Position: Foundation Models Need Digital Twin Representations
This is a position paper proposing a paradigm shift for improving foundation models in AI, but it is incremental as it builds on existing concepts without presenting new empirical results.
The paper argues that current foundation models' reliance on token representations limits their ability to learn real-world knowledge and perform tasks like semantic coherence and causal reasoning, proposing digital twin representations as an alternative to address these issues.
Current foundation models (FMs) rely on token representations that directly fragment continuous real-world multimodal data into discrete tokens. They limit FMs to learning real-world knowledge and relationships purely through statistical correlation rather than leveraging explicit domain knowledge. Consequently, current FMs struggle with maintaining semantic coherence across modalities, capturing fine-grained spatial-temporal dynamics, and performing causal reasoning. These limitations cannot be overcome by simply scaling up model size or expanding datasets. This position paper argues that the machine learning community should consider digital twin (DT) representations, which are outcome-driven digital representations that serve as building blocks for creating virtual replicas of physical processes, as an alternative to the token representation for building FMs. Finally, we discuss how DT representations can address these challenges by providing physically grounded representations that explicitly encode domain knowledge and preserve the continuous nature of real-world processes.