A post-hoc sparse autoencoder compresses the Vision Wormhole latent communication tensor by 128× with essentially unchanged single-run task accuracy, using only 50 of 4096 dictionary features.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Post-Hoc Sparse Coding of Latent Communication Between Vision-Language Model Agents
A post-hoc sparse autoencoder compresses the Vision Wormhole latent communication tensor by 128× with essentially unchanged single-run task accuracy, using only 50 of 4096 dictionary features.