Zobrazeno 1 - 10
of 16 550
pro vyhledávání: '"zhang, Di"'
Autor:
Zhang, Di, Lei, Jingdi, Li, Junxian, Wang, Xunzhi, Liu, Yujie, Yang, Zonglin, Li, Jiatong, Wang, Weida, Yang, Suorong, Wu, Jianbo, Ye, Peng, Ouyang, Wanli, Zhou, Dongzhan
Vision-language models~(VLMs) have shown remarkable advancements in multimodal reasoning tasks. However, they still often generate inaccurate or irrelevant responses due to issues like hallucinated image understandings or unrefined reasoning paths. T
Externí odkaz:
http://arxiv.org/abs/2411.18203
High-quality video-text preference data is crucial for Multimodal Large Language Models (MLLMs) alignment. However, existing preference data is very scarce. Obtaining VQA preference data for preference training is costly, and manually annotating resp
Externí odkaz:
http://arxiv.org/abs/2411.16201
Autor:
Yin, Yuanyang, Zhao, Yaqi, Zheng, Mingwu, Lin, Ke, Ou, Jiarong, Chen, Rui, Huang, Victor Shea-Jay, Wang, Jiahao, Tao, Xin, Wan, Pengfei, Zhang, Di, Yin, Baoqun, Zhang, Wentao, Gai, Kun
Achieving optimal performance of video diffusion transformers within given data and compute budget is crucial due to their high training costs. This necessitates precisely determining the optimal model size and training hyperparameters before large-s
Externí odkaz:
http://arxiv.org/abs/2411.17470
Autor:
Hu, Jiahao, Zhong, Tianxiong, Wang, Xuebo, Jiang, Boyuan, Tian, Xingye, Yang, Fei, Wan, Pengfei, Zhang, Di
Diffusion-based image editing models have made remarkable progress in recent years. However, achieving high-quality video editing remains a significant challenge. One major hurdle is the absence of open-source, large-scale video editing datasets base
Externí odkaz:
http://arxiv.org/abs/2411.15260
Autor:
Li, Jiatong, Liu, Yunqing, Liu, Wei, Le, Jingdi, Zhang, Di, Fan, Wenqi, Zhou, Dongzhan, Li, Yuqiang, Li, Qing
Molecule discovery is a pivotal research field, impacting everything from the medicines we take to the materials we use. Recently, Large Language Models (LLMs) have been widely adopted in molecule understanding and generation, yet the alignments betw
Externí odkaz:
http://arxiv.org/abs/2411.14721
Realistic simulation of dynamic scenes requires accurately capturing diverse material properties and modeling complex object interactions grounded in physical principles. However, existing methods are constrained to basic material types with limited
Externí odkaz:
http://arxiv.org/abs/2411.14423
Autor:
Li, Zhicong, Wang, Jiahao, Jiang, Zhishu, Mao, Hangyu, Chen, Zhongxia, Du, Jiazhen, Zhang, Yuanxing, Zhang, Fuzheng, Zhang, Di, Liu, Yong
Large language models often encounter challenges with static knowledge and hallucinations, which undermine their reliability. Retrieval-augmented generation (RAG) mitigates these issues by incorporating external information. However, user queries fre
Externí odkaz:
http://arxiv.org/abs/2411.13154
We calculate the renormalization group equation (RGE) of the lepton-number-violating Weinberg operator with the particle content of the Standard Model (SM), thus completing the set of two-loop RGEs of the SM effective field theory up to dimension 5.
Externí odkaz:
http://arxiv.org/abs/2411.08011
Autor:
Lu, Xingyu, Hu, Yuhang, Liu, Changyi, Zhang, Tianke, Yang, Zhenyu, Ding, Zhixiang, Qian, Shengsheng, Du, Meng, Kang, Ruiwen, Tang, Kaiyu, Yang, Fan, Gao, Tingting, Zhang, Di, Zheng, Hai-Tao, Wen, Bin
Mathematical reasoning presents a significant challenge to the cognitive capabilities of LLMs. Various methods have been proposed to enhance the mathematical ability of LLMs. However, few recognize the value of state transition for LLM reasoning. In
Externí odkaz:
http://arxiv.org/abs/2411.04799
In-situ Study of Understanding the Resistive Switching Mechanisms of Nitride-based Memristor Devices
Autor:
Zhang, Di, Dhall, Rohan, Schneider, Matthew M., Song, Chengyu, Dou, Hongyi, Kunwar, Sundar, Yazzie, Natanii R., Ciston, Jim, Cucciniello, Nicholas G., Roy, Pinku, Pettes, Michael T., Watt, John, Kuo, Winson, Wang, Haiyan, McCabe, Rodney J., Chen, Aiping
Interface-type resistive switching (RS) devices with lower operation current and more reliable switching repeatability exhibits great potential in the applications for data storage devices and ultra-low-energy computing. However, the working mechanis
Externí odkaz:
http://arxiv.org/abs/2410.23185