3 papers
cs.CV2025
Window Token Concatenation for Efficient Visual Large Language Models
Yifan Li, Wentao Bao, Botao Ye +4
To effectively reduce the visual tokens in Visual Large Language Models (VLLMs), we propose a novel approach called Window Token Concatenation (WiCo). Specifically, we employ a sli…
cs.CV2024
GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control
Mariam Hassan, Sebastian Stapf, Ahmad Rahimi +17
We present GEM, a Generalizable Ego-vision Multimodal world model that predicts future frames using a reference frame, sparse features, human poses, and ego-trajectories. Hence, ou…
cs.CV2024
No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
Botao Ye, Sifei Liu, Haofei Xu +4
We introduce NoPoSplat, a feed-forward model capable of reconstructing 3D scenes parameterized by 3D Gaussians from \textit{unposed} sparse multi-view images. Our model, trained ex…