Zobrazeno 1 - 10
of 6 914
pro vyhledávání: '"An, Zhaopeng"'
Autor:
Chen, Xingyu, Xu, Jiahao, Liang, Tian, He, Zhiwei, Pang, Jianhui, Yu, Dian, Song, Linfeng, Liu, Qiuzhi, Zhou, Mengfei, Zhang, Zhuosheng, Wang, Rui, Tu, Zhaopeng, Mi, Haitao, Yu, Dong
The remarkable performance of models like the OpenAI o1 can be attributed to their ability to emulate human-like long-time thinking during inference. These models employ extended chain-of-thought (CoT) processes, exploring multiple strategies to enha
Externí odkaz:
http://arxiv.org/abs/2412.21187
M-MAD: Multidimensional Multi-Agent Debate Framework for Fine-grained Machine Translation Evaluation
Autor:
Feng, Zhaopeng, Su, Jiayuan, Zheng, Jiamei, Ren, Jiahan, Zhang, Yan, Wu, Jian, Wang, Hongwei, Liu, Zuozhu
Recent advancements in large language models (LLMs) have given rise to the LLM-as-a-judge paradigm, showcasing their potential to deliver human-like judgments. However, in the field of machine translation (MT) evaluation, current LLM-as-a-judge metho
Externí odkaz:
http://arxiv.org/abs/2412.20127
Medication recommendation is one of the most critical health-related applications, which has attracted extensive research interest recently. Most existing works focus on a single hospital with abundant medical data. However, many small hospitals only
Externí odkaz:
http://arxiv.org/abs/2412.20040
Autor:
Yu, Dian, Zhang, Yuheng, Xu, Jiahao, Liang, Tian, Song, Linfeng, Tu, Zhaopeng, Mi, Haitao, Yu, Dong
Large language models (LLMs) can refine their responses based on feedback, enabling self-improvement through iterative training or test-time refinement. However, existing methods predominantly focus on refinement within the same reasoning format, whi
Externí odkaz:
http://arxiv.org/abs/2412.16871
Autor:
Yang, Zesong, Zhang, Ru, Shi, Jiale, Ai, Zixiang, Zhao, Boming, Bao, Hujun, Yang, Luwei, Cui, Zhaopeng
Neural surface representation has demonstrated remarkable success in the areas of novel view synthesis and 3D reconstruction. However, assessing the geometric quality of 3D reconstructions in the absence of ground truth mesh remains a significant cha
Externí odkaz:
http://arxiv.org/abs/2412.14939
Autor:
Wang, Longyue, Liu, Siyou, Lyu, Chenyang, Jiao, Wenxiang, Wang, Xing, Xu, Jiahao, Tu, Zhaopeng, Gu, Yan, Chen, Weiyu, Wu, Minghao, Zhou, Liting, Koehn, Philipp, Way, Andy, Yuan, Yulin
Following last year, we have continued to host the WMT translation shared task this year, the second edition of the Discourse-Level Literary Translation. We focus on three language directions: Chinese-English, Chinese-German, and Chinese-Russian, wit
Externí odkaz:
http://arxiv.org/abs/2412.11732
Human video synthesis aims to create lifelike characters in various environments, with wide applications in VR, storytelling, and content creation. While 2D diffusion-based methods have made significant progress, they struggle to generalize to comple
Externí odkaz:
http://arxiv.org/abs/2412.11067
Visual Anomaly Detection (VAD) aims to identify abnormal samples in images that deviate from normal patterns, covering multiple domains, including industrial, logical, and medical fields. Due to the domain gaps between these fields, existing VAD meth
Externí odkaz:
http://arxiv.org/abs/2412.03342
Autor:
Lin, Zicheng, Liang, Tian, Xu, Jiahao, Wang, Xing, Luo, Ruilin, Shi, Chufan, Li, Siheng, Yang, Yujiu, Tu, Zhaopeng
Large Language Models (LLMs) have exhibited remarkable performance on reasoning tasks. They utilize autoregressive token generation to construct reasoning trajectories, enabling the development of a coherent chain of thought. In this work, we explore
Externí odkaz:
http://arxiv.org/abs/2411.19943
Speculative Decoding (SD) has become an important technique in accelerating the inference speed of large language models. Conventional SD methods employ a fixed draft length, which ignores the token generation difficulty across tasks. Consequently, i
Externí odkaz:
http://arxiv.org/abs/2411.18462