Zobrazeno 1 - 10
of 10 341
pro vyhledávání: '"Zhaoliang An"'
In this work, we provide a systematic analysis of how large language models (LLMs) contribute to solving planning problems. In particular, we examine how LLMs perform when they are used as problem solver, solution verifier, and heuristic guidance to
Externí odkaz:
http://arxiv.org/abs/2412.09666
Cooperative perception has attracted wide attention given its capability to leverage shared information across connected automated vehicles (CAVs) and smart infrastructures to address sensing occlusion and range limitation issues. However, existing r
Externí odkaz:
http://arxiv.org/abs/2412.06142
Autor:
Zhou, Zewei, Xiang, Hao, Zheng, Zhaoliang, Zhao, Seth Z., Lei, Mingyue, Zhang, Yun, Cai, Tianhui, Liu, Xinyi, Liu, Johnson, Bajji, Maheswari, Pham, Jacob, Xia, Xin, Huang, Zhiyu, Zhou, Bolei, Ma, Jiaqi
Vehicle-to-everything (V2X) technologies offer a promising paradigm to mitigate the limitations of constrained observability in single-vehicle systems. Prior work primarily focuses on single-frame cooperative perception, which fuses agents' informati
Externí odkaz:
http://arxiv.org/abs/2412.01812
Point cloud registration is a foundational task for 3D alignment and reconstruction applications. While both traditional and learning-based registration approaches have succeeded, leveraging the intrinsic symmetry of point cloud data, including rotat
Externí odkaz:
http://arxiv.org/abs/2410.05729
Effective planning is essential for the success of any task, from organizing a vacation to routing autonomous vehicles and developing corporate strategies. It involves setting goals, formulating plans, and allocating resources to achieve them. LLMs a
Externí odkaz:
http://arxiv.org/abs/2409.01806
Autor:
Zhang, Zhaoliang, Song, Tianchen, Lee, Yongjae, Yang, Li, Peng, Cheng, Chellappa, Rama, Fan, Deliang
Recently, 3D Gaussian Splatting (3DGS) has become one of the mainstream methodologies for novel view synthesis (NVS) due to its high quality and fast rendering speed. However, as a point-based scene representation, 3DGS potentially generates a large
Externí odkaz:
http://arxiv.org/abs/2405.18784
3D Gaussian Splatting (3DGS) has made significant strides in novel view synthesis. However, its suboptimal densification process results in the excessively large number of Gaussian primitives, which impacts frame-per-second and increases memory usage
Externí odkaz:
http://arxiv.org/abs/2405.17793
Foundation models, especially those using transformers as backbones, have gained significant popularity, particularly in language and language-vision tasks. However, large foundation models are typically trained on high-quality data, which poses a si
Externí odkaz:
http://arxiv.org/abs/2404.17667
Autor:
Yang, Chen, Li, Junzhuo, Niu, Xinyao, Du, Xinrun, Gao, Songyang, Zhang, Haoran, Chen, Zhaoliang, Qu, Xingwei, Yuan, Ruibin, Li, Yizhi, Liu, Jiaheng, Huang, Stephen W., Yue, Shawn, Zhang, Ge
Uncovering early-stage metrics that reflect final model performance is one core principle for large-scale pretraining. The existing scaling law demonstrates the power-law correlation between pretraining loss and training flops, which serves as an imp
Externí odkaz:
http://arxiv.org/abs/2404.01204
Autor:
Xiang, Hao, Zheng, Zhaoliang, Xia, Xin, Xu, Runsheng, Gao, Letian, Zhou, Zewei, Han, Xu, Ji, Xinkai, Li, Mingxi, Meng, Zonglin, Jin, Li, Lei, Mingyue, Ma, Zhaoyang, He, Zihang, Ma, Haoxuan, Yuan, Yunshuang, Zhao, Yingqian, Ma, Jiaqi
Recent advancements in Vehicle-to-Everything (V2X) technologies have enabled autonomous vehicles to share sensing information to see through occlusions, greatly boosting the perception capability. However, there are no real-world datasets to facilita
Externí odkaz:
http://arxiv.org/abs/2403.16034