured visual inputs provide a way to express complex intent through subject references, poses, and spatial layouts.

The discussion then extends from images to video, where representations must evolve to preserve scene continuity while accommodating motion and change. Together, these directions establish a unified perspective on how visual representations can support controllable editing, composition, and coherent generation across space and time.

About the Speaker

Yusuf Dalva is a Ph.D. candidate at Virginia Tech, advised by Pinar Yanardag and affiliated with the Sanghani Center for Artificial Intelligence and Data Analytics.

Eccoci giunti al momento dell'anno: il Linux Day, giornata dedicata alla sponsorizzazione e diffusione di informazioni riguardanti il software FOSS.

Per maggiori informazioni rimandiamo alla pagina dedicata sul nostro sito!

Vi aspettiamo!

Ritorna il Linux Day, ritorna la giornata del Linux e del Free Libre Open Source.

Progamma e dettagli a questo link.

Il Linux day quest’anno si svolgerà il 24 ottobre presso il FabLab Bergamo.

PNLUG

Da Confermare

LUGMan

Hacklab Cormano

Rome AI, Machine Learning and Computer Vision Meetup

Date, Time and Location

Oct 29, 2026

Online. Register for the Zoom!

We’ll walk through how modern agentic systems move beyond simple prompts—leveraging structured tools like dataset operations, embeddings, evaluation pipelines, and model execution to take real action. You’ll see how these agents can tag data, run inference, evaluate performance, and surface insights automatically, all within a unified workflow.

By combining natural language interfaces with programmable building blocks, teams can dramatically reduce manual effort, accelerate experimentation, and unlock faster decision-making across the ML lifecycle.

Whether you're building data-centric AI systems, managing large-scale vision datasets, or exploring agentic workflows for the first time, this session will give you a practical blueprint for getting started.

GRUSP

GRUSP

Rome AI, Machine Learning and Computer Vision Meetup

Date, Time and Location

Nov 05, 2026

Online. Register for the Zoom!

Talks will include:

U-Net Framework for Micro-Scale Surface Damage Segmentation in High-Resolution Soybean Seed Imagery

Accurate detection of surface-level seed damage is critical for soybean seed quality assurance, yet automated micro-scale damage detection in high-resolution imagery remains an open challenge due to extreme spatial variability in damage scale, severe class imbalance across damage types, and the computational demands of processing ultra-high resolution agricultural imagery at scale. This research addresses the semantic segmentation of fine-grained soybean seed surface defects, such as wrinkles, dark spots, and general surface damage, in 6048 × 4024 pixel images where target damages can be as small as 18 × 18 pixels, using an augmented dataset of 77,000 individual seed images.

To overcome the difficulties of micro-scale detection, spatial sparsity, and class confusion, we propose a two-stage training and dual model inference framework built on an optimized U-Net architecture with a ResNet34 encoder. In the first stage, a damage specialist model is trained using weighted loss functions and a class-balanced approach that prioritizes damage classes.

In the second stage, transfer learning is applied to initialize a healthy seed specialist model from Stage 1 weights, with rebalanced class weights and tile probabilities that identify healthy seeds. During inference, a confidence-gated damage filter suppresses low-confidence predictions, and healthy seed labels are assigned only when the specialist model's confidence exceeds that of the damage model.

The two specialist models achieve validation accuracies of 94% and 98.53%, respectively, and the combined inference system successfully detects and localizes all three damage categories across unseen test images under conditions of extreme spatial variability and class imbalance. Qualitative evaluation confirms close alignment of predicted boundaries with ground truth annotations across all damage types, including dark spots.

These results demonstrate that confidence-gated dual model inference can reduce class confusion in imbalanced micro-scale segmentation, advancing the feasibility of fine-grained automated seed quality inspection at the scale.

About the Speaker

Saurav Upadhyaya is an AI/ML researcher with a Master's degree in Computer Science, whose work spans agricultural AI, conversational systems, and public health, consistently translating advanced technology into tangible real-world impact.

From camera to drone: wildfire detection and integration at the edge

Wildfires are getting larger and more expensive every year. But caught early, a fire is a small job for a small team; caught late, nothing stops it. The cameras to catch them are already installed, so the work is not necessary more sensors but making the ones we have act.

This talk walks the whole chain: a small vision model running on the camera that flags smoke, an integration layer that scores the alert against terrain, weather and history to decide whether it matters, and a drone dispatched to confirm before anyone commits a crew. We will cover what has to run at the edge and why, how small the model can get before it stops seeing smoke, and what it takes to trust a detection nobody has looked at yet.

About the Speaker

Maxime Carriere is co-founder of Kernwerk in Berlin, where he works on compressing AI models to run on cheap embedded hardware.

5,000 Flights to Answer One Question: Can a Drone Sample as Well as a Human?

Environmental testing still begins with a person walking onto a site with a shovel. We built a system that turns a plain-language brief into a sampling campaign, flies it, and returns soil, water and vegetation samples with GPS, timestamps and chain of custody intact: 5,000 flights, roughly 9,000 miles and 570 flight hours over a 185-acre site in Roatan, much of it under canopy where GPS degrades and clearances are tight.

I will walk through the vision and planning stack, including multispectral and thermal canopy sensing, terrain and land-cover mapping, and the constraint solver that clears a route against airspace and battery budget before anything leaves the ground. Then the harder problem: evidentiary comparability.

A drone-collected result means nothing to a regulator unless it agrees with a hand-collected split under the same method, so I will show the dual-collection protocol we designed to test exactly that. I will close on why calibrated uncertainty and knowing when a model should refuse to answer matter more than raw accuracy once the output lands in a regulatory filing.

About the Speaker

Rohan Talwadia is co-founder and CTO of LabGPT, which automates environmental field sampling using drones and edge analysis, with results returned through ISO/IEC 17025-accredited partner laboratories.

Un sabato pomeriggio tutto speciale dedicato a migliorare la mappa di Angera in OpenStreetMap.

L'incontro è previsto dopo pranzo presso la biblioteca di Angera per una breve introduzione ad OSM e ai suoi concetti base, per una descrizione degli obiettivi della giornata, per configurare i terminali dei mappatori e poi dividerci in squadre per mappare! Al termine di una sessione di circa due / tre ore torneremo al punto di partenza e valuteremo la bontà del nostro lavoro con qualche numero molto concreto a proposito delle modifiche alla mappa.

Ai mappatori verrà richiesto di usare il proprio smartphone (possiamo fornire assistenza su molti dispositivi Android, un poco su quelli della mela) per trovare e correggere errori, aggiungere informazioni mancanti e aggiungere nuovi oggetti alla mappa. Gli verrà inoltre richiesto di crearsi un account, eventualmente con la nostra assistenza, sul sito di OSM in quanto premessa essenziale per poter contribuire.

Per maggiori informazioni riferitevi alla pagina dedicata del nostro sito.

OpenStreetMap è un solido progetto per la mappatura aperta e contributiva della Terra che può competere con ben più noti prodotti commerciali. Si basa, come per Wikipedia, sul lavoro di milioni di volontari che mappano individualmente oppure importano massivamente dati ottenuti dalle amministrazioni pubbliche. I dati così immessi sono liberamente accessibili, previo rispetto della licenza con cui vengono distribuiti.

Dedicheremo questo pomeriggio a contribuire ad un progetto con una comunità di utenti che è mondiale!

Rome AI, Machine Learning and Computer Vision Meetup

Time, Date and Location

Nov 11, 2026

Online. Register for the Zoom!

Agentic RAG: Beyond Retrieve-and-Generate

Retrieval-Augmented Generation (RAG) has become the default pattern for grounding large language models in external knowledge, but most implementations still follow a rigid retrieve-once, generate-once pipeline — one that struggles with multi-hop questions, ambiguous queries, and knowing when its own retrieved context is insufficient. This talk introduces Agentic RAG, where retrieval is treated as an action within an agent's reasoning loop rather than a fixed upstream step.

We'll examine query decomposition and routing for breaking complex questions into targeted sub-queries, self-reflective and corrective retrieval loops that let an agent judge and re-query its own results, and tool-orchestration patterns (via MCP) that let retrieval sit alongside other agent actions like database lookups and API calls. Using a live architecture — evolving a standard RAG chatbot into an agentic, MCP-connected system — we'll walk through what changes in design, and where these systems introduce new failure modes: grounding drift, latency and cost from repeated retrieval loops, and cases where a simpler RAG pipeline still wins.

Attendees will leave with a practical framework for deciding when the added complexity of agentic RAG is worth it, and a set of design patterns for building it correctly.

About the Speaker

Balaji Venkatasubramaniyar is a Technical Lead at Wisdom Infotech, leading a 15+ person engineering team delivering enterprise solutions. With 13+ years of experience in enterprise software and insurance technology, he specializes in agentic AI systems, RAG architectures, and vector databases.

GeoAI for the Physical World: Earth Observation, Foundation Models, and Urban Digital Twins

Earth observation provides a unique form of computer vision for understanding the physical world at city to continental scales. In this talk, I will show how satellite imagery, geospatial data, machine learning, and foundation-model representations can be combined to characterize urban environments and environmental conditions.

I will present UrbanScope Open, an open GeoAI digital-twin prototype integrating Earth observation with 3D buildings, vegetation, land-surface temperature, air quality, noise, population, and other urban data. I will also share lessons from my research using geospatial foundation-model embeddings for environmental prediction across Europe.

The talk will discuss how these approaches can contribute to increasingly multimodal AI systems capable of reasoning about real-world environments.

About the Speaker

Cesar Alvarez is a researcher at the University of Augsburg working at the intersection of GeoAI, Earth observation, remote sensing, and environmental intelligence. His research applies machine learning, computer vision, and geospatial foundation models to problems including urban environments, climate risk, air quality, and agriculture.

Can agents get curious?

Most AI agents are good at answering a question once we tell them exactly what to look for. The harder problem is building agents that can explore a complex dataset autonomously: generating hypotheses, deciding which analyses are worth running, allocating additional compute when evidence is ambiguous, and knowing when they have enough evidence to stop.

In this talk, I’ll show an architecture for autonomous research agents that combines structured knowledge, iterative tool use, and explicit evidence tracking to turn open-ended questions into a sequence of testable investigations. I’ll discuss practical lessons from building and evaluating these systems, including why more test-time compute does not automatically produce better research and how provenance and evaluation can make long-running agents more reliable.

I’ll close with a live example of an agent exploring a dataset, revising its hypotheses, and choosing what to investigate next.

About the Speaker

Srivatsa P is a member of technical staff at Sigma Computing, where he works on AI agents that reason over complex enterprise data. Previously, he worked on machine learning at Apple and conducted research at the MIT Media Lab; outside of traditional ML, he has also worked on mapping coral reefs through underwater imaging, which sparked an enduring interest in how intelligent systems make sense of messy real-world data.

The South Tyrol Free Software Conference, SFSCON, is one of Europe’s most established annual conferences on Free Software. SFSCON promotes the use of Free Software in digital infrastructures as a tool to achieve greater innovation and competitiveness. Here decision-makers and developers meet, learn and get inspired.

LUGMan

GRUSP

PyVenice

Ci troviamo in #presenza giovedì 19 novembre alle ore 19:00.

🗣 La scaletta non è ancora stata definita.

E dopo\, per chi vuole\, resteremo lì per \( 🍸 \| 🍺 \) e \( 🍕 \| 🍔 \)

📽 E se avete piacere di condividere idee, progetti, argomenti, o proporvi come prossimi speaker, lascio un form Google e la pagina Sessionize !

Rome AI, Machine Learning and Computer Vision Meetup

Date, Time and Location

Nov 19, 2026

Online. Register for the Zoom!

Robot learning data doesn't look like the data that trains most vision-language models. It's temporal, low-dimensional in the parts that matter most, embodiment-specific, and expensive to collect, and increasingly, it's shipped in Hugging Face's LeRobot format. But packaging robot data consistently isn't the same as being able to see it: episodes hide broken metadata, silently dropped sensor modalities, and mismatched schemas between robots that look identical on paper.

Starting from the core differences that make robot data hard (temporal structure, proprioception, action grounding, embodiment heterogeneity, data scarcity), we'll move into live debugging: a metadata bug that broke multiple dataset imports, sensor streams that vanish without an error, and two robots running an identical benchmark whose data is structurally incompatible. By the end, you'll know what to check before you trust a LeRobot dataset, and how to actually look inside one.

GRUSP

GRUSP