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)

共收录 702
2604.21393 2026-04-24 cs.LG

Relocation of compact sets in $\mathbb{R}^n$ by diffeomorphisms and linear separability of datasets in $\mathbb{R}^n$

在R^n中通过微分同胚移动紧集及R^n中数据集的线性可分性

Xiao-Song Yang, Xuan Zhou, Qi Zhou

机构 * School of Mathematics and Statistics, Huazhong University of Science and Technology(华中科技大学数学与统计学院) Hubei Key Laboratory of Engineering Modeling and Scientific Computing, Huazhong University of Science and Technology(湖北省工程建模与科学计算重点实验室)

AI总结 本文研究了通过微分同胚将R^n中的紧集移动到任意目标域的理论,并证明了在R^{n+1}中可通过深度神经网络实现数据集的线性可分性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.21308 2026-04-24 cs.CR cs.CL

CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents

CI-Work: 企业LLM代理中情境完整性基准测试

Wenjie Fu, Xiaoting Qin, Jue Zhang, Qingwei Lin, Lukas Wutschitz, Robert Sim, Saravan Rajmohan, Dongmei Zhang

机构 * Huazhong University of Science and Technology(华中科技大学) Microsoft(微软)

AI总结 CI-Work基准测试评估企业LLM代理在密集检索中传达关键内容并隐藏敏感信息的能力,揭示隐私泄露普遍且高任务效用与隐私违规正相关,需转向以情境为中心的架构。

Journal ref The 64th Annual Meeting of the Association for Computational Linguistics (ACL'2026) -- Industry Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.20311 2026-04-24 cs.MM cs.AI

Seeing Further and Wider: Joint Spatio-Temporal Enlargement for Micro-Video Popularity Prediction

看得更远且更广:面向微视频流行度预测的联合时空放大

Dali Wang, Yunyao Zhang, Junqing Yu, Yi-Ping Phoebe Chen, Chen Xu, Zikai Song

机构 * Huazhong University of Science and Technology(华中科技大学) La Trobe University(拉特罗布大学) Beijing Institute of Computer Technology and Applications(北京计算机技术与应用研究所)

AI总结 本文提出联合时空放大框架,通过时空增强模块提升微视频流行度预测的精度与可扩展性,实验表明其在主流指标上优于11个基线方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.24765 2026-04-23 cs.AI

Semantic-Aware Logical Reasoning via a Semiotic Framework

通过象征框架实现语义感知的逻辑推理

Yunyao Zhang, Xinglang Zhang, Junxi Sheng, Wenbing Li, Junqing Yu, Yi-Ping Phoebe Chen, Wei Yang, Zikai Song

机构 * Huazhong University of Science and Technology(华中科技大学) La Trobe University(拉筹伯大学)

AI总结 本文提出LogicAgent框架,结合自动推演与反思验证,解决逻辑复杂性与语义复杂性的交互问题,通过RepublicQA基准验证其在抽象命题和逻辑深度上的表现,实现SOTA性能。

Comments Accepted at ACL 2026 (Main Conference)

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.19432 2026-04-22 cs.CV

DINO Eats CLIP: Adapting Beyond Knowns for Open-set 3D Object Retrieval

DINO Eats CLIP:超越已知领域进行开放集3D物体检索

Xinwei He, Yansong Zheng, Qianru Han, Zhichuan Wang, Yuxuan Cai, Yang Zhou, Jingbo Xia, Yulong Wang, Jinhai Xiang, Xiang Bai

机构 * Huazhong Agricultural University(华中农业大学) Huazhong University of Science and Technology(华中科技大学) Shenzhen University(深圳大学)

AI总结 本文提出DEC框架,通过动态多视图整合和虚拟特征合成模块,提升开放集3D物体检索的性能,解决已知类别过拟合问题。

Comments Accepted to CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.19349 2026-04-22 cs.CV

RAFT-MSF++: Temporal Geometry-Motion Feature Fusion for Self-Supervised Monocular Scene Flow

RAFT-MSF++: 基于时间几何-运动特征融合的自监督单目场景流估计

Xunpei Sun, Zuoxun Hou, Yi Chang, Gang Chen, Wei-Shi Zheng

机构 * School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院) Beijing Institute of Space Mechanics and Electricity(北京空间机械与电子研究所) 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)

AI总结 RAFT-MSF++提出一种自监督多帧框架,通过递归融合时间特征联合估计深度和场景流,引入几何-运动特征模块和遮挡正则化模块提升鲁棒性,实验显示在KITTI数据集上取得优异性能。

Comments This work has been submitted to the IEEE for possible publication

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.21954 2026-04-22 cs.SE cs.AI

Fine-Tuning Code Language Models to Detect Cross-Language Bugs

对代码语言模型进行微调以检测跨语言错误

Zengyang Li, Yimeng Li, Binbin Huang, Peng Liang, Ran Mo, Hui Liu, Yutao Ma

机构 * School of Computer Science, Central China Normal University(中央师范大学计算机科学学院) State Key Laboratory for Novel Software Technology, Nanjing University(南京大学新型软件技术国家重点实验室) School of Computer Science, Wuhan University(武汉大学计算机学院) 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)

AI总结 本文研究预训练代码语言模型在跨语言错误检测中的潜力,开发了CLCFinder工具并构建了包含三种编程语言组合的跨语言错误数据集,通过微调13种CodeLMs发现小模型表现优于大模型,且数据集规模和代码注释对性能影响各异。

Comments Preprint accepted for publication in ACM Transactions on Software Engineering and Methodology (TOSEM), 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.16161 2026-04-22 cs.CV cs.CL

OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models

OmniParser V2:结构化思维点用于统一的视觉文本解析及其在多模态大语言模型中的通用性

Wenwen Yu, Zhibo Yang, Jianqiang Wan, Sibo Song, Jun Tang, Wenqing Cheng, Yuliang Liu, Xiang Bai

机构 * School of Information Science and Engineering, East China University of Science and Technology(东华大学信息科学与工程学院) 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) School of Software Engineering, Huazhong University of Science and Technology(华中科技大学软件工程学院) School of Electronic Information and Communications, Huazhong University of Science and Technology(华中科技大学电子信息与通信学院) Alibaba Group(阿里巴巴集团)

AI总结 本文提出OmniParser V2,通过结构化思维点提示方案统一视觉文本解析任务,简化流程并提升性能,在多个数据集上取得最佳结果,并验证其在多模态大语言模型中的通用性。

Comments Accepted by IEEE TPAMI

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.18275 2026-04-22 cs.CV

Visual Adversarial Attack on Vision-Language Models for Autonomous Driving

面向自动驾驶的视觉对抗攻击研究

Tianyuan Zhang, Lu Wang, Xinwei Zhang, Yitong Zhang, Boyi Jia, Siyuan Liang, Shengshan Hu, Qiang Fu, Aishan Liu, Xianglong Liu

机构 * Beihang University(北航) National University of Singapore(国立新加坡大学) Huazhong University of Science and Technology(华中科技大学)

AI总结 本文提出ADvLM框架,针对自动驾驶中视觉语言模型的特殊需求,解决文本指令变异性和视觉场景时间序列性问题,实现高效对抗攻击。

Comments Accepted by Machine Intelligence Research

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.17880 2026-04-21 cs.RO cs.CV

ST-$π$: Structured SpatioTemporal VLA for Robotic Manipulation

ST-$π$: 结构化时空VLA用于机器人操作

Chuanhao Ma, Hanyu Zhou, Shihan Peng, Yan Li, Tao Gu, Luxin Yan

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) School of Computing, National University of Singapore(新加坡国立大学计算机学院) School of Computing, Macquarie University(麦考瑞大学计算机学院)

AI总结 本文提出ST-$π$模型,通过结构化时空视觉语言模型和动作专家,解决机器人操作中精细时空推理问题,同时引入结构化时空标注数据集进行训练。

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.17842 2026-04-21 eess.SP cs.LG

Canine EEG Helps Human: Cross-Species and Cross-Modality Epileptic Seizure Detection via Multi-Space Alignment

犬类EEG帮助人类:通过多空间对齐实现跨物种和跨模态的癫痫发作检测

Z. Wang, S. Li, Dongrui Wu

机构 * Ministry of Education Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(教育部图像处理与智能控制重点实验室,人工智能与自动化学院,华中科技大学) Hubei Key Laboratory of Brain-inspired Intelligent Systems, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(湖北省脑启发智能系统重点实验室,人工智能与自动化学院,华中科技大学)

AI总结 本文提出基于跨物种和跨模态EEG数据的多空间对齐方法,利用深度学习技术提升癫痫发作检测能力,实验显示在有限标注数据下,检测准确率超过90%。

Journal ref National Science Review, 12(6):nwaf086, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.14461 2026-04-21 cs.CV

Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering

Ouroboros: 单步扩散模型用于循环一致的正向与反向渲染

Shanlin Sun, Yifan Wang, Hanwen Zhang, Yifeng Xiong, Qin Ren, Ruogu Fang, Xiaohui Xie, Chenyu You

机构 * University of California, Irvine(加州大学伊维特分校) Stony Brook University(石溪大学) Huazhong University of Science and Technology(华中科技大学) University of Florida(佛罗里达大学)

AI总结 Ouroboros通过双单步扩散模型实现正反向渲染的互促,扩展了内在分解到室内外场景,并引入循环一致性机制,实验显示其在多样场景中表现优异且推理速度显著提升。

Comments Accepted by ICCV 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.04638 2026-04-21 cs.CL cs.AI

SpeechMedAssist: Efficiently and Effectively Adapting Speech Language Models for Medical Consultation

SpeechMedAssist: 有效且高效地适应语音语言模型用于医疗咨询

Sirry Chen, Jieyi Wang, Wei Chen, Zhongyu Wei

机构 * Fudan University(复旦大学) Shanghai Innovation Institude(上海创新研究院) Peking University(北京大学) Huazhong University of Science and Technology(华中科技大学)

AI总结 本文提出SpeechMedAssist,一种能进行语音多轮交互的语音语言模型,通过分阶段训练减少对医疗语音数据的需求,提升医疗咨询场景下的效果和鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06296 2026-04-21 cs.PL cs.AI

VeriEquivBench: An Equivalence Score for Ground-Truth-Free Evaluation of Formally Verifiable Code

VeriEquivBench:一种无需真实地面真相的正式可验证代码评估等价分数

Lingfei Zeng, Fengdi Che, Xuhan Huang, Fei Ye, Xu Xu, Binhang Yuan, Jie Fu

机构 * Huazhong University of Science and Technology(华中科技大学) University of Alberta(阿尔伯塔大学) The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)) Hong Kong University of Science and Technology(香港科技大学) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)

AI总结 本文提出VeriEquivBench,通过2389个复杂算法问题评估正式可验证代码的生成与推理能力,揭示当前LLM在生成正式规范和代码方面的挑战,推动可扩展可靠编码代理的发展。

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.13068 2026-04-21 cs.CR cs.AI cs.LG

Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment

揭示LLM安全对齐中的logit抑制漏洞

Yuxi Li, Yi Liu, Yuekang Li, Ling Shi, Gelei Deng, Shengquan Chen, Kailong Wang

机构 * Huazhong University of Science and Technology(华中科技大学) Nanyang Technological University(南洋理工大学) University of New South Wales(新南威尔士大学) Nankai University(南开大学)

AI总结 本文提出SSAG方法,通过系统操控输出层logit揭示LLM安全对齐的漏洞,实验显示其在五种主流模型上以95%成功率暴露有害响应,同时减少86%的响应时间。

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.13243 2026-04-21 cs.CV cs.RO

VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning

VADv2:通过概率规划实现端到端向量自主驾驶

Bo Jiang, Shaoyu Chen, Hao Gao, Bencheng Liao, Qian Zhang, Wenyu Liu, Xinggang Wang

机构 * Huazhong University of Science and Technology(华中科技大学) Horizon Robotics

AI总结 本文提出VADv2,一种基于概率规划的端到端自主驾驶模型,通过概率场函数建模动作空间到概率分布的映射,利用大规模驾驶演示提升闭合回路性能,优于现有方法。

Comments Accepted to ICLR 2026. Code is available at https://github.com/hustvl/VAD

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.16004 2026-04-20 cs.CL cs.AI

AgentV-RL: Scaling Reward Modeling with Agentic Verifier

AgentV-RL: 通过代理验证器扩展奖励建模

Jiazheng Zhang, Ziche Fu, Zhiheng Xi, Wenqing Jing, Mingxu Chai, Wei He, Guoqiang Zhang, Chenghao Fan, Chenxin An, Wenxiang Chen, Zhicheng Liu, Haojie Pan, Dingwei Zhu, Tao Gui, Qi Zhang, Xuanjing Huang

机构 * College of Computer Science and Artificial Intelligence, Fudan University(复旦大学计算机科学与人工智能学院) Huazhong University of Science and Technology(华中科技大学) The University of Hong Kong(香港大学) ByteDance Seed(字节跳动种子) Institute of Trustworthy Embodied AI, Fudan University(复旦大学可信具身人工智能研究院) Shanghai Key Laboratory of Multimodal Embodied AI(上海多模态具身人工智能重点实验室)

AI总结 本文提出Agentic Verifier框架,通过多轮工具增强的反思过程提升奖励建模效果,实验显示其在并行和顺序TTS任务中表现优异,4B变体超越现有最优ORMs 25.2%。

Comments ACL 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.13829 2026-04-20 cs.RO cs.AI cs.HC

ArrayTac: A Closed-loop Piezoelectric Tactile Platform for Continuously Tunable Rendering of Shape, Stiffness, and Friction

ArrayTac: 一种闭环压电触觉平台,用于连续可调的形状、刚度和摩擦力渲染

Tianhai Liang, Shiyi Guo, Baiye Cheng, Zhengrong Xue, Han Zhang, Huazhe Xu

机构 * Institute for Interdisciplinary Information Sciences, Tsinghua University(清华大学交叉信息研究院) Shanghai Qi Zhi Institute(上海启智研究院) Pokebot Inc.(Pokebot公司) School of Electronic Information and Communications, Huazhong University of Science and Technology(华中科技大学电子信息与通信学院)

AI总结 ArrayTac通过4x4驱动器阵列实现形状、刚度和摩擦力的连续可调高保真触觉渲染,展示了在心理物理实验中触觉识别和远程触觉感知的能力。

Comments Project website: https://arraytac.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.23421 2026-04-20 cs.CV

DriveLaW:Unifying Planning and Video Generation in a Latent Driving World

DriveLaW:在潜在驾驶世界中统一规划与视频生成

Tianze Xia, Yongkang Li, Lijun Zhou, Jingfeng Yao, Kaixin Xiong, Haiyang Sun, Bing Wang, Kun Ma, Guang Chen, Hangjun Ye, Wenyu Liu, Xinggang Wang

机构 * Huazhong University of Science and Technology(华中科技大学) Xiaomi EV(小米电动车)

AI总结 DriveLaW通过统一视频生成与运动规划,提升自动驾驶中的预测与规划性能,实现视频生成与轨迹规划的一致性,取得新的state-of-the-art结果。

Comments 18 pages, 6 figures, CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.23175 2026-04-20 cs.IR cs.AI

WARBERT: A Hierarchical BERT-based Model for Web API Recommendation

WARBERT:一种基于BERT的分层模型用于Web API推荐

Zishuo Xu, Yuhong Gu, Dezhong Yao

机构 * School of Software Engineering(软件工程学院) School of Computer Science and Technology(计算机科学与技术学院) Huazhong University of Science and Technology(华中科技大学) SmartX

AI总结 本文提出WARBERT模型,通过双组件特征融合和注意力机制解决Web API推荐中的语义模糊、语义细化不足和计算效率低问题,实验表明其在准确性和效率上均优于现有基线。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.14121 2026-04-16 cs.CL

Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis

正确预测,错误步骤?基于共识推理的知识图谱用于鲁棒的推理链合成

Zipeng Ling, Shuliang Liu, Shenghong Fu, Yuehao Tang, Seonil Son, Yao Wan, Xuming Hu

机构 * Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州)) University of Pennsylvania(宾夕法尼亚大学) Huazhong University of Science and Technology(华中科技大学) Hong Kong Polytechnic University(香港理工大学) RLWRLD

AI总结 本文提出CRAFT框架,通过构建共识推理知识图谱缓解LLM推理中的内部和步骤性错误,提升推理链质量,实验显示其在逻辑和数学推理基准上表现优越。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.13938 2026-04-16 cs.CV

ASTRA: Enhancing Multi-Subject Generation with Retrieval-Augmented Pose Guidance and Disentangled Position Embedding

ASTRA:通过检索增强的姿势引导和解纠缠位置嵌入增强多主体生成

Tianze Xia, Zijian Ning, Zonglin Zhao, Mingjia Wang

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

AI总结 ASTRA通过检索增强的姿势引导和解纠缠位置嵌入,解决多主体生成中身份与姿势结构的分离问题,提升姿态一致性和身份保真度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.13800 2026-04-16 cs.RO

EmbodiedClaw: Conversational Workflow Execution for Embodied AI Development

EmbodiedClaw:基于对话的多任务多场景多模型具身AI开发流程执行

Xueyang Zhou, Yihan Sun, Xijie Gong, Guiyao Tie, Pan Zhou, Lichao Sun, Yongchao Chen

机构 * School of Cyber Science and Engineering, Huazhong University of Science and Technology(华中科技大学信息科学与工程学院) 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) School of Information and Software Engineering, University of Electronic Science and Technology of China(电子科技大学信息与软件工程学院) Lehigh University(莱斯大学) College of AI, Tsinghua University(清华大学人工智能学院)

AI总结 本文提出EmbodiedClaw,通过对话实现具身AI开发流程的自动规划与执行,减少人工工程工作量,提升可执行性、一致性和可重复性。

Comments 13 pages, 7 figure

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.13756 2026-04-16 cs.CL cs.CV

MedRCube: A Multidimensional Framework for Fine-Grained and In-Depth Evaluation of MLLMs in Medical Imaging

MedRCube:面向医学影像中多模态大语言模型细粒度与深入评估的多维框架

Zhijie Bao, Fangke Chen, Licheng Bao, Chenhui Zhang, Wei Chen, Jiajie Peng, Zhongyu Wei

机构 * School of Data Science, Fudan University(复旦大学数据科学学院) Shanghai Innovation Institute(上海创新研究院) School of Integrated Circuits, Zhejiang University(浙江大学集成电路学院) School of Software Engineering, Huazhong University of Science and Technology(华中科技大学软件工程学院) School of Computer Science, Northwestern Polytechnical University(西北工业大学计算机学院)

AI总结 本文提出MedRCube框架,通过两阶段构建流程对33个MLLM进行细粒度评估,揭示先前方法无法获取的洞察,并引入可信度评估子集,发现快捷行为与诊断性能的显著正相关,引发临床部署的担忧。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.13731 2026-04-16 cs.CL

Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA

Doc-V*:多页文档视觉问答中的粗到细交互推理

Yuanlei Zheng, Pei Fu, Hang Li, Ziyang Wang, Yuyi Zhang, Wenyu Ruan, Xiaojin Zhang, Zhongyu Wei, Zhenbo Luo, Jian Luan, Wei Chen, Xiang Bai

机构 * School of Software Engineering, Huazhong University of Science and Technology(华中科技大学软件工程学院) MiLM Plus, Xiaomi Inc.(小米公司MiLM Plus团队) School of Computer Science and Technology, Huazhong University of Science and Technology(华中科技大学计算机科学与技术学院) School of Data Science, Fudan University(复旦大学数据科学学院)

AI总结 Doc-V*提出一种无OCR的智能框架,通过序列证据聚合解决多页文档VQA问题,结合语义检索和目标页面获取,提升回答准确性和证据收集效率,在五个基准测试中优于开源基线,提升领域外性能达47.9%。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.02902 2026-04-16 cs.AI cs.CL cs.LO

Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning

逻辑相变:理解大语言模型逻辑推理中的崩溃

Xinglang Zhang, Yunyao Zhang, ZeLiang Chen, Junqing Yu, Wei Yang, Zikai Song

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

AI总结 研究通过控制逻辑复杂性分析大语言模型的逻辑推理性能,发现逻辑相变现象,提出神经符号课程调优框架以提升高复杂度下的推理能力。

Comments Accepted at ACL 2026 (Main Conference)

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.12665 2026-04-15 cs.CV

Hypergraph-State Collaborative Reasoning for Multi-Object Tracking

超图状态协作推理用于多目标跟踪

Zikai Song, Junqing Yu, Yi-Ping Phoebe Chen, Wei Yang, Xinchao Wang

机构 * Huazhong University of Science and Technology(华中科技大学) National University of Singapore(新加坡国立大学)

AI总结 本文提出超图状态协作推理框架,通过多相关目标的联合推理提升运动估计稳定性,解决噪声和遮挡问题,实验显示在多个基准上性能优异。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.21045 2026-04-15 cs.CV cs.AI

LPNSR: Optimal Noise-Guided Diffusion Image Super-Resolution Via Learnable Noise Prediction

LPNSR: 通过可学习噪声预测实现最优噪声引导扩散图像超分辨率

Shuwei Huang, Shizhuo Liu, Zijun Wei

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

AI总结 本文提出LPNSR,通过可学习噪声预测器替代随机高斯噪声,优化扩散模型中的中间噪声,实现高感知性能,无需依赖大规模文本到图像先验。

详情

展开后加载摘要…

URL PDF HTML 收藏
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