paper-with-me

Papers

Meta-LoRA: Meta-Learning LoRA Components for Domain-Aware ID Personalization

2025-03-28 · Barış Batuhan Topal, Umut Özyurt, Zafer Doğan Budak, Ramazan Gokberk Cinbis

Recent advancements in text-to-image generative models, particularly latent diffusion models (LDMs), have demonstrated remarkable capabilities in synthesizing high-quality images from textual prompts. However, achieving identity personalization-ensuring that a model consistently generates subject-specific outputs from limited reference images-remains a fundamental challenge. To address this, we introduce Meta-Low-Rank Adaptation (Meta-LoRA), a novel framework that leverages meta-learning to encode domain-specific priors into LoRA-based identity personalization. Our method introduces a structured three-layer LoRA architecture that separates identity-agnostic knowledge from identity-specific adaptation. In the first stage, the LoRA Meta-Down layers are meta-trained across multiple subjects, learning a shared manifold that captures general identity-related features. In the second stage, only the LoRA-Mid and LoRA-Up layers are optimized to specialize on a given subject, significantly reducing adaptation time while improving identity fidelity. To evaluate our approach, we introduce Meta-PHD, a new benchmark dataset for identity personalization, and compare Meta-LoRA against state-of-the-art methods. Our results demonstrate that Meta-LoRA achieves superior identity retention, computational efficiency, and adaptability across diverse identity conditions. The code, model weights, and dataset will be released publicly upon acceptance.

📄 PDF Abstract BibTeX arXiv:2503.22352

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyMeta-Learning

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs

2025-01-01 · CVPR 2025 1 · Zixuan Hu, Yongxian Wei, Li Shen, Chun Yuan 외

Large Language Models (LLMs) such as ChatGPT demonstrate strong few-shot adaptability without requiring fine-tuning, positioning them ideal for data-limited and real-time applications. However, this adaptability has …

In-Context LearningMeta-Learning

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs

2024-12-03 · Zixuan Hu, Yongxian Wei, Li Shen, Chun Yuan 외

Large Language Models (LLMs) such as ChatGPT demonstrate strong few-shot adaptability without requiring fine-tuning, positioning them ideal for data-limited and real-time applications. However, this adaptability has not …

In-Context LearningMeta-Learning

MetaGFN: Exploring Distant Modes with Adapted Metadynamics for Continuous GFlowNets

2024-08-28 · Dominic Phillips, Flaviu Cipcigan

Generative Flow Networks (GFlowNets) are a class of generative models that sample objects in proportion to a specified reward function through a learned policy. They can be trained either on-policy or off-policy, needing…

First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs

2023-07-05 · Ben Norman, Jeff Clune

Standard reinforcement learning (RL) agents never intelligently explore like a human (i.e. taking into account complex domain priors and adapting quickly based on previous exploration). Across episodes, RL agents struggl…

Meta-LearningReinforcement Learning (RL)

Offline Meta-Reinforcement Learning with Flow-Based Task Inference and Adaptive Correction of Feature Overgeneralization

2026-01-12 · Min Wang, Xin Li, Mingzhong Wang, Hasnaa Bennis arxiv

Offline meta-reinforcement learning (OMRL) combines the strengths of learning from diverse datasets in offline RL with the adaptability to new tasks of meta-RL, promising safe and efficient knowledge acquisition by RL ag…

Reinforcement LearningOffline RL