FRAME adds a learnable fractional-Fourier order per expert in a MoE-LoRA setup so that low-rank updates are placed in the domain where they are most compact, yielding gains over fixed-domain baselines on LLaMA-3.1-8B and Qwen2.5-7B.
arXiv preprint arXiv:2505.12532 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Adapting image editing foundation models via LoRA with multi-reference conditioning achieves state-of-the-art CT metal artifact reduction using two orders of magnitude less paired training data than prior methods.
citing papers explorer
-
FRAME: Learning the Adaptation Domain with a Mixture of Fractional-Fourier Experts
FRAME adds a learnable fractional-Fourier order per expert in a MoE-LoRA setup so that low-rank updates are placed in the domain where they are most compact, yielding gains over fixed-domain baselines on LLaMA-3.1-8B and Qwen2.5-7B.
-
Leveraging Image Editing Foundation Models for Data-Efficient CT Metal Artifact Reduction
Adapting image editing foundation models via LoRA with multi-reference conditioning achieves state-of-the-art CT metal artifact reduction using two orders of magnitude less paired training data than prior methods.