What is recorded here?
Computed attention through a learned difference of two softmax maps, seeking to suppress irrelevant context while improving retrieval and language-model behavior in reported experiments.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Noise cancellation is an architectural intuition and empirical finding, not universal elimination of hallucinations or attention error. Subtractive attention changes the architecture and is not exact dense-attention acceleration.
Read the original work
- Differential Transformer
- Ye et al.: Differential attention for context-noise suppression — official project source
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Tianzhu Ye; Li Dong; Yuqing Xia; Yutao Sun; Yi Zhu; Gao Huang; Furu Wei
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
Ye et al.: Differential attention for context-noise suppression
Computed attention through a learned difference of two softmax maps, seeking to suppress irrelevant context while improving retrieval and language-model behavior in reported experiments.
Scientific scope
Noise cancellation is an architectural intuition and empirical finding, not universal elimination of hallucinations or attention error. Subtractive attention changes the architecture and is not exact dense-attention acceleration.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Tianzhu Ye; Li Dong; Yuqing Xia; Yutao Sun; Yi Zhu; Gao Huang; Furu Wei
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.