Three VQ-based QAT techniques (cosine-similarity STE, hard-attention VQ, mixed VQ/LQ NAS) are proposed; they simplify training but do not consistently outperform existing methods.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Three incremental VQ techniques using cosine similarity and NAS for neural net weight compression yield design insights without consistent accuracy gains over existing approaches.
citing papers explorer
-
RAT: RunAnyThing via Fully Automated Environment Configuration
Three VQ-based QAT techniques (cosine-similarity STE, hard-attention VQ, mixed VQ/LQ NAS) are proposed; they simplify training but do not consistently outperform existing methods.