Zobrazeno 1 - 10
of 14 385
pro vyhledávání: '"Li,Pan"'
Autor:
Zemskov, Alexander D., Fu, Yao, Li, Runchao, Wang, Xufei, Karkaria, Vispi, Tsai, Ying-Kuan, Chen, Wei, Zhang, Jianjing, Gao, Robert, Cao, Jian, Loparo, Kenneth A., Li, Pan
In Industry 4.0, the digital twin is one of the emerging technologies, offering simulation abilities to predict, refine, and interpret conditions and operations, where it is crucial to emphasize a heightened concentration on the associated security a
Externí odkaz:
http://arxiv.org/abs/2412.13939
Autor:
Wei, Rongzhe, Li, Mufei, Ghassemi, Mohsen, Kreačić, Eleonora, Li, Yifan, Yue, Xiang, Li, Bo, Potluru, Vamsi K., Li, Pan, Chien, Eli
Large Language Models are trained on extensive datasets that often contain sensitive, human-generated information, raising significant concerns about privacy breaches. While certified unlearning approaches offer strong privacy guarantees, they rely o
Externí odkaz:
http://arxiv.org/abs/2412.08559
Knowledge distillation (KD) has become a widely adopted approach for compressing large language models (LLMs) to reduce computational costs and memory footprints. However, the availability of complex teacher models is a prerequisite for running most
Externí odkaz:
http://arxiv.org/abs/2411.16991
Publikováno v:
SCIENCE CHINA Physics, Mechanics & Astronomy , Volume 68, Issue 2: 220412 (2025) | Article
Using the AdS/CFT correspondence, this paper investigates the holographic images of a charged black hole within the context of Lorentz symmetry breaking massive gravity. The photon rings, luminosity-deformed rings, or light points from various observ
Externí odkaz:
http://arxiv.org/abs/2411.12528
Autor:
Li, Mufei, Shitole, Viraj, Chien, Eli, Man, Changhai, Wang, Zhaodong, Sridharan, Srinivas, Zhang, Ying, Krishna, Tushar, Li, Pan
Directed acyclic graphs (DAGs) serve as crucial data representations in domains such as hardware synthesis and compiler/program optimization for computing systems. DAG generative models facilitate the creation of synthetic DAGs, which can be used for
Externí odkaz:
http://arxiv.org/abs/2411.02322
We explore optimally training protein language models, an area of significant interest in biological research where guidance on best practices is limited. Most models are trained with extensive compute resources until performance gains plateau, focus
Externí odkaz:
http://arxiv.org/abs/2411.02142
Autor:
Li, Pan
In this paper, we investigate the Hilbert space factorisation problem of two-sided black holes in high dimensions. We demonstrate that the Hilbert space of two-sided black holes can be factorized into the tensor product of two one-sided bulk Hilbert
Externí odkaz:
http://arxiv.org/abs/2410.23886
Large Language Models (LLMs) demonstrate strong reasoning abilities but face limitations such as hallucinations and outdated knowledge. Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) addresses these issues by grounding LLM outputs in
Externí odkaz:
http://arxiv.org/abs/2410.20724
Autor:
Zhang, Kexin, Liu, Shuhan, Wang, Song, Shi, Weili, Chen, Chen, Li, Pan, Li, Sheng, Li, Jundong, Ding, Kaize
Distribution shifts on graphs -- the discrepancies in data distribution between training and employing a graph machine learning model -- are ubiquitous and often unavoidable in real-world scenarios. These shifts may severely deteriorate model perform
Externí odkaz:
http://arxiv.org/abs/2410.19265
Graph neural networks (GNNs) have achieved remarkable success in a variety of machine learning tasks over graph data. Existing GNNs usually rely on message passing, i.e., computing node representations by gathering information from the neighborhood,
Externí odkaz:
http://arxiv.org/abs/2410.09737