Zobrazeno 1 - 10
of 8 114
pro vyhledávání: '"Liu, JingJing"'
Large language models (LLMs) have demonstrated remarkable proficiency in machine translation (MT), even without specific training on the languages in question. However, translating rare words in low-resource or domain-specific contexts remains challe
Externí odkaz:
http://arxiv.org/abs/2411.08348
Large language models (LLMs), although having revolutionized many fields, still suffer from the challenging extrapolation problem, where the inference ability of LLMs sharply declines beyond their max training lengths. In this work, we conduct a theo
Externí odkaz:
http://arxiv.org/abs/2410.15859
Autor:
Li, Jianxiong, Wang, Zhihao, Zheng, Jinliang, Zhou, Xiaoai, Wang, Guanming, Song, Guanglu, Liu, Yu, Liu, Jingjing, Zhang, Ya-Qin, Yu, Junzhi, Zhan, Xianyuan
Multimodal task specification is essential for enhanced robotic performance, where \textit{Cross-modality Alignment} enables the robot to holistically understand complex task instructions. Directly annotating multimodal instructions for model trainin
Externí odkaz:
http://arxiv.org/abs/2410.01529
Autor:
Wang, Xinlong, Zhang, Xiaosong, Luo, Zhengxiong, Sun, Quan, Cui, Yufeng, Wang, Jinsheng, Zhang, Fan, Wang, Yueze, Li, Zhen, Yu, Qiying, Zhao, Yingli, Ao, Yulong, Min, Xuebin, Li, Tao, Wu, Boya, Zhao, Bo, Zhang, Bowen, Wang, Liangdong, Liu, Guang, He, Zheqi, Yang, Xi, Liu, Jingjing, Lin, Yonghua, Huang, Tiejun, Wang, Zhongyuan
While next-token prediction is considered a promising path towards artificial general intelligence, it has struggled to excel in multimodal tasks, which are still dominated by diffusion models (e.g., Stable Diffusion) and compositional approaches (e.
Externí odkaz:
http://arxiv.org/abs/2409.18869
Data generation-based zero-shot learning, although effective in training Small Task-specific Models (STMs) via synthetic datasets generated by Pre-trained Language Models (PLMs), is often limited by the low quality of such synthetic datasets. Previou
Externí odkaz:
http://arxiv.org/abs/2406.12527
Autor:
Zheng, Jinliang, Li, Jianxiong, Cheng, Sijie, Zheng, Yinan, Li, Jiaming, Liu, Jihao, Liu, Yu, Liu, Jingjing, Zhan, Xianyuan
Instruction following is crucial in contemporary LLM. However, when extended to multimodal setting, it often suffers from misalignment between specific textual instruction and targeted local region of an image. To achieve more accurate and nuanced mu
Externí odkaz:
http://arxiv.org/abs/2405.19783
Acoustic waves in fluid with spin-0 nature have been long believed not to support spin Hall effect and strong orbital Hall effect that enables experimental observation. Here we report the first theoretical explication and experimental demonstration o
Externí odkaz:
http://arxiv.org/abs/2405.14202
Thrombotic and chronic occlusions of large blood vessels are a major cause of mortality and morbidity, and so there is a need for improved treatments in many clinical circumstances. Endovascular ultrasound approaches have been shown to hold considera
Externí odkaz:
http://arxiv.org/abs/2405.12966
Autor:
Zou, Wenjun, Lyu, Yao, Li, Jie, Yang, Yujie, Li, Shengbo Eben, Duan, Jingliang, Zhan, Xianyuan, Liu, Jingjing, Zhang, Yaqin, Li, Keqiang
Safe reinforcement learning (RL) offers advanced solutions to constrained optimal control problems. Existing studies in safe RL implicitly assume continuity in policy functions, where policies map states to actions in a smooth, uninterrupted manner;
Externí odkaz:
http://arxiv.org/abs/2403.12847
Autor:
Song, Yuxuan, Gong, Jingjing, Qu, Yanru, Zhou, Hao, Zheng, Mingyue, Liu, Jingjing, Ma, Wei-Ying
Advanced generative model (e.g., diffusion model) derived from simplified continuity assumptions of data distribution, though showing promising progress, has been difficult to apply directly to geometry generation applications due to the multi-modali
Externí odkaz:
http://arxiv.org/abs/2403.15441