SemHash-LLM is a multi-granularity semantic hashing framework that fuses character, token, and document signals via gated fusion and cascaded filtering to achieve high-quality deduplication with under 1% neural verification cost.
Roofline-guided mixed quantization and kernel co- optimization for efficient large language model inference on arm cpus
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication
SemHash-LLM is a multi-granularity semantic hashing framework that fuses character, token, and document signals via gated fusion and cascaded filtering to achieve high-quality deduplication with under 1% neural verification cost.