NEURRATOR bridges neural spike trains to frozen CLIP patch embeddings via a learned encoder, then uses a multimodal LM and sparse autoencoder to produce validated natural-language narrations of viewed scenes from Neuropixel recordings.
USER: <image>\n Describe this scene in one sentence.\n ASSISTANT:
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.NC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Can neurons speak? Semantic narration of vision at single-cell resolution
NEURRATOR bridges neural spike trains to frozen CLIP patch embeddings via a learned encoder, then uses a multimodal LM and sparse autoencoder to produce validated natural-language narrations of viewed scenes from Neuropixel recordings.