Imagen de Portada

Dynamic Training-Free Fusion of Subject and Style LoRAs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cao, Qinglong, Chen, Yuntian, Ma, Chao, Yang, Xiaokang
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Symbolic Computation
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs
por: Ouyang, Ziheng, et al.
Publicado: (2025)

Subject or Style: Adaptive and Training-Free Mixture of LoRAs
por: Zhang, Jia-Chen, et al.
Publicado: (2025)

Open-Vocabulary Remote Sensing Image Semantic Segmentation
por: Cao, Qinglong, et al.
Publicado: (2024)

Self-Attention Based Semantic Decomposition in Vector Symbolic Architectures
por: Yeung, Calvin, et al.
Publicado: (2024)

FactorHD: A Hyperdimensional Computing Model for Multi-Object Multi-Class Representation and Factorization
por: Zhou, Yifei, et al.
Publicado: (2025)

Reasoning over the Behaviour of Objects in Video-Clips for Adverb-Type Recognition
por: Seshadri, Amrit Diggavi, et al.
Publicado: (2023)

LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation
por: Shenaj, Donald, et al.
Publicado: (2024)

NePTune: A Neuro-Pythonic Framework for Tunable Compositional Reasoning on Vision-Language
por: Kamali, Danial, et al.
Publicado: (2025)

Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment
por: Okamoto, Lauren, et al.
Publicado: (2024)

Learning Domain Knowledge in Multimodal Large Language Models through Reinforcement Fine-Tuning
por: Cao, Qinglong, et al.
Publicado: (2026)

We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?
por: Qiao, Runqi, et al.
Publicado: (2024)

Vector-Symbolic Architecture for Event-Based Optical Flow
por: You, Hongzhi, et al.
Publicado: (2024)

ParSEL: Parameterized Shape Editing with Language
por: Ganeshan, Aditya, et al.
Publicado: (2024)

Neurosymbolic LoRA: Why and When to Tune Weights vs. Rewrite Prompts
por: Wang, Kevin, et al.
Publicado: (2026)

NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion
por: Chen, Chuheng, et al.
Publicado: (2025)

ORAL: Prompting Your Large-Scale LoRAs via Conditional Recurrent Diffusion
por: Khan, Rana Muhammad Shahroz, et al.
Publicado: (2025)

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs
por: Hu, Zixuan, et al.
Publicado: (2024)

ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs
por: Shah, Viraj, et al.
Publicado: (2023)

Algebraic Representations for Faster Predictions in Convolutional Neural Networks
por: Joyce, Johnny, et al.
Publicado: (2024)

FREE-Switch: Frequency-based Dynamic LoRA Switch for Style Transfer
por: Zheng, Shenghe, et al.
Publicado: (2026)

FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization
por: Zheng, Peng, et al.
Publicado: (2025)

Parameter-Efficient CT Reconstruction via Deep Graph Laplacian Regularization
por: Radhakrishnan, Veera Varuni, et al.
Publicado: (2026)

Large Language Models are Interpretable Learners
por: Wang, Ruochen, et al.
Publicado: (2024)

Graph-based data-driven discovery of interpretable laws governing corona-induced noise and radio interference for high-voltage transmission lines
por: Xu, Hao, et al.
Publicado: (2026)

Hyperion -- A fast, versatile symbolic Gaussian Belief Propagation framework for Continuous-Time SLAM
por: Hug, David, et al.
Publicado: (2024)

A Neurosymbolic Approach to Adaptive Feature Extraction in SLAM
por: Chandio, Yasra, et al.
Publicado: (2024)

Bio-inspired AI: Integrating Biological Complexity into Artificial Intelligence
por: Dehghani, Nima, et al.
Publicado: (2024)

LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning
por: Che, Chang, et al.
Publicado: (2025)

Promoting AI Equity in Science: Generalized Domain Prompt Learning for Accessible VLM Research
por: Cao, Qinglong, et al.
Publicado: (2024)

Relations, Negations, and Numbers: Looking for Logic in Generative Text-to-Image Models
por: Conwell, Colin, et al.
Publicado: (2024)

Spanning the Visual Analogy Space with a Weight Basis of LoRAs
por: Manor, Hila, et al.
Publicado: (2026)

Latent Knowledge-Guided Video Diffusion for Scientific Phenomena Generation from a Single Initial Frame
por: Cao, Qinglong, et al.
Publicado: (2024)

In-Context Meta LoRA Generation
por: Shao, Yihua, et al.
Publicado: (2025)

Amortized Equation Discovery in Hybrid Dynamical Systems
por: Liu, Yongtuo, et al.
Publicado: (2024)

Formal Verification of Neural Certificates Done Dynamically
por: Henzinger, Thomas A., et al.
Publicado: (2025)

A New Hybrid Intelligent Approach for Multimodal Detection of Suspected Disinformation on TikTok
por: Guerrero-Sosa, Jared D. T., et al.
Publicado: (2025)

Block-wise LoRA: Revisiting Fine-grained LoRA for Effective Personalization and Stylization in Text-to-Image Generation
por: Li, Likun, et al.
Publicado: (2024)

LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints
por: Xu, Weidi, et al.
Publicado: (2023)

Evolutionary Negative Module Pruning for Better LoRA Merging
por: Cao, Anda, et al.
Publicado: (2026)

VITA: Versatile Time Representation Learning for Temporal Hyper-Relational Knowledge Graphs
por: Un, ChongIn, et al.
Publicado: (2025)