NeurIPS 2025 "parameter-efficient fine-tuning" Papers
16 papers found
Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples
Shiva Sreeram, Alaa Maalouf, Pratyusha Sharma et al.
CrossSpectra: Exploiting Cross-Layer Smoothness for Parameter-Efficient Fine-Tuning
Yifei Zhang, Hao Zhu, Junhao Dong et al.
Distribution-Aligned Decoding for Efficient LLM Task Adaptation
Senkang Hu, Xudong Han, Jinqi Jiang et al.
Don’t Forget the Enjoin: FocalLoRA for Instruction Hierarchical Alignment in Large Language Models
Zitong Shi, Guancheng Wan, Haixin Wang et al.
F-Adapter: Frequency-Adaptive Parameter-Efficient Fine-Tuning in Scientific Machine Learning
Hangwei Zhang, Chun Kang, Yan Wang et al.
Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads
Zhoutong Wu, Yuan Zhang, Yiming Dong et al.
Linearization Explains Fine-Tuning in Large Language Models
Zahra Rahimi Afzal, Tara Esmaeilbeig, Mojtaba Soltanalian et al.
Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation
Weibin Liao, Tianlong Wang, Yinghao Zhu et al.
Multi-Token Prediction Needs Registers
Anastasios Gerontopoulos, Spyridon Gidaris, Nikos Komodakis
PoLAR: Polar-Decomposed Low-Rank Adapter Representation
Kai Lion, Liang Zhang, Bingcong Li et al.
Quantifying Elicitation of Latent Capabilities in Language Models
Elizabeth Donoway, Hailey Joren, Arushi Somani et al.
Ravan: Multi-Head Low-Rank Adaptation for Federated Fine-Tuning
Arian Raje, Baris Askin, Divyansh Jhunjhunwala et al.
S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning
Hanqing Zeng, Yinglong Xia, Zhuokai Zhao et al.
Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning
Haomiao Qiu, Miao Zhang, Ziyue Qiao et al.
Turning the Tables: Enabling Backward Transfer via Causal-Aware LoRA in Continual Learning
Chaoyang Li, Runze Ye, Jianyang Qin et al.
Uni-LoRA: One Vector is All You Need
Kaiyang Li, Shaobo Han, Qing Su et al.