Copertina

Ortho-Hydra: Orthogonalized Experts for DiT LoRA

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Ji, Seunghyun
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Rethinking Inter-LoRA Orthogonality in Adapter Merging: Insights from Orthogonal Monte Carlo Dropout
di: Zhang, Andi, et al.
Pubblicazione: (2025)

Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning
di: Yang, Minghao, et al.
Pubblicazione: (2025)

DyME: Dynamic Multi-Concept Erasure in Diffusion Models with Bi-Level Orthogonal LoRA Adaptation
di: Liu, Jiaqi, et al.
Pubblicazione: (2025)

Shared LoRA Subspaces for almost Strict Continual Learning
di: Kaushik, Prakhar, et al.
Pubblicazione: (2026)

Vertical LoRA: Dense Expectation-Maximization Interpretation of Transformers
di: Fu, Zhuolin
Pubblicazione: (2024)

Dual-Space Augmented Intrinsic-LoRA for Wind Turbine Segmentation
di: Singhal, Shubh, et al.
Pubblicazione: (2024)

Multi-LoRA Composition for Image Generation
di: Zhong, Ming, et al.
Pubblicazione: (2024)

Label-Free Cross-Task LoRA Merging with Null-Space Compression
di: Lee, Wonyoung, et al.
Pubblicazione: (2026)

Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA
di: Smith, James Seale, et al.
Pubblicazione: (2023)

FM-LoRA: Factorized Low-Rank Meta-Prompting for Continual Learning
di: Yu, Xiaobing, et al.
Pubblicazione: (2025)

LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual Learning
di: Liu, Xuan, et al.
Pubblicazione: (2025)

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

Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy
di: Jeong, Wooseong, et al.
Pubblicazione: (2026)

Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation
di: Shenaj, Donald, et al.
Pubblicazione: (2026)

DAC-LoRA: Dynamic Adversarial Curriculum for Efficient and Robust Few-Shot Adaptation
di: Umrajkar, Ved
Pubblicazione: (2025)

Simple Drop-in LoRA Conditioning on Attention Layers Will Improve Your Diffusion Model
di: Choi, Joo Young, et al.
Pubblicazione: (2024)

EMLoC: Emulator-based Memory-efficient Fine-tuning with LoRA Correction
di: Lin, Hsi-Che, et al.
Pubblicazione: (2025)

CoLoRSMamba: Conditional LoRA-Steered Mamba for Supervised Multimodal Violence Detection
di: Senadeera, Damith Chamalke, et al.
Pubblicazione: (2026)

MapReduce LoRA: Advancing the Pareto Front in Multi-Preference Optimization for Generative Models
di: Chen, Chieh-Yun, et al.
Pubblicazione: (2025)

DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing
di: Zhou, Zihan, et al.
Pubblicazione: (2025)

Contrastive Regularization over LoRA for Multimodal Biomedical Image Incremental Learning
di: Zhang, Haojie, et al.
Pubblicazione: (2025)

How LoRA Remembers? A Parametric Memory Law for LLM Finetuning
di: Xu, Ziwen, et al.
Pubblicazione: (2026)

Frugal Federated Learning for Violence Detection: A Comparison of LoRA-Tuned VLMs and Personalized CNNs
di: Thuau, Sébastien, et al.
Pubblicazione: (2025)

DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking
di: Haridas, Akash, et al.
Pubblicazione: (2026)

Shiva-DiT: Residual-Based Differentiable Top-$k$ Selection for Efficient Diffusion Transformers
di: Zhang, Jiaji, et al.
Pubblicazione: (2026)

ZigMa: A DiT-style Zigzag Mamba Diffusion Model
di: Hu, Vincent Tao, et al.
Pubblicazione: (2024)

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging
di: Zheng, Shenghe, et al.
Pubblicazione: (2025)

OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models
di: Aliev, Ali, et al.
Pubblicazione: (2026)

RDP LoRA: Geometry-Driven Identification for Parameter-Efficient Adaptation in Large Language Models
di: Çelebi, Yusuf, et al.
Pubblicazione: (2026)

Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising
di: Fang, Gongfan, et al.
Pubblicazione: (2024)

LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement
di: Bian, Jieming, et al.
Pubblicazione: (2024)

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

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

Advancing AI-Powered Medical Image Synthesis: Insights from MedVQA-GI Challenge Using CLIP, Fine-Tuned Stable Diffusion, and Dream-Booth + LoRA
di: Peter, Ojonugwa Oluwafemi Ejiga, et al.
Pubblicazione: (2025)

OP-LoRA: The Blessing of Dimensionality
di: Teterwak, Piotr, et al.
Pubblicazione: (2024)

Empower Vision Applications with LoRA LMM
di: Mi, Liang, et al.
Pubblicazione: (2024)

Text Slider: Efficient and Plug-and-Play Continuous Concept Control for Image/Video Synthesis via LoRA Adapters
di: Chiu, Pin-Yen, et al.
Pubblicazione: (2025)

Customize Segment Anything Model for Multi-Modal Semantic Segmentation with Mixture of LoRA Experts
di: Zhu, Chenyang, et al.
Pubblicazione: (2024)

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

Selective LoRA for Visual Tokens and Attention Heads
di: Luo, Tiange, et al.
Pubblicazione: (2025)