Occ-VLM occupancy grounding enhances indoor scene VLM

Arxiv CS.CV (computer vision)

Occ-VLM integrates 3D occupancy information into vision-language models for improved indoor scene understanding. The model targets embodied AI and robotic vision applications.

occ-vlm

See 10 more sources

Language-Instructed Vision Embeddings for Controllable and Generalizable Perception3 days agoChengzhi Mao, Xudong Lin, Wen-Sheng Chu

GLARE: A Natural Language Interface for Querying Global Explanations3 days agoBhavan Vasu, Rajesh Mangannavar

See-and-Reach: Precise Vision-Language Navigation for UAVs within the Field of View3 days agoFanfu Xue, En Yu, Yantian Shen, Zhikun Hu, Hongjun Wang, Yang Yang, Xindi Wang, Jiande Sun

Rethinking Air-Ground Collaboration: A Progressive Cross-Task Benchmark and Socialized Learning Framework4 days agoZhoupeng Guo, Yunqi Zhu, Zhihe Fan, Xinjie Yao, Ruipu Zhao, Boan Tao, Yiming Sun, Zhen Wang, Pengfei Zhu

Aerial-ground LiDAR place recognition with patch-level self-supervised learning and expanded reciprocal re-ranking4 days agoYandi Yang, Xianghong Zou, Jianping Li, Haofeng Xie, Saurav Uprety, Hongzhou Yang, Naser El-Sheimy

GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning5 days agoHaoyu Wang, Guoqing Ma, Zeyu Zhang, Yandong Guo, Boxin Shi, Hao Tang

Disagreement-Based Cross-Model Routing for Implicit Video Question Answering6 days agoDurga Sandeep Saluru

ScoutVLA: UAV-Centric Active Perception via a Dual-Expert VLA Model for Open-World Embodied Question Answering6 days agoWenhao Lu, Zhengqiu Zhu, Xiaofeng Wang, Xiaoran Zhang, Yatai Ji, Yong Zhao, Yue Hu, Yingzhen Nie, Jinlong Zhu, Zheng Zhu

FUSE: Quantifying Uncertainty in Vision-Language Models by Bayesian Fusing Epistemic and Aleatoric Uncertainty6 days agoHarry Zhang, Luca Carlone

X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining6 days agoXirui Kang, Yanpei Shi, Lucy Liang, Roy Gan, Dongxiu Liu, Pushi Zhang, Danpeng Chen, Xiaoyi Qin, Yinan Zheng, Jinliang Zheng, Hao Wang, Xianyuan Zhan, Hang Su

Arxiv CS.CV (computer vision)·Jianing LiZhou FangYijiang LiuLi Du

Jun 19, 4:00 AM