6 papers
MQAD: A Large-Scale Question Answering Dataset for Training Music Large Language Models
Zhihao Ouyang, Ju-Chiang Wang, Daiyu Zhang +3
Question-answering (QA) is a natural approach for humans to understand a piece of music audio. However, for machines, accessing a large-scale dataset covering diverse aspects of mu…
PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter
Yaohua Zha, Yanzi Wang, Hang Guo +7
Applying pre-trained models to assist point cloud understanding has recently become a mainstream paradigm in 3D perception. However, existing application strategies are straightfor…
The Study of Jet Formation Mechanism in Fermi Blazars
Shangchun Xie, Zhihao Ouyang, Jingyu Wu +5
The origin of jet launching mainly comes from two mechanisms: the BZ mechanism and the BP mechanism. However, it is in debate which one is dominating in blazars. In this work, we u…
LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling
Yaohua Zha, Naiqi Li, Yanzi Wang +6
The pre-trained point cloud model based on Masked Point Modeling (MPM) has exhibited substantial improvements across various tasks. However, these models heavily rely on the Transf…
MambaIR: A Simple Baseline for Image Restoration with State-Space Model
Hang Guo, Jinmin Li, Tao Dai +3
Recent years have seen significant advancements in image restoration, largely attributed to the development of modern deep neural networks, such as CNNs and Transformers. However,…
ReFIR: Grounding Large Restoration Models with Retrieval Augmentation
Hang Guo, Tao Dai, Zhihao Ouyang +4
Recent advances in diffusion-based Large Restoration Models (LRMs) have significantly improved photo-realistic image restoration by leveraging the internal knowledge embedded withi…