Test-Time Training Agents for Deep Exploration | Jonas Hübotter, ETH Zürich | BLISS e.V. скачать в хорошем качестве

Test-Time Training Agents for Deep Exploration | Jonas Hübotter, ETH Zürich | BLISS e.V.

We are excited to feature Jonas Hübotter, who is currently a PhD student at ETH Zürich and will discuss "Test-Time Training Agents for Deep Exploration". 🎥 Watch to Discover: The standard paradigm of machine learning separates training and testing. Training aims to learn a model by extracting general rules from data, and testing applies this model to new, unseen data. We study an alternative paradigm where the model is trained at test-time specifically for the given task. We investigate why such test-time training can effectively specialize a model to individual tasks. Further, we demonstrate that such test-time training enables models to continually improve and eventually solve challenging tasks, which are out of reach for the initial model. 📅 Recorded on January 13, 2026, at TU Berlin. ✨ About BLISS e.V. We are BLISS e.V., the AI organization in Berlin that connects like-minded individuals who share great interest and passion for the field of machine learning. This winter 2025/26, we will, again, host an exciting speaker series on site in Berlin, featuring excellent researchers from Tübingen AI Center, DeepMind, Microsoft, King's College London, cohere, and ETH Zürich. We also host: Weekly reading groups for in-depth discussions Biweekly community events for hands-on learning and networking 🎉 Get Involved: Interested in Machine Learning? Follow us to stay updated on upcoming events and join our community of AI enthusiasts! 🔗 Event Links: Talk-specific Meetup: https://www.meetup.com/bliss-speaker-... --- Timestamps: 00:00 Introduction 08:07 Test-time training 22:01 Test-time training agents 42:40 Conclusion 43:55 Q&A #MachineLearning #ArtificialIntelligence #DeepLearning #TestTimeTraining #AIResearch #ETHZurich #BLISS