Zobrazeno 1 - 10
of 3 509
pro vyhledávání: '"Wang, Siqi"'
As large language models (LLMs) constantly evolve, ensuring their safety remains a critical research problem. Previous red-teaming approaches for LLM safety have primarily focused on single prompt attacks or goal hijacking. To the best of our knowled
Externí odkaz:
http://arxiv.org/abs/2406.17626
Autor:
Zhang, Zefeng, Sheng, Jiawei, Zhang, Chuang, Liang, Yunzhi, Zhang, Wenyuan, Wang, Siqi, Liu, Tingwen
Multimodal Entity Linking (MEL) aims to link ambiguous mentions in multimodal contexts to entities in a multimodal knowledge graph. A pivotal challenge is to fully leverage multi-element correlations between mentions and entities to bridge modality g
Externí odkaz:
http://arxiv.org/abs/2406.01934
With the rapid development of deep learning, the implementation of intricate algorithms and substantial data processing have become standard elements of deep learning projects. As a result, the code has become progressively complex as the software ev
Externí odkaz:
http://arxiv.org/abs/2405.04861
Autor:
Tang, Jingqun, Lin, Chunhui, Zhao, Zhen, Wei, Shu, Wu, Binghong, Liu, Qi, Feng, Hao, Li, Yang, Wang, Siqi, Liao, Lei, Shi, Wei, Liu, Yuliang, Liu, Hao, Xie, Yuan, Bai, Xiang, Huang, Can
Text-centric visual question answering (VQA) has made great strides with the development of Multimodal Large Language Models (MLLMs), yet open-source models still fall short of leading models like GPT4V and Gemini, partly due to a lack of extensive,
Externí odkaz:
http://arxiv.org/abs/2404.12803
Digital Image Correlation (DIC) is an optical technique that measures displacement and strain by tracking pattern movement in a sequence of captured images during testing. DIC has gained recognition in asphalt pavement engineering since the early 200
Externí odkaz:
http://arxiv.org/abs/2402.17074
Autor:
Wang, Siqi, Yang, Hailong, Wang, Xuezhu, Liu, Tongxuan, Wang, Pengbo, Liang, Xuning, Ma, Kejie, Feng, Tianyu, You, Xin, Bao, Yongjun, Liu, Yi, Luan, Zhongzhi, Qian, Depei
Large language models (LLM) have recently attracted surging interest due to their outstanding capabilities across various domains. However, enabling efficient LLM inference is challenging due to its autoregressive decoding that generates tokens only
Externí odkaz:
http://arxiv.org/abs/2402.15678
The conventional surface reflection method has been widely used to measure the asphalt pavement layer dielectric constant using ground-penetrating radar (GPR). This method may be inaccurate for in-service pavement thickness estimation with dielectric
Externí odkaz:
http://arxiv.org/abs/2401.03375
Synthesis of Temporally-Robust Policies for Signal Temporal Logic Tasks using Reinforcement Learning
This paper investigates the problem of designing control policies that satisfy high-level specifications described by signal temporal logic (STL) in unknown, stochastic environments. While many existing works concentrate on optimizing the spatial rob
Externí odkaz:
http://arxiv.org/abs/2312.05764
Noisy labels can impair model performance, making the study of learning with noisy labels an important topic. Two conventional approaches are noise modeling and noise detection. However, these two methods are typically studied independently, and ther
Externí odkaz:
http://arxiv.org/abs/2312.00827
Publikováno v:
npj Computational Materials 9, 216 (2023)
The $\alpha/\beta$ interface is central to the microstructure and mechanical properties of titanium alloys. We investigate the structure, thermodynamics and migration of the coherent and semicoherent Ti $\alpha/\beta$ interfaces as a function of temp
Externí odkaz:
http://arxiv.org/abs/2311.02897