About us
¡Bienvenido al Madrid Machine Learning Meetup! El evento donde se revisan los últimos avances en Deep Learning a través de la lectura y discusión conjunta de artículos científicos.
Si te inquietan StableDiffusion, LLMs, Transformers, NeRF’s, GNNs, GANs y otros, acércate al MIL a conocer estos temas en detalle de la mano de expertos en la materia.
El Reading Group está organizado por la Universidad Politécnica de Madrid, U. Rey Juan Carlos, Apolo AI y ARQUIMEA Research Center en colabiración con el Ayuntamiento de Madrid.
Puedes ver las sesiones anteriores en:
https://youtube.com/playlist?list=PLHeG8vnHL6C8mOU8K8vs2j9I7dSMYCgJQ
Upcoming events
1
🤝In AI We Trust: Data Poisoning, Misinformation, and Secure Agents
MIL ( Madrid Innovation Lab ), de la comunidad, C. de Bravo Murillo, 39, Local interior, Chamberí, 28015 Madrid, Spain, Madrid, MD, ESWelcome to the Madrid ML Meetup! 🤗
If you're concerned about AI's fine print, this talk is for you. We'll begin with adversarial machine learning and data poisoning: how the data a model learns from can be used to manipulate it. Then we'll examine the factuality of LLM responses: why they can be convincing and false at the same time, even without an attack, and how to assess them. Finally, we'll move from answers to actions: what happens when agents rely on harnesses, skills, and tools to act on our behalf, and what permissions, boundaries, and controls we should put in place.🤝
Our speaker, Javier Carnerero Cano, is a Research Scientist at IBM Research and an Academic Visitor at Imperial College London. He holds a PhD in AI security from Imperial College London. His current work focuses on LLM factuality, data-source trust, data poisoning, misinformation, safeguards, and agentic-skills security, including collaboration with NASA on evaluating and correcting AI-generated scientific content.
The event is organized by Machine Learning Circle, Universidad Politécnica de Madrid, Universidad Rey Juan Carlos, and ARQUIMEA Research Center, in collaboration with the Madrid City Council. 🏦
60 attendees
Past events
24
