Zobrazeno 1 - 10
of 1 064 424
pro vyhledávání: '"Ren AT"'
As large language models (LLMs) grow in size, traditional full fine-tuning becomes increasingly impractical due to its high computational and storage costs. Although popular parameter-efficient fine-tuning methods, such as LoRA, have significantly re
Externí odkaz:
http://arxiv.org/abs/2412.10135
Autor:
Ma, Fei, Li, Yukan, Xie, Yifan, He, Ying, Zhang, Yi, Ren, Hongwei, Liu, Zhou, Yao, Wei, Ren, Fuji, Yu, Fei Richard, Ni, Shiguang
Human emotion synthesis is a crucial aspect of affective computing. It involves using computational methods to mimic and convey human emotions through various modalities, with the goal of enabling more natural and effective human-computer interaction
Externí odkaz:
http://arxiv.org/abs/2412.07116
This study proposes the IoT-Enhanced Pose Optimization Network (IE-PONet) for high-precision 3D pose estimation and motion optimization of track and field athletes. IE-PONet integrates C3D for spatiotemporal feature extraction, OpenPose for real-time
Externí odkaz:
http://arxiv.org/abs/2411.12676
Cancer, with its inherent heterogeneity, is commonly categorized into distinct subtypes based on unique traits, cellular origins, and molecular markers specific to each type. However, current studies primarily rely on complete multi-omics datasets fo
Externí odkaz:
http://arxiv.org/abs/2411.15180
Autor:
Lyu, Yougang, Yan, Lingyong, Wang, Zihan, Yin, Dawei, Ren, Pengjie, de Rijke, Maarten, Ren, Zhaochun
As large language models (LLMs) are rapidly advancing and achieving near-human capabilities, aligning them with human values is becoming more urgent. In scenarios where LLMs outperform humans, we face a weak-to-strong alignment problem where we need
Externí odkaz:
http://arxiv.org/abs/2410.07672
Autor:
Ren, Zheng, Huang, Jianwei, Tan, Hengxin, Biswas, Ananya, Pulkkinen, Aki, Zhang, Yichen, Xie, Yaofeng, Yue, Ziqin, Chen, Lei, Xie, Fang, Allen, Kevin, Wu, Han, Ren, Qirui, Rajapitamahuni, Anil, Kundu, Asish, Vescovo, Elio, Kono, Junichiro, Morosan, Emilia, Dai, Pengcheng, Zhu, Jian-Xin, Si, Qimiao, Minár, Ján, Yan, Binghai, Yi, Ming
Publikováno v:
Nature Communications 15, 9376 (2024)
Magnetic kagome materials provide a fascinating playground for exploring the interplay of magnetism, correlation and topology. Many magnetic kagome systems have been reported including the binary FemXn (X=Sn, Ge; m:n = 3:1, 3:2, 1:1) family and the r
Externí odkaz:
http://arxiv.org/abs/2410.06147
Autor:
Ren, Yuchen, Han, Wenwei, Zhang, Qianyuan, Tang, Yining, Bai, Weiqiang, Cai, Yuchen, Qiao, Lifeng, Jiang, Hao, Yuan, Dong, Chen, Tao, Sun, Siqi, Tan, Pan, Ouyang, Wanli, Dong, Nanqing, Ma, Xinzhu, Ye, Peng
As key elements within the central dogma, DNA, RNA, and proteins play crucial roles in maintaining life by guaranteeing accurate genetic expression and implementation. Although research on these molecules has profoundly impacted fields like medicine,
Externí odkaz:
http://arxiv.org/abs/2412.10347
Autor:
Perestjuk, Marko, Armand, Rémi, Campos, Miguel Gerardo Sandoval, Ferhat, Lamine, Reboud, Vincent, Bresson, Nicolas, Hartmann, Jean-Michel, Mathieu, Vincent, Ren, Guanghui, Boes, Andreas, Mitchell, Arnan, Monat, Christelle, Grillet, Christian
We report ring resonators on a silicon germanium on silicon platform operating in the mid-infrared wavelength range around 3.5 - 4.6 {\mu}m with quality factors reaching up to one million. Advances in fabrication technology enable us to demonstrate s
Externí odkaz:
http://arxiv.org/abs/2412.10269
Autor:
Zhang, Weixiang, Xie, Shuzhao, Ren, Chengwei, Xie, Siyi, Tang, Chen, Ge, Shijia, Wang, Mingzi, Wang, Zhi
We propose EVOlutionary Selector (EVOS), an efficient training paradigm for accelerating Implicit Neural Representation (INR). Unlike conventional INR training that feeds all samples through the neural network in each iteration, our approach restrict
Externí odkaz:
http://arxiv.org/abs/2412.10153
Autor:
Shi, Zican, Hu, Jing, Ren, Jie, Ye, Hengkang, Yuan, Xuyang, Ouyang, Yan, He, Jia, Ji, Bo, Guo, Junyu
The introduction of Feature Pyramid Network (FPN) has significantly improved object detection performance. However, substantial challenges remain in detecting tiny objects, as their features occupy only a very small proportion of the feature maps. Al
Externí odkaz:
http://arxiv.org/abs/2412.10116