2

面向动态环境的智能体自我进化综述

Xikun Bao, Xulong Zhang, Xiaoyang Qu, Xiaojun Ni, Hui Tian, Jianzong Wang

Last updated on Feb 9, 2026

具身智能VLA的多模态感知技术综述

Jiangmeng Zhou, Aolan Sun, Xiaoyang Qu, Xulong Zhang, Jianzong Wang

Last updated on Dec 15, 2025

基于潜空间拼接与对比学习的语音匿名方法研究

Xulong Zhang, Xiaoyang Qu, Xiaojun Ni, Hui Tian, Jianzong Wang

Last updated on Dec 15, 2025

多代码智能体研究与应用综述

Xulong Zhang, Xikun Bao, Xiaoyang Qu, Xiaojun Ni, Hui Tian, Jianzong Wang

Last updated on Dec 15, 2025

大型视觉语言模型幻觉综述

Xulong Zhang, Peng Pan, Xiaoyang Qu, Xiaojun Ni, Hui Tian, Jianzong Wang

Last updated on Dec 15, 2025

结合少样本逻辑推理的多模态机器人故障解释一致性方法

Qihua Weng, Yuchen Han, Xulong Zhang, Fagui Liu, Xiaojun Ni, Hui Tian, Jianhan Wu, Jianzong Wang

Last updated on Nov 22, 2025

基于多智能体协作的移动边缘计算任务卸载及调度策略

Jiaqi Shi, Xulong Zhang, Xiaoyang Qu, Xiaojun Ni, Hui Tian, Jianzong Wang

Last updated on Nov 22, 2025

Knowledge Distillation for Financial Large Language Models: A Systematic Review of Strategies, Applications, and Evaluation

Jiaqi Shi, Xulong Zhang, Xiaoyang Qu, Junfei Xie, Jianzong Wang

Knowledge Distillation for Financial Large Language Models: A Systematic Review of Strategies, Applications, and Evaluation

面向具身智能的视觉-语言-动作模型动作表征和生成策略综述

视觉-语言-动作模型是实现具身智能的核心路径，其核心在于将多模态感知理解无缝转化为物理世界的具体行动。然而，动作表征与生成策略作为连接“感知”与“执行”的枢纽环节，面临着高维连续空间、动作多样性与机器人实时控制需求间的复杂挑战。该综述系统性地梳理和总结了VLA模型中动作 …

Wentao Zhang, Aolan Sun, Xiaoyang Qu, Xulong Zhang, Jianzong Wang

Last updated on Oct 27, 2025

Robust Detection of Partially Spoofed Audio Using Semantic-Aware Inconsistency Learning

Partially spoofed technology subtly manipulates interested parts in an audio to alter the original meaning, with its fine-grained …

Jialu Cao, Hui Tian, Peng Tian, Haizhou Li, Jianzong Wang