Publications (7)
Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Prediction
Chi Yan, Dan Xu
The 3D occupancy prediction task has witnessed remarkable progress in recent years, playing a crucial role in vision-based autonomous driving systems. While traditional methods are…
VITA-E: Natural Embodied Interaction with Concurrent Seeing, Hearing, Speaking, and Acting
Xiaoyu Liu, Chaoyou Fu, Chi Yan +15
Current Vision-Language-Action (VLA) models are often constrained by a rigid, static interaction paradigm, which lacks the ability to see, hear, speak, and act concurrently as well…
AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations
Junli Liu, Qizhi Chen, Zhigang Wang +6
Visual grounding (VG) aims to localize target objects in an image based on natural language descriptions. In this paper, we propose AerialVG, a new task focusing on visual groundin…
Implicit Event-RGBD Neural SLAM
Delin Qu, Chi Yan, Dong Wang +4
Implicit neural SLAM has achieved remarkable progress recently. Nevertheless, existing methods face significant challenges in non-ideal scenarios, such as motion blur or lighting v…
GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting
Chi Yan, Delin Qu, Dan Xu +4
In this paper, we introduce \textbf{GS-SLAM} that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping (SLAM) system. It facilitates a better bala…
Sensitivity of the Geomagnetic Octupole to a Stably Stratified Layer in the Earth's Core
Chi Yan, Sabine Stanley
Current "Earth-like" numerical dynamo simulations are able to reproduce many characteristics of the observed geomagnetic field. One notable exception is the geomagnetic octupolar c…