Zobrazeno 1 - 10
of 602
pro vyhledávání: '"Li, Shimin"'
Autor:
Shao, Yunfan, Li, Linyang, Ma, Yichuan, Li, Peiji, Song, Demin, Cheng, Qinyuan, Li, Shimin, Li, Xiaonan, Wang, Pengyu, Guo, Qipeng, Yan, Hang, Qiu, Xipeng, Huang, Xuanjing, Lin, Dahua
Complex reasoning is an impressive ability shown by large language models (LLMs). Most LLMs are skilled in deductive reasoning, such as chain-of-thought prompting or iterative tool-using to solve challenging tasks step-by-step. In this paper, we hope
Externí odkaz:
http://arxiv.org/abs/2407.12504
Autor:
Wang, Siyin, Ye, Xingsong, Cheng, Qinyuan, Duan, Junwen, Li, Shimin, Fu, Jinlan, Qiu, Xipeng, Huang, Xuanjing
As Artificial General Intelligence (AGI) becomes increasingly integrated into various facets of human life, ensuring the safety and ethical alignment of such systems is paramount. Previous studies primarily focus on single-modality threats, which may
Externí odkaz:
http://arxiv.org/abs/2406.15279
Autor:
Cheng, Qinyuan, Li, Xiaonan, Li, Shimin, Zhu, Qin, Yin, Zhangyue, Shao, Yunfan, Li, Linyang, Sun, Tianxiang, Yan, Hang, Qiu, Xipeng
In Retrieval-Augmented Generation (RAG), retrieval is not always helpful and applying it to every instruction is sub-optimal. Therefore, determining whether to retrieve is crucial for RAG, which is usually referred to as Active Retrieval. However, ex
Externí odkaz:
http://arxiv.org/abs/2406.12534
Recently, research on the complex periodic behavior of multi-scale systems has become increasingly popular. Krupa et al. \cite{krupa2} provided a way to obtain relaxation oscillations in slow-fast systems through singular Hopf bifurcations and canard
Externí odkaz:
http://arxiv.org/abs/2406.03732
Speech language models have significantly advanced in generating realistic speech, with neural codec language models standing out. However, the integration of human feedback to align speech outputs to human preferences is often neglected. This paper
Externí odkaz:
http://arxiv.org/abs/2404.05600
Autor:
Wang, Siyin, Li, Shimin, Sun, Tianxiang, Fu, Jinlan, Cheng, Qinyuan, Ye, Jiasheng, Ye, Junjie, Qiu, Xipeng, Huang, Xuanjing
In the realm of Large Language Models (LLMs), users commonly employ diverse decoding strategies and adjust hyperparameters to control the generated text. However, a critical question emerges: Are LLMs conscious of the existence of these decoding stra
Externí odkaz:
http://arxiv.org/abs/2402.11251
Autor:
Cheng, Qinyuan, Sun, Tianxiang, Liu, Xiangyang, Zhang, Wenwei, Yin, Zhangyue, Li, Shimin, Li, Linyang, He, Zhengfu, Chen, Kai, Qiu, Xipeng
Recently, AI assistants based on large language models (LLMs) show surprising performance in many tasks, such as dialogue, solving math problems, writing code, and using tools. Although LLMs possess intensive world knowledge, they still make factual
Externí odkaz:
http://arxiv.org/abs/2401.13275
Benefiting from effective speech modeling, current Speech Large Language Models (SLLMs) have demonstrated exceptional capabilities in in-context speech generation and efficient generalization to unseen speakers. However, the prevailing information mo
Externí odkaz:
http://arxiv.org/abs/2401.13527
Agents based on Large Language Models (LLMs) are increasingly permeating various domains of human production and life, highlighting the importance of aligning them with human values. The current alignment of AI systems primarily focuses on passively
Externí odkaz:
http://arxiv.org/abs/2401.04620
Computing the proximal operator of the sparsity-promoting piece-wise exponential (PiE) penalty $1-e^{-|x|/\sigma}$ with a given shape parameter $\sigma>0$, which is treated as a popular nonconvex surrogate of $\ell_0$-norm, is fundamental in feature
Externí odkaz:
http://arxiv.org/abs/2310.17849