Mastering the RAG for better decision-making :

strategic vision, innovation, business use cases, implementation...

With adoption set to grow by +49.1% by 2030 (Grand View Research), RAG (Retrieval-Augmented Generation) is becoming the cornerstone of next-generation AI Agents, capable of mobilizing reliable, contextualized and dynamic knowledge.

More than just a demonstration, ILLUIN Technology offers an educational session dedicated to decision-makers: understanding key principles, high-impact business use cases, and concrete implementation conditions with top talent.

Our experts will share their reading of the latest advances in the field and how our R&D is transforming them into ready-to-use solutions for major groups. It's an opportunity to gain some perspective and leave with some concrete benchmarks for your AI projects.

Information practical information

Auditorium GMAI Dialogue - left

When?

🗓️ June 19, 2025, 8:30 a.m. to 10:30 a.m.

Where?

📍 Paris, La Défense, Tour Légende - 20 place de la Défense - 92800 Puteaux

For whom?

🎯 AI decision-makers, Innovation, CIOs, data/IA teams... anyone who leads AI teams of any size.

The speakers

Grégoire Perret

Renaud MONNET - VP Digital, AI & CIO at CentraleSupélecSpecial guest

Originally co-founded by 12 engineers from CentraleSupélec, ILLUIN Technology has always maintained close collaborative links with many illustrious entities at the Université Paris-Saclay, both for research purposes and to pass on to younger generations.

Renaud MONNET, one of the architects of this virtuous open innovation dynamic, will share his experience as an ILLUIN Technology customer, and research and academic partner.

Robert VESOUL

CEO & Co-founder
ILLUIN Technology

Wacim BELBLIDIA

Executive VP AI & IDP Products
ILLUIN Technology

Xavier VACCARI

VP Strategy & Partnerships
ILLUIN Technology

Gautier VIAUD

Head of R&D
ILLUIN Technology

2 months of Compass newsletters offered to participants 🎁

Compass is our intelligence program for tech, AI and Data Science teams. Through weekly newsletters, we share our expertise and R&D results. Below, our late April 2025 newsletter in podcast format 🎧

Process and themes addressed

8:30 am ☕️ Welcome coffee

9:00 am 🎤 Introduction to ILLUIN Technology

9h15 🔭 AI trends 2025: focus on RAG and AI Agents

9:30 a.m. 🔬 R&D revelations and innovations RAG Multimodal

10h00 🙋‍♀️ Questions and discussion

RAG and RAG Multimodal

RAG is establishing itself as a strategic lever in AI projects. We offer you a clear, operational vision of what RAG really enables today: key principles,industrialization challenges, feedback, and high-impact business use cases. From strategic intelligence to technical game-changers, you'll leave with concrete reference points for piloting or challenging your future AI projects.

Agents and RAGs

Next-generation AI Agents rely on RAG to gain in autonomy, relevance and robustness. We'll show you (with the nAIxt platform in particular) how to orchestrate agents capable of reasoning from a knowledge base updated in real time. The aim is to design reliable, adaptive and truly useful business assistants.

Focus ColPali v2 and R&D

Our R&D is at the cutting edge of RAG, as demonstrated by the worldwide success of our ColPali publication. You'll discover our advances in image retrieving, small efficient models (ColSmol), and new evaluation techniques (ViDoRe v2). Visual RAG demo, agentic RAG... between vision and execution, we take you behind the scenes of innovation.

Why come?

  • Understanding the fundamentals of RAG
  • Discover use cases and concrete applications RAG - AI Agents
  • Learn from our many real-life experiences
  • Anticipating future developments thanks to our R&D work
  • Discuss your use cases with our experts

Our strengths, our know-how :5 pillars that make us unique

experts from the the best training

🎓 Career
EPFL x CentraleSupélec, PhD

🎂 XP
4 years old

⚡️ Domains
#Research #Theory #LLMCore

🎓 Career path
CentraleSupélec x Oxford, PhD

🎂 XP
10 years

⚡️ Domains
#Research #LLMStrategy #LLMCore

🎓 Courses
CentraleSupélec x Imperial College London

🎂 XP
6 years old

⚡️ Domains
#Research #LLMCore #LLMOps

🎓 Course
CentraleSupélec x DTU

🎂 XP
8 years

⚡️ Domains
#LLMStrategy #Product #Business

🎓 Courses
CentraleSupélec x ENS Paris-Saclay

🎂 XP
4 years old

⚡️ Domains
#Research #Theory #LLMCore

🎓 Courses
CentraleSupélec

🎂 XP
8 years

⚡️ Domains
#LLMStrategy #SoftEng #Business

20%

of employees involvedon R&D projects

Data Scientist
Research Data Scientist
NLU / LLM Engineer
RAG Expert
GenAI Pipeline Designer
Prompt Engineering Expert

Technical excellence

Our engineers, who come from the best French and European educational establishments, have mastered the state of the art in all areas of AI technology, and are recognized in the ecosystem as top-level experts.

Multidisciplinary expertise

Our 100+ experts cover all the skills needed to design and industrialize your AI projects: Data Science, Data Engineering, DataOps, MLOps, Software Engineering...

Speed and business vision

Our teams' high level of technical expertise translates into a speed that our customers notice and measure, enhanced by a rapid understanding of business challenges, and even sector specialization for certain profiles.

Maker DNA, commitment and advice

That's how our customers describe us: pleasant, committed personalities working alongside in-house teams, who like to roll up their sleeves to find elegant solutions to complex problems.

Our investment

5400+

JH of R&D / year

20%

of the workforce involved

Our research areas

Computer Vision & Documents

GenAI & Language Processing

Voice flow analysis

Our partners

A powerful tech differentiator for customized use cases

nAIxt is our proprietary multimodal, composite and agentic AI development and orchestration platform, which enables us to implement and industrialize your most complex custom use cases 3 to 5 times faster! It's also the foundation of our suite of products, which are true tech gas pedals too.

No time to scan the entire AI landscape? We do it for you every week!

Compass is a technology watch and upskilling program for tech, AI and Data Science teams. Through weekly newsletters, we share our expertise and R&D results.

⬅️ Opposite, our newsletter for late April 2025 in podcast format!

🔥 On this week's menu: the models that are shaking up benchmarks (Qwen3, Phi-4, DeepSeek-Prover-V2), a novel method for evaluating RAG (AutoNuggetizer), and a big reality check on Chatbot Arena. On the pedagogical side: Speech-to-Speech, LLM flaws, sycophancy... we break it down and explain!

🎧 Read or listen: 10 minutes to shine in meetings.

experts from the the best training

🎓 Career
EPFL x CentraleSupélec, PhD

🎂 XP
4 years old

⚡️ Domains
#Research #Theory #LLMCore

🎓 Career path
CentraleSupélec x Oxford, PhD

🎂 XP
10 years

⚡️ Domains
#Research #LLMStrategy #LLMCore

🎓 Courses
CentraleSupélec x Imperial College London

🎂 XP
6 years old

⚡️ Domains
#Research #LLMCore #LLMOps

🎓 Course
CentraleSupélec x DTU

🎂 XP
8 years

⚡️ Domains
#LLMStrategy #Product #Business

🎓 Courses
CentraleSupélec x ENS Paris-Saclay

🎂 XP
4 years old

⚡️ Domains
#Research #Theory #LLMCore

🎓 Courses
CentraleSupélec

🎂 XP
8 years

⚡️ Domains
#LLMStrategy #SoftEng #Business

20%

of employees involvedon R&D projects

Data Scientist
Research Data Scientist
NLU / LLM Engineer
RAG Expert
GenAI Pipeline Designer
Prompt Engineering Expert

Technical excellence

Our engineers, who come from the best French and European educational establishments, have mastered the state of the art in all areas of AI technology, and are recognized in the ecosystem as top-level experts.

Multidisciplinary expertise

Our 100+ experts cover all the skills needed to design and industrialize your AI projects: Data Science, Data Engineering, DataOps, MLOps, Software Engineering...

Speed and business vision

Our teams' high level of technical expertise translates into a speed that our customers notice and measure, enhanced by a rapid understanding of business challenges, and even sector specialization for certain profiles.

Maker DNA, commitment and advice

That's how our customers describe us: pleasant, committed personalities working alongside in-house teams, who like to roll up their sleeves to find elegant solutions to complex problems.

Our investment

5400+

JH of R&D / year

20%

of the workforce involved

Our research areas

Computer Vision & Documents

GenAI & Language Processing

Voice flow analysis

Our partners

A powerful tech differentiator for customized use cases

nAIxt is our proprietary multimodal, composite and agentic AI development and orchestration platform, which enables us to implement and industrialize your most complex custom use cases 3 to 5 times faster! It's also the foundation of our suite of products, which are true tech gas pedals too.

No time to scan the entire AI landscape? We do it for you every week!

Compass is a technology watch and upskilling program for tech, AI and Data Science teams. Through weekly newsletters, we share our expertise and R&D results.

⬅️ Opposite, our newsletter for late April 2025 in podcast format!

🔥 On this week's menu: the models that are shaking up benchmarks (Qwen3, Phi-4, DeepSeek-Prover-V2), a novel method for evaluating RAG (AutoNuggetizer), and a big reality check on Chatbot Arena. On the pedagogical side: Speech-to-Speech, LLM flaws, sycophancy... we break it down and explain!

🎧 Read or listen: 10 minutes to shine in meetings.

Discover our latestR&D insights on RAG

ViDoRe Benchmark V3: A comprehensive evaluation of RAG in real-world use cases

ViDoRe Benchmark V3: A comprehensive evaluation of RAG in real-world use cases

How ViDoRe V3 sets a new standard for evaluating RAG pipelines on visually-rich, enterprise documents. A comprehensive, human-verified benchmark by ...
DeepSearch using visual RAG in agentic frameworks

DeepSearch using visual RAG in agentic frameworks

How visual retrieval methods-such as ColPali-can significantly enhance retrieval-augmented generation (RAG) systems, particularly when integrated within agentic environments ...
Introducing ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval

Introducing ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval

ViDoRe Benchmark V2 pushes the boundaries of visual retrieval evaluation by introducing more challenging, diverse, and realistic tasks. Addressing the ...

The leaders choose us

Registration is now closed, thank you!

🗓️ June 19, 2025, starting at 8:30 a.m.

📍 Face-to-face, Paris, La Défense, Tour Légende - 20 place de la Défense - 92800 Puteaux