11 papers
A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models
Duo Li, Zuhao Yang, Xiaoqin Zhang +2
Discrete diffusion-based multimodal large language models (dMLLMs) have emerged as a promising alternative to autoregressive MLLMs thanks to their advantages in parallel decoding a…
STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understanding
Wenhao Li, Xueying Jiang, Gongjie Zhang +3
4D point cloud videos capture rich spatial and temporal dynamics of scenes which possess unique values in various 4D understanding tasks. However, most existing methods work in the…
L3DR: 3D-aware LiDAR Diffusion and Rectification
Quan Liu, Xiaoqin Zhang, Ling Shao +1
Range-view (RV) based LiDAR diffusion has recently made huge strides towards 2D photo-realism. However, it neglects 3D geometry realism and often generates various RV artifacts suc…
Direction-aware 3D Large Multimodal Models
Quan Liu, Weihao Xuan, Junjue Wang +3
3D large multimodal models (3D LMMs) rely heavily on ego poses for enabling directional question-answering and spatial reasoning. However, most existing point cloud benchmarks cont…
MuSASplat: Efficient Sparse-View 3D Gaussian Splats via Lightweight Multi-Scale Adaptation
Muyu Xu, Fangneng Zhan, Xiaoqin Zhang +2
Sparse-view 3D Gaussian splatting seeks to render high-quality novel views of 3D scenes from a limited set of input images. While recent pose-free feed-forward methods leveraging p…
ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance
Duo Li, Zuhao Yang, Xiaoqin Zhang +2
Visual token pruning aims to compress and prune redundant visual tokens which play a critical role in efficient inference with large vision-language models (LVLMs). However, most e…