What is recorded here?
Added local text-to-text attention within dedicated visual fusion layers, retaining cross-attention-like scaling while narrowing the tested performance gap to full visual-token insertion.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Inherits cross-attention and blockwise attention. Efficiency and accuracy comparisons are configuration-dependent; continuous visual updates do not give unbounded visual memory. Original title uses via Self-Attention, unlike the later index title.
Read the original work
- CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion
- Kyutai scientific publications index
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
Moritz Böhle; Amelie Royer; Juliette Marrie; Edouard Grave; Patrick Pérez
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
CASA: local text self-attention for visual fusion
Added local text-to-text attention within dedicated visual fusion layers, retaining cross-attention-like scaling while narrowing the tested performance gap to full visual-token insertion.
Scientific scope
Inherits cross-attention and blockwise attention. Efficiency and accuracy comparisons are configuration-dependent; continuous visual updates do not give unbounded visual memory. Original title uses via Self-Attention, unlike the later index title.
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
Moritz Böhle; Amelie Royer; Juliette Marrie; Edouard Grave; Patrick Pérez
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.