2025-10-01 –, Gaston Berger
As AI floods the digital landscape with content, what happens when it starts repeating itself?
This talk explores model collapse, a progressive erosion where LLMs and image generators loop on their own results, hindering the creation of novel output.
We will show how self-training leads to bias and loss of diversity, examine the causes of this degradation, and quantify its impact on model creativity.
Finally, we will also present concrete strategies to safeguard the future of generative AI, emphasizing the critical need to preserve innovation and originality.
By the end of this talk, attendees will gain insights into the practical implications of model collapse, understanding its impact on content diversity and the long-term viability of AI.
As AI floods the digital landscape with content, what happens when it starts repeating itself?
This talk explores model collapse, a progressive erosion where LLMs and image generators loop on their own results, hindering the creation of novel output.
We will show how self-training leads to bias and loss of diversity, examine the causes of this degradation, and quantify its impact on model creativity.
Finally, we will also present concrete strategies to safeguard the future of generative AI, emphasizing the critical need to preserve innovation and originality.
By the end of this talk, attendees will gain insights into the practical implications of model collapse, understanding its impact on content diversity and the long-term viability of AI.
Talk outline:
- 0-8 min: Introduction to the issue and examples
- 8-18 min: Definition of model collapse and explanation of root causes
- 18-25 min: Remediation strategies
- 25-30 min: Conclusion and Q&A
Statistician by education, Valeria is an AI Scientist specializing in real-time models for complex, challenging scenarios. Driven by a deep curiosity for the latest research, she applies advanced analytical techniques to build intelligent systems that deliver immediate and effective solutions in high-impact domains.