Výsledky vyhledávání

Report

Extension of compressive sampling to binary vector recovery for model-based defect imaging

Common imaging techniques for detecting structural defects typically require sampling at more than twice the spatial frequency to achieve a target resolution. This study introduces a novel framework for imaging structural defects using significantly

Externí odkaz: http://arxiv.org/abs/2412.01055

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Report

Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models

Autor: Zhang, Fuxiang, Li, Junyou, Li, Yi-Chen, Zhang, Zongzhang, Yu, Yang, Ye, Deheng

Low sample efficiency is an enduring challenge of reinforcement learning (RL). With the advent of versatile large language models (LLMs), recent works impart common-sense knowledge to accelerate policy learning for RL processes. However, we note that

Externí odkaz: http://arxiv.org/abs/2407.03964

Zobrazit plný text záznamu

Report

Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation

Autor: Li, Yi-Chen, Zhang, Fuxiang, Qiu, Wenjie, Yuan, Lei, Jia, Chengxing, Zhang, Zongzhang, Yu, Yang, An, Bo

Large Language Models (LLMs), trained on a large amount of corpus, have demonstrated remarkable abilities. However, it may not be sufficient to directly apply open-source LLMs like Llama to certain real-world scenarios, since most of them are trained

Externí odkaz: http://arxiv.org/abs/2407.03856

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Report

BWArea Model: Learning World Model, Inverse Dynamics, and Policy for Controllable Language Generation

Autor: Jia, Chengxing, Wang, Pengyuan, Li, Ziniu, Li, Yi-Chen, Zhang, Zhilong, Tang, Nan, Yu, Yang

Large language models (LLMs) have catalyzed a paradigm shift in natural language processing, yet their limited controllability poses a significant challenge for downstream applications. We aim to address this by drawing inspiration from the neural me

Externí odkaz: http://arxiv.org/abs/2405.17039

Zobrazit plný text záznamu

Report

Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning

Autor: Lin, Haoxin, Xu, Yu-Yan, Sun, Yihao, Zhang, Zhilong, Li, Yi-Chen, Jia, Chengxing, Ye, Junyin, Zhang, Jiaji, Yu, Yang

Model-based methods in reinforcement learning offer a promising approach to enhance data efficiency by facilitating policy exploration within a dynamics model. However, accurately predicting sequential steps in the dynamics model remains a challenge

Externí odkaz: http://arxiv.org/abs/2405.17031

Zobrazit plný text záznamu

Report

Revealing the Boundary between Quantum Mechanics and Classical Model by EPR-Steering Inequality

Autor: Wang, Ruo-Chen, Li, Zhuo-Chen, Fan, Xing-Yan, Xie, Xiang-Ru, Wei, Hong-Hao, Oh, Choo Hiap, Chen, Jing-Ling

In quantum information, the Werner state is a benchmark to test the boundary between quantum mechanics and classical models. There have been three well-known critical values for the two-qubit Werner state, i.e., $V_{\rm c}^{\rm E}=1/3$ characterizing

Externí odkaz: http://arxiv.org/abs/2404.04048

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Vyhledávací nástroje:

Upřesnit hledání