London AI, Machine Learning and Computer Vision Meetup

Oct 15, 2026
9:00 AM - 11:00 AM PST
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.

Oct 22, 2026
9:00 AM - 11:00 AM PST
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.

Oct 29, 2026
9:00 AM - 10:00 AM PST
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.

Nov 05, 2026
9:00 AM - 11:00 AM PST
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.