PoisonLoRA demonstrates ~100% attack success rates for stealthy LoRA poisoning via concept hijacking and task injection on real platforms, with robustness to base model transfer and multiple remixes.
Lora-composer: Leveraging low-rank adaptation for multi-concept customization in training-free diffusion models
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
LivingSwap is the first video reference-guided face swapping model that uses keyframe conditioning and temporal stitching to preserve source video realism with high fidelity across long sequences.
ChangeBridge introduces a drift-asynchronous diffusion bridge with composed initialization, pixel-wise drift maps, and drift-aware denoising to produce spatially and temporally coherent post-event remote sensing images.
CCDM uses attribute-decoupled LoRA with relevance-guided aggregation and controllable regional context synthesis to support incremental concept customization in diffusion models while mitigating catastrophic forgetting and concept neglect.
NP-LoRA fuses subject and style LoRAs via null-space projection of the content update onto the orthogonal complement of the style subspace, with a soft variant controlled by one parameter.
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.
An overview revisits LoRA variants by categorizing advances in architectural design, efficient optimization, and applications while linking them to classical signal processing tools for principled fine-tuning.
citing papers explorer
-
Customization under Fire: Plugin Poisoning in Text-to-Image Ecosystem
PoisonLoRA demonstrates ~100% attack success rates for stealthy LoRA poisoning via concept hijacking and task injection on real platforms, with robustness to base model transfer and multiple remixes.
-
Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality
LivingSwap is the first video reference-guided face swapping model that uses keyframe conditioning and temporal stitching to preserve source video realism with high fidelity across long sequences.
-
ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Sensing
ChangeBridge introduces a drift-asynchronous diffusion bridge with composed initialization, pixel-wise drift maps, and drift-aware denoising to produce spatially and temporally coherent post-event remote sensing images.
-
Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization
CCDM uses attribute-decoupled LoRA with relevance-guided aggregation and controllable regional context synthesis to support incremental concept customization in diffusion models while mitigating catastrophic forgetting and concept neglect.
-
NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion
NP-LoRA fuses subject and style LoRAs via null-space projection of the content update onto the orthogonal complement of the style subspace, with a soft variant controlled by one parameter.
-
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.
-
Low-Rank Adaptation Redux for Large Models
An overview revisits LoRA variants by categorizing advances in architectural design, efficient optimization, and applications while linking them to classical signal processing tools for principled fine-tuning.