Training-free Riemannian fusion merges orthogonal style and concept adapters for diffusion models via geodesic approximation on GS matrices plus spectra restoration.
K-lora: Unlocking training-free fusion of any subject and style loras
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
verdicts
UNVERDICTED 7representative citing papers
LoRA-Mixer routes modular LoRA experts into attention projection matrices with an adaptive Routing Specialization Loss to improve multi-task performance while using fewer trainable parameters than prior LoRA-MoE methods.
Disco-LoRA proposes disentangling content-style and content-motion via dual-LoRA with statistical regularization to enable multi-concept video customization.
AD-Relight adapts diffusion-based relighting models at test time via a multi-stage framework to relight custom ad banners so they match scene illumination, outperforming warping and prior relighting approaches.
FREE-Switch dynamically switches LoRA adapters using frequency importance per diffusion step and adds semantic alignment to reduce content drift when merging specialized image generators.
CraftGraffiti applies LoRA-tuned diffusion transformers followed by identity-augmented self-attention and CLIP-guided pose extension to generate graffiti while preserving facial features.
ContextForge recycles context in long-horizon LLM tasks via query generation, memory retrieval, and synthesis, yielding reduced token use and improved consistency on a 15-turn healthcare benchmark while preserving accuracy.
citing papers explorer
-
OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models
Training-free Riemannian fusion merges orthogonal style and concept adapters for diffusion models via geodesic approximation on GS matrices plus spectra restoration.
-
LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing
LoRA-Mixer routes modular LoRA experts into attention projection matrices with an adaptive Routing Specialization Loss to improve multi-task performance while using fewer trainable parameters than prior LoRA-MoE methods.
-
Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customization
Disco-LoRA proposes disentangling content-style and content-motion via dual-LoRA with statistical regularization to enable multi-concept video customization.
-
AD-Relight: Training-Free Banner Relighting via Illumination Translation with Diffusion Priors
AD-Relight adapts diffusion-based relighting models at test time via a multi-stage framework to relight custom ad banners so they match scene illumination, outperforming warping and prior relighting approaches.
-
FREE-Switch: Frequency-based Dynamic LoRA Switch for Style Transfer
FREE-Switch dynamically switches LoRA adapters using frequency importance per diffusion step and adds semantic alignment to reduce content drift when merging specialized image generators.
-
CraftGraffiti: Exploring Human Identity with Custom Graffiti Art via Facial-Preserving Diffusion Models
CraftGraffiti applies LoRA-tuned diffusion transformers followed by identity-augmented self-attention and CLIP-guided pose extension to generate graffiti while preserving facial features.
-
Context Recycling for Long-Horizon LLM Inference
ContextForge recycles context in long-horizon LLM tasks via query generation, memory retrieval, and synthesis, yielding reduced token use and improved consistency on a 15-turn healthcare benchmark while preserving accuracy.