VL-Group

university

https://vl-group.github.io

AI & ML interests

multimodal learning, MLLM

vl-group's activity

xiaosu-zhu

authored 2 papers 4 months ago

RoScenes: A Large-scale Multi-view 3D Dataset for Roadside Perception

Paper • 2405.09883 • Published May 16, 2024 • 1

Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression

Paper • 2203.10897 • Published Mar 21, 2022

PommesPeter

updated a model 5 months ago

vl-group/McQuic-VAE-Encoder

Updated Aug 12, 2024