Zobrazeno 1 - 10
of 3 900
pro vyhledávání: '"YU, Haiyang"'
Autor:
Wang, Han, Nie, Yuxiang, Ye, Yongjie, GuanYu, Deng, Wang, Yanjie, Li, Shuai, Yu, Haiyang, Lu, Jinghui, Huang, Can
The application of Large Vision-Language Models (LVLMs) for analyzing images and videos is an exciting and rapidly evolving field. In recent years, we've seen significant growth in high-quality image-text datasets for fine-tuning image understanding,
Externí odkaz:
http://arxiv.org/abs/2412.09530
Computational modeling of aerodynamics is a key problem in aerospace engineering, often involving flows interacting with solid objects such as airfoils. Deep surrogate models have emerged as purely data-driven approaches that learn direct mappings fr
Externí odkaz:
http://arxiv.org/abs/2412.09399
Autor:
Wang, Lening, Zheng, Wenzhao, Du, Dalong, Zhang, Yunpeng, Ren, Yilong, Jiang, Han, Cui, Zhiyong, Yu, Haiyang, Zhou, Jie, Lu, Jiwen, Zhang, Shanghang
4D driving simulation is essential for developing realistic autonomous driving simulators. Despite advancements in existing methods for generating driving scenes, significant challenges remain in view transformation and spatial-temporal dynamic model
Externí odkaz:
http://arxiv.org/abs/2412.05280
Autor:
Wang, Minzheng, Zhang, Xinghua, Chen, Kun, Xu, Nan, Yu, Haiyang, Huang, Fei, Mao, Wenji, Li, Yongbin
Large language models (LLMs) have made dialogue one of the central modes of human-machine interaction, leading to the accumulation of vast amounts of conversation logs and increasing demand for dialogue generation. A conversational life-cycle spans f
Externí odkaz:
http://arxiv.org/abs/2412.04905
Publikováno v:
In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 881-887
Cross-lingual semantic textual relatedness task is an important research task that addresses challenges in cross-lingual communication and text understanding. It helps establish semantic connections between different languages, crucial for downstream
Externí odkaz:
http://arxiv.org/abs/2411.18990
We introduce BackdoorMBTI, the first backdoor learning toolkit and benchmark designed for multimodal evaluation across three representative modalities from eleven commonly used datasets. BackdoorMBTI provides a systematic backdoor learning pipeline,
Externí odkaz:
http://arxiv.org/abs/2411.11006
In the realm of large language models (LLMs), the ability of models to accurately follow instructions is paramount as more agents and applications leverage LLMs for construction, where the complexity of instructions are rapidly increasing. However, o
Externí odkaz:
http://arxiv.org/abs/2411.06208
Publikováno v:
Transactions on Machine Learning Research, 2024. Featured Certification
Recent advancements in equivariant deep models have shown promise in accurately predicting atomic potentials and force fields in molecular dynamics simulations. Using spherical harmonics (SH) and tensor products (TP), these equivariant networks gain
Externí odkaz:
http://arxiv.org/abs/2411.04219
Autor:
Lu, Xinyu, Wen, Xueru, Lu, Yaojie, Yu, Bowen, Lin, Hongyu, Yu, Haiyang, Sun, Le, Han, Xianpei, Li, Yongbin
As post-training processes utilize increasingly large datasets and base models continue to grow in size, the computational demands and implementation challenges of existing algorithms are escalating significantly. In this paper, we propose modeling t
Externí odkaz:
http://arxiv.org/abs/2410.21027
Cybersecurity has become a crucial concern in the field of connected autonomous vehicles. Cyber threat intelligence (CTI), as the collection of cyber threat information, offers an ideal way for responding to emerging cyber threats and realizing proac
Externí odkaz:
http://arxiv.org/abs/2410.16016