Open Source Summit Korea 2026: Full Schedule

11-12, August 2026
Seoul, South Korea
View More Details & Registration
Note: The schedule is subject to change.

The Sched app allows you to build your schedule but is not a substitute for your event registration. You must be registered for Open Source Summit Korea 2026 to participate in the sessions. If you have not registered but would like to join us, please go to the event registration page to purchase a registration.

This schedule is automatically displayed in Korea Standard Time (KST), UTC +9. To see the schedule in your preferred timezone, please select from the drop-down menu to the right.

09:00 KST

Keynote: Welcome + Opening Remarks - Jim Zemlin, CEO, The Linux Foundation

Tuesday August 11, 2026 09:00 - 09:25 KST

Grand Ballroom 2-3

Speakers

Jim Zemlin

CEO, The Linux Foundation

Jim Zemlin’s career spans three of the largest technology trends to rise over the last decade: mobile computing, cloud computing, and open source software. Today, as executive director of The Linux Foundation, he uses this experience to accelerate innovation in technology through... Read More →

Tuesday August 11, 2026 09:00 - 09:25 KST
Grand Ballroom 2-3

Keynote Sessions

09:30 KST

Keynote Sessions To Be Announced

Tuesday August 11, 2026 09:30 - 10:15 KST

Grand Ballroom 2-3

Tuesday August 11, 2026 09:30 - 10:15 KST
Grand Ballroom 2-3

Keynote Sessions

10:15 KST

Keynote: Priya Nagpurkar, Vice President, Hybrid Cloud and AI Platforms, IBM Research

Tuesday August 11, 2026 10:15 - 10:30 KST

Grand Ballroom 2-3

Speakers

Priya Nagpurkar

Vice President, Hybrid Cloud and AI Platform, IBM Research

Tuesday August 11, 2026 10:15 - 10:30 KST
Grand Ballroom 2-3

Keynote Sessions

11:00 KST

Squeezing Every Millisecond: A Practical Guide To Optimizing Time To First Token With OSS Muscle - Hrittik Roy, Platform Advocate

Tuesday August 11, 2026 11:00 - 11:30 KST

Grand Ballroom 2-3

Large language models are getting faster GPUs every year, yet users still notice the pause before the first word appears. That pause has a name: Time To First Token (TTFT). And in production LLM systems, shaving even a few hundred milliseconds from it can dramatically change how responsive an application feels.

This talk tells the story of where those milliseconds go.

We will walk through the lifecycle of a request in modern LLM serving systems and explore the practical techniques engineers use to reduce TTFT in real deployments. Using examples from open source stacks like vLLM, TensorRT-LLM, and Hugging Face TGI, we will examine four powerful optimization levers: KV cache strategies, speculative decoding, model quantization, and batching policies.

Instead of focusing only on theory, the session highlights the tradeoffs practitioners face. When does speculative decoding actually help? When does batching hurt latency? When does quantization reduce memory pressure enough to speed up the first token?

Attendees will leave with a practical playbook for diagnosing TTFT bottlenecks and choosing the right optimization strategy for their model, infrastructure, and workload.

Speakers

Hrittik Roy

vCluster, Platform Advocate

Hrittik is a Platform Advocate at Loft Labs and a CNCF Ambassador, with expertise in cloud native technologies and open source communities. He has contributed extensively to developer advocacy, technical writing, and community engagement. Hrittik has been a featured speaker at events... Read More →

Tuesday August 11, 2026 11:00 - 11:30 KST
Grand Ballroom 2-3

Open AI + Data

11:40 KST

Stop Trusting a Black Box: The Economic Case for Open, Sovereign AI - Vincent Caldeira, Red Hat

Tuesday August 11, 2026 11:40 - 12:10 KST

Grand Ballroom 2-3

As AI matures from a novelty into a strategic asset, 79% of organisations now prioritise sovereignty to mitigate vendor lock-in and secure critical data. Despite this, the market remains paralysed by a paradox: while open models have achieved performance parity with proprietary systems at a fraction of the cost, they remain massively under-utilised due to perceived friction and trust gaps.

This session dissects this market inefficiency, with insights from LF Research revealing how closed-source dominance is often driven by inertia rather than superior capability. We will explore how to operationalise true independence by rejecting "open-washing" in favour of rigorous frameworks that demand full model completeness: verifying everything from training data to weights. Join us to learn how to transition from renting black-box APIs to architecting a transparent, reproducible, and economically superior AI stack.

Speakers

Vincent Caldeira

CTO APAC, Red Hat

Vincent Caldeira, Red Hat APAC CTO and Industry Visiting Scholar at Columbia University, drives tech strategy and emerging engineering. A Top 10 APAC CTO (2023) with 20+ years in finance IT, he is an authority on open source, cloud-native technologies and AI. Vincent holds leadership... Read More →

Tuesday August 11, 2026 11:40 - 12:10 KST
Grand Ballroom 2-3

Open AI + Data

13:35 KST

Optimizing ML Inference Across Heterogeneous Accelerators - Sanjiban Sengupta, CERN, University of Manchester

Tuesday August 11, 2026 13:35 - 14:05 KST

Grand Ballroom 2-3

Machine learning is central to high-energy physics,.These environments impose strict latency, throughput, and memory constraints, requiring data processing at unprecedented rates. Addressing these demands requires efficient, hardware-aware inference across heterogeneous architectures.

The ML4EP team at CERN is developing an integrated ecosystem for this purpose. We present recent advances in efficient ML deployment. First, aie4ml ports trained models to next-generation AMD FPGAs for ultra-low-latency inference. PQuantML complements this with hardware-aware pruning and quantization, reducing model size and compute cost while preserving performance.

For CPU and GPU inference, SOFIE translates trained models into optimized C++ for heterogeneous systems. Using alpaka, it enables backend-agnostic execution while minimizing data movement. It integrates with PQuantML to support quantized models and is deployable in both online systems and offline workflows.

Speakers

Sanjiban Sengupta

Doctoral Student at CERN, University of Manchester, CERN, University of Manchester

Sanjiban is a Doctoral Student at CERN, affiliated with the University of Manchester, researching ML inference optimization for the LHC. He contributed to SOFIE, focusing on Keras/PyTorch parsing, ONNX-based operators, and GNN support. He was a CERN Summer Student (2022) and a GSoC... Read More →

Tuesday August 11, 2026 13:35 - 14:05 KST
Grand Ballroom 2-3

Open AI + Data

14:15 KST

The Era of Vibe Coding: Why High-Skill Engineers Are More Critical Than Ever - Yongjin Lee, Songnae High-school

Tuesday August 11, 2026 14:15 - 14:45 KST

Grand Ballroom 2-3

"Let’s be real: My AI has dementia."
"Vibe-coding in real: Me and My AI is stupid"
Welcome to the "Vibe Coding" era, where anyone can prompt their way to complex code. But as a 17-year-old developer who "bullied" LLMs to build a custom Linux Based OS (MaruxOS) from scratch, I’ve seen the ugly truth: AI is a brilliant assistant, but a chronic liar with a 5-minute memory.
In this session, I expose the messy reality of AI-native development. I’ll share how I battled "Contextual Dementia"—where AI forgets my ARM64 architecture mid-patch—and survived "Mindless Yes-Clicking Syndrome," where a single trusted prompt almost nuked my entire glibc.
Key Takeaways:
The Hallucination Hunter: Sniffing out AI’s "confident bullshit."
The Dementia Doctor: Managing AI’s memory loss to maintain architectural integrity.
The Final Decider: Moving beyond the "Yes-Clicking" trap to take true technical ownership.
AI might be writing the code, but only a real engineer can stop it from burning the house down.

Speakers

Yongjin Lee

Student, Developer, Songnae High-school

A normal(maybe?) Student from Korea Developer of Korean Transportation app "LIINK" Developer of Open Source Project MaruxOS Loves developing things for societyFounder of MaruLab

Tuesday August 11, 2026 14:15 - 14:45 KST
Grand Ballroom 2-3

Open AI + Data

14:55 KST

Open Source AI Agents on User-Owned Infra: K3s, MCP, and GPU Sharing in Practice - Miley Fu, OlaresOS

Tuesday August 11, 2026 14:55 - 15:25 KST

Grand Ballroom 2-3

Most open-source AI demos stop at a chatbot, but real users want agents that can work with private files, call tools, and run close to their important data without sending everything to the public cloud.

This talk shows a practical reference architecture for private agent workflows on a single-node K3s-based personal cloud, including local model serving, private knowledge bases, app sandboxing, secure remote access, and multiple GPU allocation modes for competing AI workloads.

Using an open-source personal cloud OS as a case study, I will share what works, what breaks, and which design choices matter when you try to make local AI usable by developers, creators, and small teams rather than just homelab experts.

Speakers

Miley Fu

DevRel, OlaresOS

Miley us the co-chair and keynote speaker for KubeCon+Open Source Summit and AI Dev China 2024. She works on WasmEdge runtime under Linux Foundation as the founding member for over 6 years. She talks at KubeCon, KCD Beijing+Shenzhen, CloudDay Italy, DevRelCon, Open Source Summit Japan... Read More →

Tuesday August 11, 2026 14:55 - 15:25 KST
Grand Ballroom 2-3

Open AI + Data

15:55 KST

MCP Adoption and Why OSPO Skills Matter - Ana Jiménez Santamaría, Linux Foundation (TODO Group and PyTorch Foundation)

Tuesday August 11, 2026 15:55 - 16:25 KST

Grand Ballroom 2-3

As organizations explore the Model Context Protocol (MCP), many of the early conversations naturally happen around AI tooling, integrations, and experimentation. At the same time, MCP may also raise questions that are familiar to Open Source Program Offices (OSPOs) and related teams or professionals with open source management experience, including governance, contribution strategy, standards engagement, and cross-functional coordination

This talk reflects on what organizations might gain by bringing those perspectives into MCP discussions earlier, as well as into their broader Agentic AI strategy. Rather than treating MCP only as a technical AI topic, the session will explore it as an area where open source process knowledge may also add value. Attendees will leave with ideas for how OSPOs can contribute to MCP adoption in practical, collaborative, and organization-aware ways

Speakers

Ana Jiménez Santamaría

Project Manager, Linux Foundation (TODO Group and PyTorch Foundation)

Ana is a Sr. Project Manager at the Linux Foundation, where she supports global open source communities and drives strategic initiatives across the TODO Group and the PyTorch Foundation. She collaborates with CTOs, engineering teams, and business units to promote Open Source management... Read More →

Tuesday August 11, 2026 15:55 - 16:25 KST
Grand Ballroom 2-3

Open AI + Data

16:35 KST

Benchmarking Beyond OpenSearch: Multi-Engine Vector Search Performance With OSB - Mike Oviedo, AWS

Tuesday August 11, 2026 16:35 - 17:05 KST

Grand Ballroom 2-3

As vector search becomes foundational to AI workloads, teams need reliable ways to evaluate engine performance before committing to one. We extended OpenSearch Benchmark (OSB) to support Milvus and Vespa alongside OpenSearch, making it possible to compare throughput, latency, and recall across engines using the same datasets and query patterns.

In this talk, we'll walk through how OSB's new engine-as-module architecture lets you benchmark any search engine with a single CLI command. We'll show how customizable workload parameters control everything from HNSW graph construction to bulk ingestion strategies, and demonstrate how to visualize comparative results in OpenSearch Dashboards, turning raw benchmark data into actionable performance insights.

Whether you're evaluating engines for a new project or optimizing an existing deployment, you'll leave with practical knowledge of how to run your own benchmarks and how to extend OSB to support additional engines by implementing five functions.

Speakers

Mike Oviedo

Software Engineer, AWS

Michael Oviedo is a software engineer at AWS, working on performance and benchmarking tools for OpenSearch. He is a maintainer of the OpenSearch Benchmark project. Outside of work he enjoys playing golf and visiting national parks.

Tuesday August 11, 2026 16:35 - 17:05 KST
Grand Ballroom 2-3

Open AI + Data

17:15 KST

Personalisation and Specialisation of Search With OpenSearch Agentic Search - Cedric Pelvet & Aswath Srinivasan, AWS

Tuesday August 11, 2026 17:15 - 17:45 KST

Grand Ballroom 2-3

Agentic search lets you ask in Natural Language and have OpenSearch plan and execute retrieval. The Query Planner re-writes Natural Language to OpenSearch DSL using SOTA LLMs. This works amazingly well but not without important limitations:

1/ The biggest factor is added latency for remote inference. eCommerce Search demands sub-100ms response times. Even the best results when slow lead to search abandonment.
2/ We'll demo overcoming latency by hosting SLMs locally within OpenSearch nodes using vLLM/Ollama. This is faster & cheaper, but SLMs suffer quality decline in query re-writes. We'll explore fine-tuning with domain-specific data—proving fine-tuned SLMs beat SOTA LLMs.
3/ Relevance remains generic even with Agentic Search. We'll show how to improve it using user and business contexts with hybrid search and reranking.

This hands-on talk covers:
1/ Search Latency with Remote Inference
2/ Locally hosting SLMs using vLLM/Ollama
3/ Agentic search with SLM Local Inference
4/ Improving relevance with user and business contexts
5/ Fine-tuning SLMs for domain-specific query re-writing via Axolotl/LLaMA-Factory

Speakers

Cedric Pelvet

Principal OpenSearch Specialist SA, Amazon Web Services

Cédric Pelvet is a Principal Specialist Solutions Architect at AWS, focusing on AI and near-realtime distributed systems for data like OpenSearch, Kafka and Flink.

Aswath Srinivasan

Senior Search Engine Architect,, OpenSearch @ AWS

Aswath Srinivasan is a Senior Search Engine Architect at Amazon Web Services currently based in Munich, Germany. With over 18 years of experience in various search technologies, Aswath currently focuses on OpenSearch. He is a search and open-source enthusiast and helps customers and... Read More →

Tuesday August 11, 2026 17:15 - 17:45 KST
Grand Ballroom 2-3

Open AI + Data

09:00 KST

Keynote: Welcome Back - Jim Zemlin, CEO, The Linux Foundation

Wednesday August 12, 2026 09:00 - 09:10 KST

Grand Ballroom 2-3

Speakers

Jim Zemlin

CEO, The Linux Foundation

Wednesday August 12, 2026 09:00 - 09:10 KST
Grand Ballroom 2-3

Keynote Sessions

09:10 KST

Keynote Sessions To Be Announced

Wednesday August 12, 2026 09:10 - 10:05 KST

Grand Ballroom 2-3

Wednesday August 12, 2026 09:10 - 10:05 KST
Grand Ballroom 2-3

Keynote Sessions

10:10 KST

Keynote: Building Trust in the Age of AI: From Data Openness to Responsible Innovation - Dr. Hongrak Lee, President and Chief AI Officer, LG AI Research

Wednesday August 12, 2026 10:10 - 10:25 KST

Grand Ballroom 2-3

This presentation examines the evolving role of open data in the next phase of artificial intelligence development, and the growing imperative to align innovation with trust. As AI systems become increasingly data-driven, the quality, origin, and governance of data are emerging as foundational issues that will shape not only technological progress, but also public confidence and global competitiveness.
The talk situates these developments within a broader shift toward greater transparency and accountability in AI, reflected in emerging policy directions such as the EU AI Act and Korea’s Korean AI Basic Act. Rather than viewing openness as a risk to be constrained, it explores how responsible data practices and shared governance approaches can enable wider participation in AI development while maintaining integrity and trust.
Ultimately, the presentation argues that the future of AI will depend not only on model performance, but on the strength of the underlying data ecosystem. Building sustainable trust around open data—through transparency, collaboration, and accountability—will be critical to unlocking the full potential of AI at scale.

Speakers

Dr. Hongrak Lee

President and Chief AI Officer, LG AI Research

Honglak Lee is currently an Executive Vice President and Chief Scientist of Artificial Intelligence at LG AI Research and an Associate Professor of Computer Science at the University of Michigan, Ann Arbor. Previously he worked as a Research Scientist at Google Research, Brain Team... Read More →

Wednesday August 12, 2026 10:10 - 10:25 KST
Grand Ballroom 2-3

Keynote Sessions

11:00 KST

LLMs Change — Where Should Knowledge Live? (Lessons From SBOM) - Koji Annoura, Annoura Office

Wednesday August 12, 2026 11:00 - 11:30 KST

Grand Ballroom 2-3

Large Language Models (LLMs) are widely used to search, summarize, and generate answers. They are powerful, but results are not always stable and can be difficult to verify.

Many systems use Retrieval-Augmented Generation (RAG) to connect LLMs with external data. This helps, but does not fully solve the problem. The same question can produce different answers depending on the model or context, making knowledge hard to manage.

This raises a simple question: where should knowledge be managed?

A similar issue exists in software supply chains. SBOM (Software Bill of Materials) makes components and relationships visible, but is often treated as static data.

Based on hands-on experience designing graph-based knowledge systems, this session introduces a design approach: managing knowledge outside LLMs as structured, persistent data.

We discuss lessons from SBOM and how graph-based approaches—using technologies such as SQL/PGQ or GQL—can help understand relationships and trace changes.

The focus is a practical way of thinking for more open and sustainable knowledge practices.

Speakers

Koji Annoura

Graph Data & AI Practitioner, Annoura Office

Koji Annoura is a practitioner in graph data and knowledge systems, focusing on modeling relationships in real-world systems.

He co-founded the Neo4j Users Group Tokyo in 2013 and founded the Apache Hop User Group Japan in 2021.
His work focuses on structuring complex data usi... Read More →

Wednesday August 12, 2026 11:00 - 11:30 KST
Grand Ballroom 2-3

Open AI + Data

11:40 KST

From Black Box To Insight: Observability for AI Agents in Production - Mostafa Radwan, Datadog & Brandon Kang, Akamai Technologies

Wednesday August 12, 2026 11:40 - 12:10 KST

Grand Ballroom 2-3

AI agents are quickly moving from prototypes to production systems that manage APIs, tools, and complex reasoning tasks.

Once these systems are deployed, they often act like black boxes, hiding failures, slowdowns, and unexpected behavior.

This session will show you how to add observability to agentic systems with open-source tools and cloud-native tech.

Brandon and Mostafa will break down the lifecycle of an AI agent, covering prompt execution, tool invocation, memory access, and multi-agent coordination, and demonstrate how to make each stage observable.

Using a practical, architecture-focused approach, they will show how to:

- Trace agent workflows across distributed systems
- Monitor latency and token usage
- Detect anomalies such as hallucinations, tool misuse, and runaway behavior.
- Connect LLM behavior with infrastructure metrics like GPU, container, and network data.

They will also present a complete reference architecture that uses open-source projects including OpenTelemetry (OTel), Prometheus, Grafana, and some new tools for LLM observability.

Attendees will learn practical ways to build transparent and reliable production AI agent systems.

Speakers

Mostafa Radwan

Senior Solutions Engineer, Datadog

Mostafa is a technologist specialized in cloud native computing, observability, and security.

He started his career as a software engineer before getting in the trenches of application and production support.

He worked as a Solutions Architect at Docker where he helped enterp... Read More →

Brandon Kang

Principal Technical Solutions Architect, Akamai Technologies

Brandon Kang is a principal solutions architect at Akamai, driving cloud-native and AI initiatives.
With experience at Samsung, Microsoft, and Akamai, he brings deep expertise in large scale cloud native architecture and AI.
He is the author of 12 IT books on S/W engineering, Sec... Read More →

Wednesday August 12, 2026 11:40 - 12:10 KST
Grand Ballroom 2-3

Open AI + Data

13:35 KST

Prompt Injection Is the New SQL Injection: Securing Tool-Using Agents - Jigyasa Grover, Uber & Rishabh Misra, Atlassian

Wednesday August 12, 2026 13:35 - 14:05 KST

Grand Ballroom 2-3

As LLM-based agents gain access to tools - APIs, databases, file systems, and internal services, the security model changes. The model is no longer only generating text; it is selecting actions and invoking capabilities across systems.

Prompt injection attacks exploit this boundary. between model reasoning & external execution.

This talk examines how tool-enabled agents built on open LLM frameworks expand the attack surface and why traditional input validation approaches are insufficient.

We will analyze concrete failure modes such as:
- Prompt injection vs classical injection: control of model reasoning rather than query structure
- Tool outputs as secondary injection vector in multi-step workflows
- Why system prompts & guardrails are not reliable isolation boundaries
- Capability scoping & least-privilege design for tool access
- Isolation patterns for tool execution (sandboxing, mediated execution layers)
- Structured tool interfaces vs free-form prompting
- Observability patterns for tracing agent decisions and tool calls
- Adversarial testing of agent pipelines

Examples draw from patterns emerging in open-source LLM and agent ecosystems.

Speakers

Jigyasa Grover

ML Tech Lead • Google Developer Advisory Board Member • LinkedIn [in]structor • Book Author • Startup Advisor • 12 time AI + Open Source Award Winner • Featured @ Forbes, UN, Google I/O, and more!, Uber

Jigyasa Grover is an ML tech lead at Uber focused on large-scale ML and personalization, previously at Twitter/X, Meta, Faire, and Bordo AI. Author of Sculpting Data for ML, she serves on Google’s Developer Advisory Board and was selected for Google I/O. A Google Developer Expert... Read More →

Rishabh Misra

Principal ML Engineer, Atlassian

I am a Principal ML Engineer & Researcher with over 10 years of experience in the AI and ML space. I am currently driving LLM pretraining, postraining, and personalization efforts at Atlassian, and have previously led Deep Learning & GenAI-powered user personalization at late-stage... Read More →

Wednesday August 12, 2026 13:35 - 14:05 KST
Grand Ballroom 2-3

Open AI + Data

14:15 KST

How x402 Brings Open Source Governance to Payments - Junhyeok Yoo, Four Pillars

Wednesday August 12, 2026 14:15 - 14:45 KST

Grand Ballroom 2-3

In April 2026, x402 joined the Linux Foundation with over 20 founding members. It is the first payment protocol under open source governance at the Linux Foundation.

x402 activates HTTP 402 "Payment Required," reserved in 1997 but never used. A server responds with 402 and payment terms, the client settles on-chain, the resource is delivered. Apache 2.0, zero protocol fees, chain-agnostic, no single-organization dependency.

Part 1: Why now. Every internet layer runs on open protocols except payments. That breaks when AI agents must pay at machine speed. We map the agentic payment stack and ask: is it open, who governs it?

Part 2: How x402 works. HTTP 402 challenge-response, stateless architecture, one middleware line to gate any API, production deployments today.

Part 3: Bottom-up to foundation. x402 was open-sourced, developers adopted it, major infrastructure providers shipped native support, competing protocols chose to integrate x402 rather than build a rival. Then it moved to the Linux Foundation.

Part 4: What comes next. The protocol is early. Foundation governance changes the signal. We examine what sustained adoption requires.

Speakers

Junhyeok Yoo

Researcher, Four Pillars

Junhyeok Yoo is a Researcher at Four Pillars in Seoul, deeply focused on the infrastructure of agentic commerce and machine economies. As a 4th-year CS undergraduate at SKKU(Sungkyunkwan University) and VP of Decipher (SNU’s blockchain academy), he explores the intersection of computer... Read More →

Wednesday August 12, 2026 14:15 - 14:45 KST
Grand Ballroom 2-3

Open AI + Data

14:55 KST

Yukti: A Unified Inference Interface for Low-Latency Machine Learning in High-Energy Physics - Sanjiban Sengupta, CERN, University of Manchester

Wednesday August 12, 2026 14:55 - 15:25 KST

Grand Ballroom 2-3

Machine learning is increasingly used in high-energy physics, particularly in trigger systems that process data at rates of 100 kHz while making real-time event selection decisions. The latency and reliability requirements demand highly optimized inference pipelines. While portable solutions such as ONNX Runtime simplify deployment, many applications rely on hardware-specific libraries like NVIDIA TensorRT and MIGraphX (via ROCm) for optimal performance. Code-generation approaches such as SOFIE offer additional efficiency but introduce integration complexity.

We present a unified inference interface that abstracts backend-specific details while preserving performance. It enables execution across multiple inference libraries without data copies or user-side configuration changes. An offline processor converts trained models into backend-optimized plans, and a lightweight runtime loads and executes them through a common API with direct data access for heterogeneous environments.

Speakers

Sanjiban Sengupta

Doctoral Student at CERN, University of Manchester, CERN, University of Manchester

Wednesday August 12, 2026 14:55 - 15:25 KST
Grand Ballroom 2-3

Open AI + Data

15:55 KST

Connecting the Dots With Context Graphs - Stephen Chin, Neo4j

Wednesday August 12, 2026 15:55 - 16:25 KST

Grand Ballroom 2-3

AI systems need more than intelligence; they need context that persists. Without it, even strong models can misinterpret information, lose decision rationale, or repeat the same mistakes. Context Graphs have emerged as a practical pattern for agentic AI: a living graph that captures not only what was retrieved or known, but how context led to actions through tool calls, constraints, policies, and outcomes, stitched across entities and time so precedent becomes searchable.

This talk explores context engineering as the discipline of designing that context layer, and shows how context graphs complement retrieval by enabling multi-hop, structured context assembly (building on GraphRAG-style hierarchical summaries) while improving explainability and evaluation. Attendees will leave with a practical understanding of how to build context pipelines that combine contextual retrieval with persistent memory and provenance, and why context graphs are becoming central to trustworthy, enterprise-ready AI systems.

Speakers

Stephen Chin

VP of Developer Relations, Neo4j

Stephen Chin is VP of Developer Relations at Neo4j and author of numerous titles including the upcoming GraphRAG: The Definitive Guide for O'Reilly. He has given keynotes and main stage talks at numerous conferences around the world including AI Engineer Summit, AI DevSummit, Devoxx... Read More →

Wednesday August 12, 2026 15:55 - 16:25 KST
Grand Ballroom 2-3

Open AI + Data

16:35 KST

Science in the Agentic Era: Structured Experimentation With Ado - Alessandro Pomponio & Michael Johnston, IBM

Wednesday August 12, 2026 16:35 - 17:05 KST

Grand Ballroom 2-3

As AI agents become increasingly capable of generating code and executing complex workflows, their use in research is still limited by concerns about rigour and reproducibility. This session introduces ado, an open-source framework that brings structure to agent-driven scientific experimentation.

ado defines schemas for the core elements of a discovery process: the problem space and how to explore it. Agents iteratively propose and refine experimental campaigns as validated configurations based on these schemas, while ado handles execution. This separation of research intent from execution constrains agents to focus on the research task, reducing hallucinations and the need to write boilerplate code. Combined with a set of agent skills for formulating problems, creating and running experiments, and analysing their results, ado provides a framework for end-to-end agent-driven discovery workflows.

Whether you are an experienced researcher or new to computational experimentation, this talk presents a practical model for integrating AI agents into research workflows while keeping experimentation structured, transparent, and reproducible.

Speakers

Michael Johnston

STSM, IBM Research, IBM

Michael Johnston is an STSM at IBM Research and manager of the Next Generation Systems and Cloud team at the Ireland lab. His background is in computational physics and HPC and his current focus is on future systems for science, with an emphasis on benchmarking, performance optimisation... Read More →

Alessandro Pomponio

Research Software Engineer, IBM

Alessandro Pomponio is a Research Software Engineer and a member of the Next Generation Systems and Cloud team in IBM Research Europe – Ireland. His work focuses on optimizing containerized workflows and accelerating the scientific discovery process. His main areas of interests... Read More →

Wednesday August 12, 2026 16:35 - 17:05 KST
Grand Ballroom 2-3

Open AI + Data

17:15 KST

Exploring HiFloat8: A Tapered Format Complementing the FP8 Ecosystem for Robust Model Training - Speakers To Be Announced

Wednesday August 12, 2026 17:15 - 17:45 KST

Grand Ballroom 2-3

Standard FP8 formats suffer from frequent gradient overflows and heavy reliance on complex Delayed Scaling, which often lead to training instability or suboptimal convergence in large models. This session introduces HiFloat8 (HiF8) — a tapered precision format that offers an alternative approach to managing dynamic range. This "natural" alignment with neural network weight/gradient distributions allows HiF8 to capture high-magnitude outliers without the aggressive scaling required by standard FP8.We explore how HiF8 can works in the training and inference procedure.We will demonstrate the implementation of HiF8 within the ecosystem. They allow developers to evaluate performance of Hif8 on GPUs. Also, we will give an analysis of training stability and final loss parity where HiF8 provides relatively the same accuracy and 1.5-1.7 times GEMM performance than FP16. Finally, we will share insights from our ongoing collaboration on dedicated hardware support for HiF8.

Wednesday August 12, 2026 17:15 - 17:45 KST
Grand Ballroom 2-3

Open AI + Data

09:00 KST

09:30 KST

10:15 KST

11:00 KST

11:40 KST

13:35 KST

14:15 KST

14:55 KST

15:55 KST

16:35 KST

17:15 KST

09:00 KST

09:10 KST

10:10 KST

11:00 KST

11:40 KST

13:35 KST

14:15 KST

14:55 KST

15:55 KST

16:35 KST

17:15 KST

Get help with the event