Zobrazeno 1 - 10
of 20 768
pro vyhledávání: '"Yu-Dong"'
We present detailed evolutionary simulations of wide binary systems with high-mass ($8-20\,M_{\odot}$) donor stars and a $1.4\,M_{\odot}$ neutron star. Mass transfer in such binaries is dynamically unstable and common envelope (CE) evolution is follo
Externí odkaz:
http://arxiv.org/abs/2412.01776
We reveal that low-bit quantization favors undertrained large language models (LLMs) by observing that models with larger sizes or fewer training tokens experience less quantization-induced degradation (QiD) when applying low-bit quantization, wherea
Externí odkaz:
http://arxiv.org/abs/2411.17691
Federated Named Entity Recognition (FNER) boosts model training within each local client by aggregating the model updates of decentralized local clients, without sharing their private data. However, existing FNER methods assume fixed entity types and
Externí odkaz:
http://arxiv.org/abs/2411.11623
Proper moral beliefs are fundamental for language models, yet assessing these beliefs poses a significant challenge. This study introduces a novel three-module framework to evaluate the moral beliefs of four prominent large language models. Initially
Externí odkaz:
http://arxiv.org/abs/2411.03665
Autor:
He, Hongliang, Yao, Wenlin, Ma, Kaixin, Yu, Wenhao, Zhang, Hongming, Fang, Tianqing, Lan, Zhenzhong, Yu, Dong
The rapid development of large language and multimodal models has sparked significant interest in using proprietary models, such as GPT-4o, to develop autonomous agents capable of handling real-world scenarios like web navigation. Although recent ope
Externí odkaz:
http://arxiv.org/abs/2410.19609
Autor:
Yang, Ruihan, Zhang, Caiqi, Zhang, Zhisong, Huang, Xinting, Yang, Sen, Collier, Nigel, Yu, Dong, Yang, Deqing
While Large Language Models (LLMs) demonstrate impressive capabilities, they still struggle with generating factually incorrect content (i.e., hallucinations). A promising approach to mitigate this issue is enabling models to express uncertainty when
Externí odkaz:
http://arxiv.org/abs/2410.14309
Autor:
Zhang, Caiqi, Yang, Ruihan, Zhang, Zhisong, Huang, Xinting, Yang, Sen, Yu, Dong, Collier, Nigel
Large language models (LLMs) often suffer from hallucinations, posing significant challenges for real-world applications. Confidence calibration, which estimates the underlying uncertainty of model predictions, is essential to enhance the LLMs' trust
Externí odkaz:
http://arxiv.org/abs/2410.13246
Traditional transformer models often allocate a fixed amount of computational resources to every input token, leading to inefficient and unnecessary computation. To address this, the Mixture of Depths (MoD) was introduced to dynamically adjust the co
Externí odkaz:
http://arxiv.org/abs/2410.13184
Recent large language model (LLM)-driven chat assistant systems have integrated memory components to track user-assistant chat histories, enabling more accurate and personalized responses. However, their long-term memory capabilities in sustained int
Externí odkaz:
http://arxiv.org/abs/2410.10813
We introduce SRC-gAudio, a novel audio generation model designed to facilitate text-to-audio generation across a wide range of sampling rates within a single model architecture. SRC-gAudio incorporates the sampling rate as part of the generation cond
Externí odkaz:
http://arxiv.org/abs/2410.06544