Temporal AI: Reasoning Through Time Across Continuous Data Streams
How can AI reason about a system as it changes over time?
Language models have made text a powerful interface for knowledge and reasoning, with multimodal models extending these capabilities to images and audio. Continuous sensor streams present a different challenge: understanding how signals evolve over time.
Join the session with Patrick Langer, Co-Founder of Aionic Labs, exploring Temporal AI and Time Series Language Models (TSLMs), including OpenTSLM. We’ll discuss how these models reason across sensor streams and how they could help build a shared understanding of a changing system to support multiple tasks.
→ Explore the related research before the webinar
What we’ll cover
- Time Series Language Models: What TSLMs are and how OpenTSLM approaches reasoning over sensor data.
- Understanding change over time: Why continuous data streams call for models that capture how a system evolves.
- Shared representations for multiple tasks: The direction toward more general temporal models and the limitations of current time-series foundation models.
Who should attend
Researchers, scientists and ML engineers interested in time-series modeling, multimodal AI and reasoning over sensor data.
About Nebius Science Paper Club
Nebius Science Paper Club is a webinar series led by Nebius researchers. Each session brings together paper authors and practitioners to discuss new ideas, research, and discoveries in AI.
The session is open to researchers, engineers, students, and anyone interested in knowledge distillation, model compression, and computer vision.
Register to get the link and the recording
Try Nebius AI Cloud console today
