Papers/2611.17340
🧪 Test?View on arXiv

LoRAWeaver: Directional Adapter Routing in LoRA Representation Space

Not specified in the provided content

fine-tuningadapter routingrepresentation learning
2611.17340
Builder Relevance
80%
19h ago

Abstract

This paper presents a training-free method for selecting LoRA adapters by aligning query representations with task prototypes using cosine similarity.

Reality Card

Core Claim

The proposed method outperforms training-free baselines in cross-task settings and approaches the performance of a trained retrieval encoder without requiring a router.

Method / Result

The method was tested on a 48-task FLAN-v2 benchmark and showed improved performance in dynamic settings.

Limitations

The paper does not specify the authors, which may limit reproducibility and further validation of the results.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers