A query-guided token pruning method improves speech-LLM accuracy on a new long-form audio benchmark while cutting computation.
AnyGPT: Unified multimodal LLM with discrete sequence modeling,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
eess.AS 1years
2024 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval
A query-guided token pruning method improves speech-LLM accuracy on a new long-form audio benchmark while cutting computation.