World Congress 2026 Europe Jul 9, 2026 Session details

Hacking AI at the Edge of the Indian Ocean

Anastasiia Stefanska , James Cha-Earley

Aboard a research vessel in the Indian Ocean, engineers bypassed satellite bandwidth limits with a far-edge AI pipeline. Discover how they processed terabytes of 8K video completely offline.

Pause
Mute Enter Fullscreen
#1 about 2 min

Volunteering on a scientific mission in the Indian Ocean

Partnering with a non-profit organization democratizes ocean knowledge by collecting and processing massive amounts of scientific data.

#2 about 4 min

Navigating the Indian Ocean on the OceanXplorer vessel

Tracking wave heights illustrates the physical challenges of conducting a continuous production hackathon aboard a swaying ship.

#3 about 4 min

Unmanned scanners, submarines, and deep ocean sensors

Various hardware systems collect geospatial sweeps, video footage, and water salinity data to digitize the ocean floor.

#4 about 5 min

Running local video inference without high speed internet

Applying a Florence 2 model locally through a Streamlit app solves the challenge of analyzing massive footage without internet bandwidth.

#5 about 7 min

Uploading thumbnail frames to automatic cloud processing pipelines

Uploading compressed thumbnails into cloud stages allows Claude Sonnet to parse images without manual format conversions.

#6 about 4 min

Querying unstructured expedition data with conversational artificial intelligence

Semantic views and AI agents translate natural language queries into actionable insights across complex scientific mission records.

#7 about 3 min

Navigating elevated security risks in the Malacca Strait

Strict security protocols guard against piracy threats while transiting dangerous maritime regions like the Malacca Strait.

#8 about 3 min

Averaging biodiversity detections across marine video frames

Averaging colony counts across multiple image frames overcomes underwater lighting limitations and improves longitudinal biodiversity tracking.

Matching moments

5:51 min

Deploying machine learning models at the edge for conservation

Sohan Maheshwar · LIVE

1:09 min

Deploying algorithms and AI models to edge production

Irina Terekhova Irina Terekhova · WWC Europe 2026

3:37 min

Discovering hardware prize uses for localized artificial intelligence

Chris Heilmann +5 · LIVE

2:26 min

Cost and latency pressures pushing AI to the edge

Moe Sani Moe Sani · WWC Europe 2026

2:00 min

Reviewing key architectural decisions for federated AI computing

Jeremy Murray Jeremy Murray · WWC Europe 2026

2:42 min

Dissecting artificial intelligence layers from compute to applications

Christian Nagel Christian Nagel +3 · WWC Europe 2026

Upcoming sessions on this topic

Open session

World Congress 2026 North America

AI Agents are Only as Smart as their Context: Building a Real-Time Context Engine at Intuit

Bharat Patel

Lead Software Engineer at Intuit

Bharat Patel
Open session

World Congress 2026 North America

You Can’t Re-Run Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan
Open session

World Congress 2026 North America

Ship 10x Faster: AI-Powered Development with Claude Code and MCP Tools

Viktoria Semaan

Principal Technical Evangelist at Databricks

Viktoria Semaan
Open session

World Congress 2026 North America

Building Stuff with GenAI - The Open Minded Workshop beyond OpenAI

Andreas Erben

CTO for Applied AI and Metaverse at daenet

Andreas Erben
Open session

World Congress 2026 North America

Look What Java Can Do Now: Live-Coding a GenAI MCP Server with the JAQ Stack

Suren Konathala

Senior Engineering Leader, Marketing & AdTech, AI GTM & Digital Experience Platforms, Java x AI

Suren Konathala
Open session

World Congress 2026 North America

Making Science Larger, not just Faster

Yuval Dvir

Commercial Executive, SandboxAQ

Yuval Dvir