AI Tools & Models HOTFeaturedAll
arXiv cs.AIScore60

Interpretable weight-space programming builds transparent transformers and brain encoding models

Summary

This work uses interpretable weight-space programming to build transparent transformers that serve scientific explanation, not just prediction.

Why this matters

Covers model · Relevant to this topic

Open original ↗

Source: arXiv cs.AI · arxiv.org

Topics

Related items