2025 Poster "model merging" Papers
13 papers found
Accurate and Efficient Low-Rank Model Merging in Core Space
Aniello Panariello, Daniel Marczak, Simone Magistri et al.
NeurIPS 2025posterarXiv:2509.17786
3
citations
CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving
Huitong Yang, Zhuoxiao Chen, Fengyi Zhang et al.
NeurIPS 2025posterarXiv:2505.16524
Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity
Enneng Yang, Anke Tang, Li Shen et al.
NeurIPS 2025poster
DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic
Munish Monga, Vishal Chudasama, Pankaj Wasnik et al.
ICCV 2025posterarXiv:2506.21260
FREE-Merging: Fourier Transform for Efficient Model Merging
Shenghe Zheng, Hongzhi Wang
ICCV 2025posterarXiv:2411.16815
3
citations
Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs
Rui Dai, Sile Hu, Xu Shen et al.
ICLR 2025posterarXiv:2504.10902
6
citations
Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering
Ziyu Zhao, tao shen, Didi Zhu et al.
ICLR 2025posterarXiv:2409.16167
33
citations
Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
Jinluan Yang, Dingnan Jin, Anke Tang et al.
NeurIPS 2025posterarXiv:2502.06876
13
citations
Multimodal Lego: Model Merging and Fine-Tuning Across Topologies and Modalities in Biomedicine
Konstantin Hemker, Nikola Simidjievski, Mateja Jamnik
ICLR 2025posterarXiv:2405.19950
2
citations
PLeaS - Merging Models with Permutations and Least Squares
Anshul Nasery, Jonathan Hayase, Pang Wei Koh et al.
CVPR 2025posterarXiv:2407.02447
10
citations
Task Vector Quantization for Memory-Efficient Model Merging
Youngeun Kim, Seunghwan Lee, Aecheon Jung et al.
ICCV 2025posterarXiv:2503.06921
3
citations
Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration
Wenju Sun, Qingyong Li, Wen Wang et al.
NeurIPS 2025posterarXiv:2505.23859
2
citations
Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning
Haomiao Qiu, Miao Zhang, Ziyue Qiao et al.
NeurIPS 2025posterarXiv:2505.22389