Nonlinear LoRA

LoRA: Low-Rank Adaptation

Follow this topic Ask about this topic

Latest papers

10 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Diffu-LoRA: A Novel Low-Rank Adaptation for Personalized Diffusion Models
Sep 24, 2026Tianjing Li, Wei ZhuNonlinear LoRA Diffusion Model Adaptation
Zhangjiang Lab of Artificial Intelligence, Shanghai, China
Nonlinearity-Aware LoRA: Structured Gate Adaptation under Low-Rank Constraints
Jun 30, 2026Shuai Yuan, Sudong Cai, Bingzhi Chen +4LLM Fine-Tuning Low-Rank Adaptation
1Beijing Institute of Technology, Zhuhai · 2The Hong Kong Polytechnic University · 3The University of Osaka +1
Clinically Structured Rank-Gated LoRA for Cross-Benchmark Medical Question Answering
Jun 30, 2026Hao Gong, Ruilin Gong, Yining HuangNonlinear LoRA Low-Rank Adaptation
University of Chinese Academy of Sciences · Henan University of Technology · Meta Emergence Laboratory
Parameter-Efficient Fine-Tuning with Learnable Rank
Jun 3, 2026Arpit Garg, Simon Lucey, Hemanth SaratchandranNonlinear LoRA Low-Rank Adaptation
Australian Institute for Machine Learning Adelaide University
MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning
May 8, 2026Ionut-Vlad Modoranu, Mher Safaryan, Dan AlistarhNonlinear LoRA LLM Fine-Tuning
Institute of Science and Technology Austria (ISTA). · Lancaster University, UK · ISTA
Polynomial Expansion Rank Adaptation: Enhancing Low-Rank Fine-Tuning with High-Order Interactions
Apr 12, 2026Wenhao Zhang, Lin Mu, Li Ni +2Nonlinear LoRA LLM Fine-Tuning
Anhui University · University of Science and Technology of China
FAAR: Efficient Frequency-Aware Multi-Task Fine-Tuning via Automatic Rank Selection
Mar 20, 2026Maxime Fontana, Michael Spratling, Miaojing ShiNonlinear LoRA Parameter-Efficient Fine-Tuning
King’s College London London, UK · University of Luxembourg Esch-sur-Alzette, Luxembourg · Tongji University Shanghai, China
Adaptive Capacity Allocation for Vision Language Action Fine-tuning
Mar 8, 2026Donghoon Kim, Minji Bae, Unghui Nam +4VLA Model Training Nonlinear LoRA
Department of Electrical and Computer Engineering, Seoul National University, Seoul 08826, Republic of Korea · Department of Computer Science and Engineering, Sungkyunkwan University, Suwon 16419, Republic of Korea
CeRA: Breaking the Linear Ceiling of Low-Rank Adaptation with Non-linearity Retained at Inference
Feb 26, 2026Hung-Hsuan ChenNonlinear LoRA Adapter Tuning
Computer Science and Information Engineering National Central University Taoyuan, Taiwan
Nonlinearity as Rank: Generative Low-Rank Adapter with Radial Basis Functions
Feb 5, 2026Yihao Ouyang, Shiwei Li, Haozhao Wang +5Nonlinear LoRA Low-Rank Adaptation
Huazhong University of Science and Technology, Wuhan, China

Sep 24, 2026J/K move · Enter open · S save

Diffu-LoRA: A Novel Low-Rank Adaptation for Personalized Diffusion Models

Tianjing Li, Wei Zhu

Zhangjiang Lab of Artificial Intelligence, Shanghai, China

Nonlinear LoRA Diffusion Model Adaptation Diffusion Model Fine-Tuning T2I Generation Low-Rank Adaptation

Open paper AskPDF arXiv

Personalizing text-to-image diffusion models from a few reference images requires preserving subject identity while following prompts that describe new contexts. Full-model fine-tuning is parameter-intensive, whereas low-rank adaptation (LoRA) reduces the number of trainable parameters but leaves open how adaptation capacity should be distributed across layers. We introduce Diffu-LoRA, a parameter-efficient method that learns this allocation through gated low-rank adaptation. Diffu-LoRA inserts trainable low-rank components into the linear layers of Transformer blocks and assigns a learnable gate to each component. Bilevel optimization updates the adaptation weights and gate parameters on separate data splits, while progressive pruning removes components with the lowest gate values to meet a prescribed rank budget. This procedure allocates adaptation capacity nonuniformly across layers while keeping the pretrained backbone frozen. Experiments with Stable Diffusion on subjects from DreamBooth and additional collected datasets show improved overall subject fidelity and prompt alignment relative to the evaluated fine-tuning baselines. Ablation studies examine the contributions of bilevel optimization, progressive pruning, and adapter placement. These results support learned rank allocation as a practical approach to parameter-efficient diffusion model personalization.