Zobrazeno 1 - 10
of 2 779
pro vyhledávání: '"Dai, Yong"'
Autor:
Lin, Fan, Xie, Shuyi, Dai, Yong, Yao, Wenlin, Lang, Tianjiao, Xu, Zishan, Hu, Zhichao, Xiao, Xiao, Liu, Yuhong, Zhang, Yu
As Large Language Models (LLMs) grow increasingly adept at managing complex tasks, the evaluation set must keep pace with these advancements to ensure it remains sufficiently discriminative. Item Discrimination (ID) theory, which is widely used in ed
Externí odkaz:
http://arxiv.org/abs/2409.18892
Autor:
Zhu, Zhilin, Hong, Xiaopeng, Ma, Zhiheng, Zhuang, Weijun, Ma, Yaohui, Dai, Yong, Wang, Yaowei
Continual Test-Time Adaptation (CTTA) involves adapting a pre-trained source model to continually changing unsupervised target domains. In this paper, we systematically analyze the challenges of this task: online environment, unsupervised nature, and
Externí odkaz:
http://arxiv.org/abs/2407.09367
Contemporary continual learning approaches typically select prompts from a pool, which function as supplementary inputs to a pre-trained model. However, this strategy is hindered by the inherent noise of its selection approach when handling increasin
Externí odkaz:
http://arxiv.org/abs/2404.18060
We explore the self-play training procedure of large language models (LLMs) in a two-player adversarial language game called Adversarial Taboo. In this game, an attacker and a defender communicate around a target word only visible to the attacker. Th
Externí odkaz:
http://arxiv.org/abs/2404.10642
Over the past decade, a series of unflagging efforts have been dedicated to developing highly expressive and controllable text-to-speech (TTS) systems. In general, the holistic TTS comprises two interconnected components: the frontend module and the
Externí odkaz:
http://arxiv.org/abs/2404.09192
Tool-augmented large language models (LLMs) are attracting widespread attention when accessing up-to-date knowledge and alleviating hallucination issues. Nowadays, advanced closed-source LLMs (e.g., ChatGPT) have demonstrated surprising tool-usage ca
Externí odkaz:
http://arxiv.org/abs/2402.16696
Recently, Class-Agnostic Counting (CAC) problem has garnered increasing attention owing to its intriguing generality and superior efficiency compared to Category-Specific Counting (CSC). This paper proposes a novel ExpressCount to enhance zero-shot o
Externí odkaz:
http://arxiv.org/abs/2402.05394
While vision-language pre-trained models (VL-PTMs) have advanced multimodal research in recent years, their mastery in a few languages like English restricts their applicability in broader communities. To this end, there is an increasing interest in
Externí odkaz:
http://arxiv.org/abs/2401.17186
Autor:
He, Hongliang, Yao, Wenlin, Ma, Kaixin, Yu, Wenhao, Dai, Yong, Zhang, Hongming, Lan, Zhenzhong, Yu, Dong
The rapid advancement of large language models (LLMs) has led to a new era marked by the development of autonomous applications in real-world scenarios, which drives innovation in creating advanced web agents. Existing web agents typically only handl
Externí odkaz:
http://arxiv.org/abs/2401.13919
Autor:
Feng, Zhangyin, Hu, Runyi, Liu, Liangxin, Zhang, Fan, Tang, Duyu, Dai, Yong, Feng, Xiaocheng, Li, Jiwei, Qin, Bing, Shi, Shuming
Autoregressive and diffusion models drive the recent breakthroughs on text-to-image generation. Despite their huge success of generating high-realistic images, a common shortcoming of these models is their high inference latency - autoregressive mode
Externí odkaz:
http://arxiv.org/abs/2312.14988