Spectral Tempering derives an adaptive scaling factor γ(k) from the embedding eigenspectrum via local SNR analysis and knee-point normalization to achieve near-optimal compression without training or validation.
In: Findings of the Association for Computational Linguistics: EMNLP 2020
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Byte-level simulations show subword tokenization improves LLM training mainly via increased throughput and boundary priors.
SPEAR applies multi-agent systems with planning, execution, and repair agents using negotiation protocols to smart contract auditing and compares it empirically to centralized and pipeline approaches.
citing papers explorer
-
Spectral Tempering for Embedding Compression in Dense Passage Retrieval
Spectral Tempering derives an adaptive scaling factor γ(k) from the embedding eigenspectrum via local SNR analysis and knee-point normalization to achieve near-optimal compression without training or validation.
-
Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation
Byte-level simulations show subword tokenization improves LLM training mainly via increased throughput and boundary priors.
-
SPEAR: An Engineering Case Study of Multi-Agent Coordination for Smart Contract Auditing
SPEAR applies multi-agent systems with planning, execution, and repair agents using negotiation protocols to smart contract auditing and compares it empirically to centralized and pipeline approaches.