Zobrazeno 1 - 10
of 1 194
pro vyhledávání: '"Li, Yuan‐Fang"'
Hyperedge prediction is crucial in hypergraph analysis for understanding complex multi-entity interactions in various web-based applications, including social networks and e-commerce systems. Traditional methods often face difficulties in generating
Externí odkaz:
http://arxiv.org/abs/2411.12354
Autor:
Shiri, Fatemeh, Guo, Xiao-Yu, Far, Mona Golestan, Yu, Xin, Haffari, Gholamreza, Li, Yuan-Fang
Large Multimodal Models (LMMs) have achieved strong performance across a range of vision and language tasks. However, their spatial reasoning capabilities are under-investigated. In this paper, we construct a novel VQA dataset, Spatial-MM, to compreh
Externí odkaz:
http://arxiv.org/abs/2411.06048
Data-free knowledge distillation (DFKD) has emerged as a pivotal technique in the domain of model compression, substantially reducing the dependency on the original training data. Nonetheless, conventional DFKD methods that employ synthesized trainin
Externí odkaz:
http://arxiv.org/abs/2410.17606
Autor:
Chen, Meng, Arthur, Philip, Feng, Qianyu, Hoang, Cong Duy Vu, Hong, Yu-Heng, Moghaddam, Mahdi Kazemi, Nezami, Omid, Nguyen, Thien, Tangari, Gioacchino, Vu, Duy, Vu, Thanh, Johnson, Mark, Kenthapadi, Krishnaram, Dharmasiri, Don, Duong, Long, Li, Yuan-Fang
Large language models (LLMs) have shown impressive performance in \emph{code} understanding and generation, making coding tasks a key focus for researchers due to their practical applications and value as a testbed for LLM evaluation. Data synthesis
Externí odkaz:
http://arxiv.org/abs/2411.00005
Autor:
Qu, Shilin, Wang, Weiqing, Zhou, Xin, Zhan, Haolan, Li, Zhuang, Qu, Lizhen, Luo, Linhao, Li, Yuan-Fang, Haffari, Gholamreza
Publikováno v:
TOMM 2024
Sociocultural norms serve as guiding principles for personal conduct in social interactions, emphasizing respect, cooperation, and appropriate behavior, which is able to benefit tasks including conversational information retrieval, contextual informa
Externí odkaz:
http://arxiv.org/abs/2410.03049
We propose Hi-SLAM, a semantic 3D Gaussian Splatting SLAM method featuring a novel hierarchical categorical representation, which enables accurate global 3D semantic mapping, scaling-up capability, and explicit semantic label prediction in the 3D wor
Externí odkaz:
http://arxiv.org/abs/2409.12518
Autor:
Cai, Zhixi, Cardenas, Cristian Rojas, Leo, Kevin, Zhang, Chenyuan, Backman, Kal, Li, Hanbing, Li, Boying, Ghorbanali, Mahsa, Datta, Stavya, Qu, Lizhen, Santiago, Julian Gutierrez, Ignatiev, Alexey, Li, Yuan-Fang, Vered, Mor, Stuckey, Peter J, de la Banda, Maria Garcia, Rezatofighi, Hamid
This paper addresses the problem of autonomous UAV search missions, where a UAV must locate specific Entities of Interest (EOIs) within a time limit, based on brief descriptions in large, hazard-prone environments with keep-out zones. The UAV must pe
Externí odkaz:
http://arxiv.org/abs/2409.10196
Accurate prediction of house price, a vital aspect of the residential real estate sector, is of substantial interest for a wide range of stakeholders. However, predicting house prices is a complex task due to the significant variability influenced by
Externí odkaz:
http://arxiv.org/abs/2409.05335
While large multimodal models (LMMs) have obtained strong performance on many multimodal tasks, they may still hallucinate while generating text. Their performance on detecting salient features from visual data is also unclear. In this paper, we deve
Externí odkaz:
http://arxiv.org/abs/2409.03961
We often use "explainable" Artificial Intelligence (XAI)" and "interpretable AI (IAI)" interchangeably when we apply various XAI tools for a given dataset to explain the reasons that underpin machine learning (ML) outputs. However, these notions can
Externí odkaz:
http://arxiv.org/abs/2408.12420