arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Huazhong University of Science and Technology(华中科技大学)

2026-04-14 至 2026-04-14 共收录 5
2507.08339 2026-04-14 cs.CL

What Factors Affect LLMs and RLLMs in Financial Question Answering?

影响LLMs和RLLMs在金融问答中的因素是什么?

Peng Wang, Xuesi Hu, Jiageng Wu, Yuntao Zou, Qiancheng Zhang, Dagang Li

机构 * School of Computer Science and Engineering, Macau University of Science and Technology, China(澳门科技大学计算机科学与工程学院) SKLPlanets, Macau University of Science and Technology, China(澳门科技大学月球与行星科学国家重点实验室) School of Economics, Anhui University, China(安徽大学经济学院) School of Energy and Power Engineering, Huazhong University of Science and Technology, China(华中科技大学能源与动力工程学院)

AI总结 研究探讨了提示方法、代理框架和多语言对齐方法对LLMs和RLLMs在金融问答任务中的影响,发现提示方法和代理框架能提升LLMs性能,而RLLMs自身具备Long CoT能力,传统方法对其提升有限。

Comments Accepted by ACL 2026 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.10165 2026-04-14 cs.RO

MoRI: Mixture of RL and IL Experts for Long-Horizon Manipulation Tasks

MoRI:混合强化学习和模仿学习专家用于长 horizon � Manipulation 任务

Yaohang Xu, Lianjie Ma, Gewei Zuo, Wentao Zhang, Han Ding, Lijun Zhu

机构 * School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(华中科技大学人工智能与自动化学院) DRAGON Lab, The University of Tokyo(东京大学DRAGON实验室) School of Mechanical Science and Engineering, Huazhong University of Science and Technology(华中科技大学机械科学与工程学院)

AI总结 MoRI通过混合强化学习和模仿学习专家,动态切换处理粗略运动和精细操作,提高长horizon manipulation任务的效率和成功率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.10056 2026-04-14 cs.CV

U$^{2}$Flow: Uncertainty-Aware Unsupervised Optical Flow Estimation

U²Flow:基于不确定性的无监督光流估计

Xunpei Sun, Wenwei Lin, Yi Chang, Gang Chen

机构 * Sun Yat-sen University(中山大学) Huazhong University of Science and Technology(华中科技大学)

AI总结 U²Flow是首个联合估计光流和像素不确定性的无监督框架,通过解耦学习策略从增强一致性中获取不确定性监督,提升训练稳定性。引入不确定性引导的双向流融合机制,实验表明其在KITTI和Sintel上达到无监督方法最优,生成可靠不确定性图。

Comments Accepted as an oral presentation at CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.10031 2026-04-14 cs.CL cs.AI

CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models

CoSToM: 为大语言模型内在理论思维对齐的因果导向引导

Mengfan Li, Xuanhua Shi, Yang Deng

机构 * National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, Huazhong University of Science and Technology(华中科技大学国家大数据技术与系统工程技术研究中心、服务计算技术与系统实验室、集群与网格计算实验室) Singapore Management University(新加坡管理大学)

AI总结 本文提出CoSToM框架,通过因果追踪和激活引导提升大语言模型的社会推理能力与对话质量。

Comments Accepted to ACL 2026 (Main Conference)

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.11390 2026-04-14 cs.HC cs.LG eess.SP

PAT: Privacy-Preserving Adversarial Transfer for Accurate, Robust and Privacy-Preserving EEG Decoding

PAT: 用于准确、鲁棒且隐私保护的对抗性迁移

Xiaoqing Chen, Tianwang Jia, Yunlu Tu, Dongrui Wu

机构 * Hubei Key Laboratory of Brain-inspired Intelligent Systems, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(华中科技大学人工智能与自动化学院脑启发智能系统湖北省重点实验室) Shenzhen Huazhong University of Science and Technology Research Institute(深圳华中科技大学研究院) Zhongguancun Academy(中关村学院)

AI总结 本文提出PAT框架,结合数据对齐、对抗训练和隐私保护迁移,提升EEG解码的准确性、鲁棒性和隐私保护,实验表明其在多个数据集上优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏