Výsledky vyhledávání - "Niu, Xiaoguang"

Report

Efficient Diversity-based Experience Replay for Deep Reinforcement Learning

Autor: Zhao, Kaiyan, Wang, Yiming, Chen, Yuyang, Niu, Xiaoguang, Li, Yan, U, Leong Hou

Deep Reinforcement Learning (DRL) has achieved remarkable success in solving complex decision-making problems by combining the representation capabilities of deep learning with the decision-making power of reinforcement learning. However, learning in

Externí odkaz: http://arxiv.org/abs/2410.20487

Zobrazit plný text záznamu

Report

Enhancing LLM Agents for Code Generation with Possibility and Pass-rate Prioritized Experience Replay

Autor: Chen, Yuyang, Zhao, Kaiyan, Wang, Yiming, Yang, Ming, Zhang, Jian, Niu, Xiaoguang

Nowadays transformer-based Large Language Models (LLM) for code generation tasks usually apply sampling and filtering pipelines. Due to the sparse reward problem in code generation tasks caused by one-token incorrectness, transformer-based models wil

Externí odkaz: http://arxiv.org/abs/2410.12236

Zobrazit plný text záznamu

Report

Rethinking Cross-Attention for Infrared and Visible Image Fusion

Autor: Jian, Lihua, Xiong, Songlei, Yan, Han, Niu, Xiaoguang, Wu, Shaowu, Zhang, Di

The salient information of an infrared image and the abundant texture of a visible image can be fused to obtain a comprehensive image. As can be known, the current fusion methods based on Transformer techniques for infrared and visible (IV) images ha

Externí odkaz: http://arxiv.org/abs/2401.11675

Zobrazit plný text záznamu