What is recorded here?
Trimmed small task-vector updates, elected a parameter-wise sign and merged only aligned updates to reduce empirical interference between models fine-tuned from a common base.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Inherits task vectors and model merging. Common parameter alignment/base assumptions matter; sign agreement does not prove universal multitask retention, optimum loss or safe behavior. No retraining refers to the merge, not the source fine-tuning or validation search.
Read the original work
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
Prateek Yadav; Derek Tam; Leshem Choshen; Colin Raffel; Mohit Bansal
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
TIES-Merging: trimming task deltas and resolving sign conflicts
Trimmed small task-vector updates, elected a parameter-wise sign and merged only aligned updates to reduce empirical interference between models fine-tuned from a common base.
Scientific scope
Inherits task vectors and model merging. Common parameter alignment/base assumptions matter; sign agreement does not prove universal multitask retention, optimum loss or safe behavior. No retraining refers to the merge, not the source fine-tuning or validation search.
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
Prateek Yadav; Derek Tam; Leshem Choshen; Colin Raffel; Mohit Bansal
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.