BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Modelsby Yupeng Chang, Yi…
DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalizationby Xin Sun, Liang Wang, Qiang Liu, Shu Wu,…
LoRA-Pro: Are Low-Rank Adapters Properly Optimized?by Zhengbo Wang, Jian Liang, Ran He, Zilei Wang, Tieniu…
Rapid Switching and Multi-Adapter Fusion via Sparse High Rank Adaptersby Kartikeya Bhardwaj, Nilesh Prasad Pandey,…
CIC-BART-SSA: Controllable Image Captioning with Structured Semantic Augmentationby Kalliopi Basioti, Mohamed A. Abdelsalam, Federico Fancellu,…
Unraveling the Truth: Do VLMs really Understand Charts? A Deep Dive into Consistency and Robustnessby…
On Large Language Model Continual Unlearningby Chongyang Gao, Lixu Wang, Kaize Ding, Chenkai Weng, Xiao…
Hydra: Bidirectional State Space Models Through Generalized Matrix Mixersby Sukjun Hwang, Aakash Lahoti, Tri Dao,…
Automatic Pruning of Fine-tuning Datasets for Transformer-based Language Modelsby Mohammadreza Tayaranian, Seyyed Hasan Mozafari, Brett…
ROSA: Random Subspace Adaptation for Efficient Fine-Tuningby Marawan Gamal Abdel Hameed, Aristides Milios, Siva Reddy,…