arXiv (All)
open access
Complex-valued Phase-Coherent Transformers
Complex-valued Transformers have inherited softmax attention over the raw complex inner product. Outside natively complex domains this standard form stays near chance, and no complex attention had been shown to correct it. We show that the match must be a scaled cosine score: L2-normalise queries an
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Identifying Crucial Attention Heads for Multilingual Language Models: Retrieval and Retrieval-Transition Heads#1070770
- Putting Registers to Work: Task Registers for Token Pruning in Vision Transformers#444674
- Optimizer-dependent training dynamics converge to the same one-third optimal data scaling#1142056
- Technical Manual for a Toolkit for Measuring Contextual Individuation in Transformer Language Models#972265
- Multi-Head Self Attention is a Parameter Identification Mechanism#821187
Record · ID 1037098
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive