WAND adapts AR-TTS models to constant complexity via windowed attention and distillation, cutting KV cache memory by up to 66.2% while preserving quality and achieving length-invariant latency.
Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models
WAND adapts AR-TTS models to constant complexity via windowed attention and distillation, cutting KV cache memory by up to 66.2% while preserving quality and achieving length-invariant latency.