GitHub

Efficient Visual Representation Learning with Bidirectional State Space Model

May. 2nd, 2024: Vision Mamba (Vim) is accepted by ICML2024. 🎉 Conference page can be found here. Feb. 10th, 2024: We update Vim-tiny/small weights and training scripts. By placing the class token at ...
IEEE

Rapid-Mapping: LiDAR-Visual Implicit Neural Representations for Real-Time Dense Mapping

Abstract: Real-time dense mapping with high-fidelity textures in large-scale environments is such a challenge in robots, digital twins, and AR/VR applications. Neural Radiance Field (NeRF) has ...
IEEE

Study on Target Tracking Commands of UAV PTZ Visual Systems Based on the Acquired Image After Pattern Recognition

Abstract: This paper aims at investigating servo commands of the UAV PTZ vision system for target tracking. The comprehensive analyses of parameters influencing target tracking are developed in the ...
GitHub

Don’t Blind Your VLA: Aligning Visual Representations for OOD Generalization

To address the degradation of visual-language (VL) representations during VLA supervised fine-tuning (SFT), we introduce Visual Representation Alignment. During SFT, we pull a VLA’s visual tokens ...