Zobrazeno 1 - 10
of 4 491
pro vyhledávání: '"Su, Hang"'
Automated evaluation is crucial for streamlining text summarization benchmarking and model development, given the costly and time-consuming nature of human evaluation. Traditional methods like ROUGE do not correlate well with human judgment, while re
Externí odkaz:
http://arxiv.org/abs/2407.00908
Multiphase oxidation of sulfur dioxide (SO2) is an important source of sulfate in the atmosphere. There are, however, concerns that protons produced during SO2 oxidation may cause rapid acidification of aerosol water and thereby quickly shut down the
Externí odkaz:
http://arxiv.org/abs/2406.19133
Autor:
Zhang, Yichi, Huang, Yao, Sun, Yitong, Liu, Chang, Zhao, Zhe, Fang, Zhengwei, Wang, Yifan, Chen, Huanran, Yang, Xiao, Wei, Xingxing, Su, Hang, Dong, Yinpeng, Zhu, Jun
Despite the superior capabilities of Multimodal Large Language Models (MLLMs) across diverse tasks, they still face significant trustworthiness challenges. Yet, current literature on the assessment of trustworthy MLLMs remains limited, lacking a holi
Externí odkaz:
http://arxiv.org/abs/2406.07057
Large Language Models (LLMs) are powerful models for generation tasks, but they may not generate good quality outputs in their first attempt. Apart from model fine-tuning, existing approaches to improve prediction accuracy and quality typically invol
Externí odkaz:
http://arxiv.org/abs/2406.05588
We show that the ground-state expectation value of twisting operator is a topological order parameter for $\text{U}(1)$- and $\mathbb{Z}_{N}$-symmetric symmetry-protected topological (SPT) phases in one-dimensional ``spin'' systems -- it is quantized
Externí odkaz:
http://arxiv.org/abs/2406.05407
Transformer has shown promise in reinforcement learning to model time-varying features for obtaining generalized low-level robot policies on diverse robotics datasets in embodied learning. However, it still suffers from the issues of low data efficie
Externí odkaz:
http://arxiv.org/abs/2405.19885
Embodied intelligence empowers agents with a profound sense of perception, enabling them to respond in a manner closely aligned with real-world situations. Large Language Models (LLMs) delve into language instructions with depth, serving a crucial ro
Externí odkaz:
http://arxiv.org/abs/2405.19802
Despite the widespread application of large language models (LLMs) across various tasks, recent studies indicate that they are susceptible to jailbreak attacks, which can render their defense mechanisms ineffective. However, previous jailbreak resear
Externí odkaz:
http://arxiv.org/abs/2405.19668
Autor:
Cheng, Ze, Hao, Zhongkai, Wang, Xiaoqiang, Huang, Jianing, Wu, Youjia, Liu, Xudan, Zhao, Yiru, Liu, Songming, Su, Hang
For partial differential equations on domains of arbitrary shapes, existing works of neural operators attempt to learn a mapping from geometries to solutions. It often requires a large dataset of geometry-solution pairs in order to obtain a sufficien
Externí odkaz:
http://arxiv.org/abs/2405.17509
Catastrophic overfitting (CO) presents a significant challenge in single-step adversarial training (AT), manifesting as highly distorted deep neural networks (DNNs) that are vulnerable to multi-step adversarial attacks. However, the underlying factor
Externí odkaz:
http://arxiv.org/abs/2405.16262