Zobrazeno 1 - 10
of 4 344
pro vyhledávání: '"lin, Sen"'
This work investigates the application of Machine Unlearning (MU) for mitigating the impact of trojans embedded in conventional large language models of natural language (Text-LLMs) and large language models of code (Code-LLMs) We propose a novel unl
Externí odkaz:
http://arxiv.org/abs/2408.12416
Autor:
Wang, Zhiren, Lin, Sen, Dantec, Marianne Le, Rančić, Miloš, Goldner, Philippe, Bertaina, Sylvain, Chanelière, Thierry, Liu, Ren-Bao, Esteve, Daniel, Vion, Denis, Flurin, Emmanuel, Bertet, Patrice
Rare-earth-ion (REI) ensembles in crystals have remarkable optical and spin properties characterized by narrow homogeneous linewidths relative to the inhomogeneous ensemble broadening. This makes it possible to precisely tailor the ensemble spectral
Externí odkaz:
http://arxiv.org/abs/2408.12758
Robotic arms are key components in fruit-harvesting robots. In agricultural settings, conventional serial or parallel robotic arms often fall short in meeting the demands for a large workspace, rapid movement, enhanced capability of obstacle avoidanc
Externí odkaz:
http://arxiv.org/abs/2407.19826
Continual learning (CL) has garnered significant attention because of its ability to adapt to new tasks that arrive over time. Catastrophic forgetting (of old tasks) has been identified as a major issue in CL, as the model adapts to new tasks. The Mi
Externí odkaz:
http://arxiv.org/abs/2406.16437
In this paper, we study offline-to-online Imitation Learning (IL) that pretrains an imitation policy from static demonstration data, followed by fast finetuning with minimal environmental interaction. We find the na\"ive combination of existing offli
Externí odkaz:
http://arxiv.org/abs/2405.17477
Offline Imitation Learning (IL) with imperfect demonstrations has garnered increasing attention owing to the scarcity of expert data in many real-world domains. A fundamental problem in this scenario is how to extract positive behaviors from noisy da
Externí odkaz:
http://arxiv.org/abs/2405.17476
Autor:
Huang, Tianyi, Lin, Sen, Zou, Jingyi, Wang, Zexiao, Zhong, Yibai, Li, Jingwei, Wang, Ruixuan, Wang, Han, Li, Qing, Xu, Min, Shen, Sheng, Zhang, Xu
Recently tellurium (Te) has attracted resurgent interests due to its p-type characteristics and outstanding ambient environmental stability. Here we present a substrate engineering based physical vapor deposition method to synthesize high-quality Te
Externí odkaz:
http://arxiv.org/abs/2404.14681
Autor:
Liu, Xiu, Zhong, Yibai, Wang, Zexiao, Huang, Tianyi, Lin, Sen, Zou, Jingyi, Wang, Haozhe, Wang, Zhien, Li, Zhuo, Luo, Xiao, Cheng, Rui, Li, Jiayu, Yun, Hyeong Seok, Wang, Han, Kong, Jing, Zhang, Xu, Shen, Sheng
Active metasurfaces have recently emerged as compact, lightweight, and efficient platforms for dynamic control of electromagnetic fields and optical responses. However, the complexities associated with their post-fabrication tunability significantly
Externí odkaz:
http://arxiv.org/abs/2403.07145
In this paper, we present Gauss's law-preserving spectral methods and their efficient solution algorithms for curl-curl source and eigenvalue problems in two and three dimensions arising from Maxwell's equations. Arbitrary order $H(curl)$-conforming
Externí odkaz:
http://arxiv.org/abs/2402.19125
Graph analysis is fundamental in real-world applications. Traditional approaches rely on SPARQL-like languages or clicking-and-dragging interfaces to interact with graph data. However, these methods either require users to possess high programming sk
Externí odkaz:
http://arxiv.org/abs/2401.12672