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
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
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.