Zobrazeno 1 - 10
of 11 512
pro vyhledávání: '"ZHAO, YUAN"'
Autor:
Yao, Kai, Tan, Zhaorui, Ye, Tiandi, Li, Lichun, Zhao, Yuan, Liu, Wenyan, Wang, Wei, Zhu, Jianke
Offsite-tuning is a privacy-preserving method for tuning large language models (LLMs) by sharing a lossy compressed emulator from the LLM owners with data owners for downstream task tuning. This approach protects the privacy of both the model and dat
Externí odkaz:
http://arxiv.org/abs/2412.09812
Autor:
Zhao, Xiaoqi, Pang, Youwei, Chang, Shijie, Zhao, Yuan, Zhang, Lihe, Lu, Huchuan, Ouyang, Jinsong, Fakhri, Georges El, Liu, Xiaofeng
As a foundational model, SAM has significantly influenced multiple fields within computer vision, and its upgraded version, SAM 2, enhances capabilities in video segmentation, poised to make a substantial impact once again. While SAMs (SAM and SAM 2)
Externí odkaz:
http://arxiv.org/abs/2412.01240
Parameter-Efficient Fine-Tuning (PEFT) methods have gained significant popularity for adapting pre-trained Large Language Models (LLMs) to downstream tasks, primarily due to their potential to significantly reduce memory and computational overheads.
Externí odkaz:
http://arxiv.org/abs/2410.11772
Autor:
Vermani, Ayesha, Dowling, Matthew, Jeon, Hyungju, Jordan, Ian, Nassar, Josue, Bernaerts, Yves, Zhao, Yuan, Van Vaerenbergh, Steven, Park, Il Memming
Function and dysfunctions of neural systems are tied to the temporal evolution of neural states. The current limitations in showing their causal role stem largely from the absence of tools capable of probing the brain's internal state in real-time. T
Externí odkaz:
http://arxiv.org/abs/2409.01280
Automatic Video Dubbing (AVD) aims to take the given script and generate speech that aligns with lip motion and prosody expressiveness. Current AVD models mainly utilize visual information of the current sentence to enhance the prosody of synthesized
Externí odkaz:
http://arxiv.org/abs/2408.11593
Autor:
Zhao, Yuan-yuan, Yue, Fuyong, Gao, Feng, Wang, Qibing, Li, Chao, Liu, Zichen, Wang, Lei, He, Zhixue
Entanglement distribution is a critical technique that enables numerous quantum applications. Most fiber-based long-distance experiments reported to date have utilized photon pair sources generated in bulk optical crystals, with the entanglement enco
Externí odkaz:
http://arxiv.org/abs/2407.21305
Excited states (ESs) of two- and three-dimensional (2D and 3D) solitons of the semivortex (SV) and mixed-mode (MM) types, supported by the interplay of the spin-orbit coupling (SOC) and local nonlinearity in binary Bose-Einstein condensates, are unst
Externí odkaz:
http://arxiv.org/abs/2407.19432
Autor:
Zhao, Yuan-Sheng, Huang, Xu-Guang
Publikováno v:
Chin. Phys. C48, 084103 (2024)
The chiral magnetic wave (CMW) is a collective mode in quark-gluon plasma originated from the chiral magnetic effect (CME) and chiral separation effect. Its detection in heavy-ion collisions is challenging due to significant background contamination.
Externí odkaz:
http://arxiv.org/abs/2407.00926
State-space graphical models and the variational autoencoder framework provide a principled apparatus for learning dynamical systems from data. State-of-the-art probabilistic approaches are often able to scale to large problems at the cost of flexibi
Externí odkaz:
http://arxiv.org/abs/2403.01371
Autor:
Lee, Patrick, Trujillo, Alain Chirino, Plancarte, Diana Cuevas, Ojo, Olumide Ebenezer, Liu, Xinyi, Shode, Iyanuoluwa, Zhao, Yuan, Peng, Jing, Feldman, Anna
This study investigates the computational processing of euphemisms, a universal linguistic phenomenon, across multiple languages. We train a multilingual transformer model (XLM-RoBERTa) to disambiguate potentially euphemistic terms (PETs) in multilin
Externí odkaz:
http://arxiv.org/abs/2401.14526