I suppose the follow-up question is: how effectively can a model learn to re-implement a physics simulator, if given access to it during training—instead of being explicitly trained to generate XML config files to run the simulator during inference?
If it’s substantially more efficient to use this paper’s approach and train your model to use a general purpose (and transparent) physics simulator, I think this bodes well for interpretability in general. In the ELK formulation, this would enable Ontology Identification.
On this point, the paper says:
Mind’s Eye is also efficient, since it delegates domain-specific knowledge to external expert models… The size of the LM can thus be significantly shrunk since it removes the burden of memorizing all the domain-specific knowledge. Experiments find that 100× smaller LMs augmented with Mind’s Eye can achieve similar reasoning capabilities as vanilla large models, and its promptingbased nature avoids the instability issues of training mixture-of-expert models (Zoph et al., 2022). The compatibility with small LMs not only enables faster LM inference, but also saves time during model saving, storing, and sharing.
On the other hand, the general trend of “end-to-end trained is better than hand-crafted architectures” has been going strong in recent years; it’s mentioned in the CAIS post, and Demis Hassabis noted that he thinks it’s likely to continue in his interview by Lex Fridman (indeed they chatted quite a bit about using AI models to solve Physics problems). And indeed, DeepMind has a recent paper gesturing towards an end-to-end learned Physics model from video, which looks far less capable than the one shown in the OP, but two papers down the line, who knows.
I suppose the follow-up question is: how effectively can a model learn to re-implement a physics simulator, if given access to it during training—instead of being explicitly trained to generate XML config files to run the simulator during inference?
If it’s substantially more efficient to use this paper’s approach and train your model to use a general purpose (and transparent) physics simulator, I think this bodes well for interpretability in general. In the ELK formulation, this would enable Ontology Identification.
On this point, the paper says:
On the other hand, the general trend of “end-to-end trained is better than hand-crafted architectures” has been going strong in recent years; it’s mentioned in the CAIS post, and Demis Hassabis noted that he thinks it’s likely to continue in his interview by Lex Fridman (indeed they chatted quite a bit about using AI models to solve Physics problems). And indeed, DeepMind has a recent paper gesturing towards an end-to-end learned Physics model from video, which looks far less capable than the one shown in the OP, but two papers down the line, who knows.