arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Harbin Institute of Technology(哈尔滨工业大学)

共收录 1439
2506.15307 2026-03-03 cs.LG

SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC

SecP-Tuning: 通过MPC实现大语言模型高效隐私保护提示微调

Jinglong Luo, Zhuo Zhang, Yehong Zhang, Shiyu Liu, Ye Dong, Hui Wang, Yue Yu, Xun Zhou, Zenglin Xu

机构 * Pengcheng Laboratory(鹏城实验室) Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳)) Fudan University(复旦大学) Shanghai Academy of AI for Science(上海人工智能科学研究院) Institute of Statistical Interdisciplinary Research, Southwestern University of Finance and Economics(统计交叉学科研究所,西南财经大学) National University of Singapore(新加坡国立大学)

AI总结 SecP-Tuning通过MPC实现大语言模型高效隐私保护提示微调,显著提升微调效率并减少通信开销。

Comments ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.00155 2026-03-03 cs.CV cs.AI cs.IR

EfficientPosterGen: Semantic-aware Efficient Poster Generation via Token Compression and Accurate Violation Detection

EfficientPosterGen: 通过令牌压缩和准确违规检测的语义感知高效海报生成

Wenxin Tang, Jingyu Xiao, Yanpei Gong, Fengyuan Ran, Tongchuan Xia, Junliang Liu, Man Ho Lam, Wenxuan Wang, Michael R. Lyu

机构 * Tsinghua University(清华大学) The Chinese University of Hong Kong(香港中文大学) Harbin Institute of Technology(哈尔滨工业大学) Wuhan University(武汉大学) Beijing University of Posts and Telecommunications(北京邮电大学) Dalian Maritime University(大连海事大学) Renmin University of China(中国人民大学)

AI总结 EfficientPosterGen通过语义感知检索、视觉上下文压缩和无代理布局检测技术,实现高效且可靠的学术海报自动生成。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.00055 2026-03-03 cs.LG cs.AI

M3-AD: Reflection-aware Multi-modal, Multi-category, and Multi-dimensional Benchmark and Framework for Industrial Anomaly Detection

M3-AD:面向工业异常检测的反思-aware 多模态、多类别和多维基准与框架

Chao Huang, Yanhui Li, Yunkang Cao, Wei Wang, Hongxi Huang, Jie Wen, Wenqi Ren, Xiaochun Cao

机构 * Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区) Hunan University(湖南大学) Harbin Institute of Technology, Shenzhen(哈尔滨工业大学深圳学院)

AI总结 M3-AD提出了一种反思-aware 的多模态框架,通过RA-Monitor提升工业异常检测的鲁棒性和可靠性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.00043 2026-03-03 cs.LG cs.AI

Reinforcement Learning for Control with Probabilistic Stability Guarantee: A Finite-Sample Approach

基于概率稳定性的强化学习控制:一种有限样本方法

Minghao Han, Lixian Zhang, Chenliang Liu, Zhipeng Zhou, Jun Wang, Wei Pan

机构 * Department of Control Science Engineering, Harbin Institute of Technology, China. State Key Laboratory of Robotics Systems (HIT), Harbin Institute of Technology, China. School of Automation, Central South University, China. Department of Cognitive Robotics, Delft University of Technology, Netherlands. Department of Computer Science, University College London, UK. Department of Computer Science, University of Manchester, UK.

AI总结 本文提出L-REINFORCE算法,通过有限样本实现强化学习控制中的概率稳定性保证,提升了稳定性分析与控制器设计的能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.23969 2026-03-02 cs.MM cs.CV

MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generation

MSVBench: 向多镜头视频生成的人机水平评估迈进

Haoyuan Shi, Yunxin Li, Nanhao Deng, Zhenran Xu, Xinyu Chen, Longyue Wang, Baotian Hu, Min Zhang

机构 * Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳)) Alibaba International Digital Commerce(阿里巴巴国际数字商业)

AI总结 MSVBench通过引入分层脚本和参考图像,提出混合评估框架,验证了视频生成模型的连贯性和吸引力,并展示了其在多镜头视频生成中的有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.23945 2026-03-02 cs.CV cs.AI cs.MM

PointCoT: A Multi-modal Benchmark for Explicit 3D Geometric Reasoning

PointCoT: 一种用于显式3D几何推理的多模态基准

Dongxu Zhang, Yiding Sun, Pengcheng Li, Yumou Liu, Hongqiang Lin, Haoran Xu, Xiaoxuan Mu, Liang Lin, Wenbiao Yan, Ning Yang, Chaowei Fang, Juanjuan Zhao, Jihua Zhu, Conghui He, Cheng Tan

机构 * Xi'an Jiaotong University(西安交通大学) Tsinghua University(清华大学) Shanghai Jiao Tong University(上海交通大学) Zhejiang University(浙江大学) Nanyang Technological University(南洋理工大学) Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳)) Institute of Automation, CASIA(中国科学院自动化研究所) Taiyuan University of Technology(太原理工大学) Shanghai AI Laboratory(上海人工智能实验室)

AI总结 PointCoT通过显式链式推理提升3D几何推理能力,提出多模态基准和双流架构,实现对3D点云的高精度理解与推理。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.19862 2026-03-02 cs.CL cs.LG

REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Reasoning

REA-RL:面向高效推理的反思意识在线强化学习

Hexuan Deng, Wenxiang Jiao, Xuebo Liu, Jun Rao, Min Zhang

机构 * Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China(计算与智能学院,哈尔滨工业大学深圳学院) Zhongguancun Academy, Beijing, China(中关村学院,北京) Xiaohongshu Inc.(小红书公司)

AI总结 REA-RL通过引入反思模型和反思奖励,提升在线强化学习中推理效率和性能平衡。

Comments Accepted by ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.22623 2026-02-27 cs.LG cs.AI cs.CL

ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL

ContextRL: 通过上下文增强强化学习提升大语言模型的知识发现效率

Xingyu Lu, Jinpeng Wang, YiFan Zhang, Shijie Ma, Xiao Hu, Tianke Zhang, Haonan fan, Kaiyu Jiang, Changyi Liu, Kaiyu Tang, Bin Wen, Fan Yang, Tingting Gao, Han Li, Chun Yuan

机构 * Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院) Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳)) Chinese Academy of Sciences(中国科学院) Tsinghua University(清华大学)

AI总结 ContextRL通过上下文增强强化学习提升大语言模型的知识发现效率,有效缓解奖励黑客问题并提升性能。

Comments 14 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.22570 2026-02-27 cs.CV cs.AI

Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation

引导至关重要:重新审视文本到图像生成中的评估误区

Dian Xie, Shitong Shao, Lichen Bai, Zikai Zhou, Bojun Cheng, Shuo Yang, Jun Wu, Zeke Xie

机构 * The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州)) Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳)) Cogniser Information Technology(Cogniser信息科技)

AI总结 本文重新审视文本到图像生成中的评估误区,提出引导感知评估框架,并设计超越扩散引导方法以提升人类偏好评分。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.21944 2026-02-26 cs.CV

Learning to Fuse and Reconstruct Multi-View Graphs for Diabetic Retinopathy Grading

学习多视图图融合与重建以进行糖尿病视网膜病变分级

Haoran Li, Yuxin Lin, Huan Wang, Xiaoling Luo, Qi Zhu, Jiahua Shi, Huaming Chen, Bo Du, Johan Barthelemy, Zongyan Xue, Jun Shen, Yong Xu

机构 * Department of Data Science and Artificial Intelligence, Monash University(数据科学与人工智能系,墨尔本大学) ARC Centre of Excellence for the Weather of the 21st Century(21世纪天气卓越研究中心) School of Computing and Information Technology, University of Wollongong(计算与信息科技学院,沃林戈大学) Shenzhen Key Laboratory of Visual Object Detection and Recognition, Harbin Institute of Technology (Shenzhen)(深圳视觉目标检测与识别重点实验室,哈尔滨工业大学(深圳)) College of Computer Science and Software Engineering, Shenzhen University(计算机科学与软件工程学院,深圳大学) College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics(人工智能学院,南京航空航天大学) Centre for Nutrition and Food Sciences, The University of Queensland(营养与食品科学中心,昆士兰大学) School of Electrical and Computer Engineering, University of Sydney(电气与计算机工程学院,悉尼大学) Department of Management, Griffith University(管理学院,格里菲斯大学) NVIDIA The University of New South Wales(新南威尔士大学)

AI总结 本文提出MVGFDR框架,通过多视图图融合与重建技术提升糖尿病视网膜病变分级的准确性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.21864 2026-02-26 cs.CV cs.AI cs.CL cs.GR

DynamicGTR: Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities on Graph QAs

DynamicGTR: 利用图拓扑表示偏好提升视觉语言模型在图问答中的能力

Yanbin Wei, Jiangyue Yan, Chun Kang, Yang Chen, Hua Liu, James Kwok, Yu Zhang

机构 * Southern University of Science and Technology(南方科技大学) Hong Kong University of Science and Technology(香港理工大学) Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳)) Beihang University(北京航空航天大学)

AI总结 DynamicGTR通过动态选择最优图拓扑表示,提升视觉语言模型在图问答中的零样本性能及跨任务迁移能力。

Comments CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.21634 2026-02-26 cs.LG cs.MA

AgentLTV: An Agent-Based Unified Search-and-Evolution Framework for Automated Lifetime Value Prediction

AgentLTV: 一种基于代理的统一搜索与进化框架用于自动化生命周期价值预测

Chaowei Wu, Huazhu Chen, Congde Yuan, Qirui Yang, Guoqing Song, Yue Gao, Li Luo, Frank Youhua Chen, Mengzhuo Guo

机构 * Sichuan University(四川大学) Harbin Institute of Technology(哈尔滨工业大学) Sun Yat-sen University(中山大学) City University of Hong Kong(香港城市大学) Xiangtan University(湘潭大学)

AI总结 AgentLTV通过基于代理的统一搜索与进化框架,实现自动化生命周期价值预测,通过MCTS和EA阶段优化模型,提升预测准确性和稳定性。

Comments 12 pages, 4 figures, submitted to KDD 2026: 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, ADS Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03255 2026-02-26 cs.LG cs.AI

SciTS: Scientific Time Series Understanding and Generation with LLMs

SciTS: 基于大语言模型的科学时间序列理解与生成

Wen Wu, Ziyang Zhang, Liwei Liu, Xuenan Xu, Jimin Zhuang, Ke Fan, Qitan Lv, Junlin Liu, Chen Zhang, Zheqi Yuan, Siyuan Hou, Tianyi Lin, Kai Chen, Bowen Zhou, Chao Zhang

机构 * Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Tsinghua University(清华大学) Harbin Institute of Technology(哈尔滨工业大学) University of Science and Technology of China(中国科学技术大学)

AI总结 SciTS提出了一种基于LLM的科学时间序列理解与生成框架,通过基准测试发现通用LLM在泛化能力上优于专门模型,并引入TimeOmni框架提升性能。

Comments Accepted to ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06060 2026-02-26 cs.CL cs.AI

Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models

简单而有效的:在联邦微调大型语言模型中提取客户端私有数据

Yingqi Hu, Zhuo Zhang, Jingyuan Zhang, Jinghua Wang, Qifan Wang, Lizhen Qu, Zenglin Xu

机构 * Harbin Institute of Technology(哈尔滨工业大学) Kuaishou Technology(快手科技) Meta AI Monash University(墨尔本大学) Fudan University(复旦大学) Shanghai Academy of Artificial Intelligence for Science(上海人工智能科学研究院)

AI总结 本文提出三种简单有效的方法,用于在联邦微调大型语言模型中提取客户端私有数据,揭示了FedLLMs中的隐私风险并建立了评估框架。

Comments IJCNLP 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.20976 2026-02-25 cs.CL cs.CY

Evaluating Proactive Risk Awareness of Large Language Models

评估大型语言模型的前瞻性风险意识

Xuan Luo, Yubin Chen, Zhiyu Hou, Linpu Yu, Geng Tu, Jing Li, Ruifeng Xu

机构 * The Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳)) The Hong Kong Polytechnic University, Hong Kong(香港理工大学) Southern University of Science and Technology, Shenzhen(南方科技大学) Shenzhen Loop Area Institute, Shenzhen, China(深圳南山区研究院)

AI总结 本文提出前瞻性风险意识评估框架,通过Butterfly数据集评估LLMs在生态领域预见潜在危害的能力,发现响应长度限制和多模态保护盲点等问题,强调部署LLM时需加强主动防护。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.14297 2026-02-25 cs.CR cs.CL

A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness

一种利用大语言模型帮助性的简单高效逃逸方法

Xuan Luo, Yue Wang, Zefeng He, Geng Tu, Jing Li, Ruifeng Xu

机构 * The Harbin Institute of Technology(哈尔滨工业大学) The Hong Kong Polytechnic University(香港理工大学) Shenzhen University(深圳大学) Shenzhen Loop Area Institute(深圳河套学院)

AI总结 本研究提出了一种利用大语言模型帮助性的简单高效逃逸方法,通过重构范式HILL在多种模型上实现高攻击成功率,揭示了安全机制的局限性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.20850 2026-02-25 cs.RO

KCFRC: Kinematic Collision-Aware Foothold Reachability Criteria for Legged Locomotion

KCFRC:用于腿部运动的运动学碰撞感知脚部可达性准则

Lei Ye, Haibo Gao, Huaiguang Yang, Peng Xu, Haoyu Wang, Tie Liu, Junqi Shan, Zongquan Deng, Liang Ding

机构 * State Key Laboratory of Robotics and Systems, Harbin Institute of Technology(机器人系统国家重点实验室,哈尔滨工业大学)

AI总结 KCFRC通过高效脚部可达性分析提升腿部机器人在复杂环境中的适应性和鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.20187 2026-02-25 eess.IV cs.AI

AINet: Anchor Instances Learning for Regional Heterogeneity in Whole Slide Image

AINet: 区域异质性在全切片图像中的锚实例学习

Tingting Zheng, Hongxun Yao, Kui Jiang, Sicheng Zhao, Yi Xiao

机构 * Harbin Institute of Technology(哈尔滨工业大学) Tsinghua University(清华大学) Zhengzhou University(郑州大学)

AI总结 AINet通过锚实例学习解决全切片图像中区域异质性问题,采用双层锚实例挖掘和锚引导区域校正模块,提升模型性能并减少计算资源消耗。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.08435 2026-02-25 cs.RO

PegasusFlow: Parallel Rolling-Denoising Score Sampling for Robot Diffusion Planner Flow Matching

PegasusFlow: 并行滚动去噪分数采样用于机器人扩散规划流程匹配

Lei Ye, Haibo Gao, Peng Xu, Zhelin Zhang, Junqi Shan, Ao Zhang, Wei Zhang, Ruyi Zhou, Zongquan Deng, Liang Ding

机构 * State Key Laboratory of Robotics and Systems, Harbin Institute of Technology(机器人系统国家重点实验室,哈尔滨工业大学)

AI总结 PegasusFlow通过并行滚动去噪分数采样方法,实现了无需专家数据的机器人轨迹规划,显著提升了复杂地形中的导航性能。

Comments 8 pages, 7 figures, conference paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.17404 2026-02-25 cs.CV

MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling

MoSA: 通过结构-外观解耦生成运动一致的人体视频

Haoyu Wang, Hao Tang, Donglin Di, Zhilu Zhang, Wangmeng Zuo, Feng Gao, Siwei Ma, Shiliang Zhang

机构 * State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(多媒体信息处理国家重点实验室,计算机学院,北京大学) School of Arts(艺术学院) Li Auto(力汽车) Harbin Institute of Technology(哈尔滨工业大学)

AI总结 MoSA通过结构-外观解耦生成运动一致的人体视频,引入Human-Aware Dynamic Control模块和接触约束,提升细粒度控制与人-环境交互建模,实现更逼真的人体视频生成。

Comments Accepted by ICLR 2026. Project: https://hywang2002.github.io/MoSA

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.19870 2026-02-24 cs.CV

ApET: Approximation-Error Guided Token Compression for Efficient VLMs

ApET:基于近似误差的令牌压缩用于高效的视觉语言模型

Qiankun Ma, Ziyao Zhang, Haofei Wang, Jie Chen, Zhen Song, Hairong Zheng

机构 * Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究所) Peng Cheng Laboratory(鹏城实验室) University of Chinese Academy of Sciences(中国科学院大学) Harbin Institute of Technology(哈尔滨工业大学) Peking University(北京大学)

AI总结 ApET通过近似误差指导的令牌压缩,在不使用注意力机制的情况下高效压缩视觉语言模型的令牌预算,提升推理效率。

Comments CVPR2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.19764 2026-02-24 cs.RO

Towards Dexterous Embodied Manipulation via Deep Multi-Sensory Fusion and Sparse Expert Scaling

通过深度多感官融合与稀疏专家扩展实现灵巧的具身体验

Yirui Sun, Guangyu Zhuge, Keliang Liu, Jie Gu, Zhihao xia, Qionglin Ren, Chunxu tian, Zhongxue Ga

机构 * College of Intelligent Robotics and Advanced Manufacturing, Fudan University(智能机器人与先进制造学院,复旦大学) School of Information Science and Engineering, Harbin Institute of Technology(信息科学与工程学院,哈尔滨工业大学)

AI总结 DeMUSE通过深度多感官融合与稀疏专家扩展,实现复杂物理互动的高成功率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.19198 2026-02-24 cs.CV

Prompt Tuning for CLIP on the Pretrained Manifold

在预训练流形上进行CLIP的提示调优

Xi Yang, Yuanrong Xu, Weigang Zhang, Guangming Lu, David Zhang, Jie Wen

机构 * Guizhou University, Guiyang, China(贵州大学) Harbin Institute of Technology, China(哈尔滨工业大学) The Chinese University of Hong Kong, Shenzhen, China(香港中文大学(深圳))

AI总结 ManiPT通过在预训练流形上进行提示调优,引入余弦一致性约束和结构偏差,以提高模型在有限监督下的泛化能力和转移性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.18880 2026-02-24 cs.CV cs.AI

FOCA: Frequency-Oriented Cross-Domain Forgery Detection, Localization and Explanation via Multi-Modal Large Language Model

FOCA:基于多模态大语言模型的频率导向跨域伪造检测、定位与解释

Zhou Liu, Tonghua Su, Hongshi Zhang, Fuxiang Yang, Donglin Di, Yang Song, Lei Fan

机构 * Harbin Institute of Technology(哈尔滨工业大学) DZ-Matrix Guangdong Laboratory of Artificial Intelligence and Digital Economy(广东省人工智能与数字经济实验室) Chongqing Research Institute of HIT(哈尔滨工业大学重庆研究院) University of New South Wales(新南威尔士大学)

AI总结 FOCA通过多模态大语言模型整合空间与频域特征,实现图像伪造的高精度检测、定位及可解释性解释,优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.18697 2026-02-24 cs.CV

Deep LoRA-Unfolding Networks for Image Restoration

深度 LoRA 展开网络用于图像恢复

Xiangming Wang, Haijin Zeng, Benteng Sun, Jiezhang Cao, Kai Zhang, Qiangqiang Shen, Yongyong Chen

机构 * School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen)(计算机科学与技术学院,哈尔滨工业大学(深圳)) Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University(图像通信与网络工程院,上海交通大学) School of Intelligence Science and Technology, Nanjing University(智能科学与技术学院,南京大学) School of Electronics and Information Engineering, Harbin Institute of Technology (Shenzhen)(电子与信息工程学院,哈尔滨工业大学(深圳))

AI总结 LoRun 通过引入 LoRA 适配器实现高效图像恢复,减少参数冗余并提升去噪性能。

Comments Accepted by IEEE Transactions on Image Processing

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.01696 2026-02-24 cs.CV cs.AI

Cross-Modal Purification and Fusion for Small-Object RGB-D Transmission-Line Defect Detection

跨模态净化与融合用于小物体RGB-D传输线缺陷检测

Jiaming Cui, Wenqiang Li, Shuai Zhou, Ruifeng Qin, Feng Shen

机构 * School of Mechatronics Engineering, Harbin Institute of Technology(机械电子工程学院,哈尔滨工业大学) School of Instrument Science and Engineering, Harbin Institute of Technology(仪器科学与工程学院,哈尔滨工业大学) Electric Power Research Institute, Yunnan Power Grid Co., Ltd.(电力研究院,云南电网公司)

AI总结 CMAFNet通过跨模态净化与融合技术,提升小物体RGB-D传输线缺陷检测的精度与效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.17195 2026-02-24 cs.RO

Depth-PC: A Visual Servo Framework Integrated with Cross-Modality Fusion for Sim2Real Transfer

Depth-PC: 一种集成跨模态融合的视觉伺服框架用于仿真到现实迁移

Haoyu Zhang, Yang Liu, Yimu Jiang, Weiyang Lin, Chao Ye

机构 * Research Institute of Intelligent Control and Systems, Harbin Institute of Technology(智能控制与系统研究所,哈尔滨工业大学)

AI总结 Depth-PC通过跨模态融合和图神经网络实现零样本仿真到现实迁移的视觉伺服框架

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.16500 2026-02-19 cs.CL

Optimizing Soft Prompt Tuning via Structural Evolution

通过结构进化优化软提示微调

Zhenzhen Huang, Chaoning Zhang, Haoyu Bian, Songbo Zhang, Chi-lok Andy Tai, Jiaquan Zhang, Caiyan Qin, Jingjing Qu, Yalan Ye, Yang Yang, Heng Tao Shen

机构 * 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) School of Computer Science and Engineering, University of Electronic Science and Technology of China(电子科技大学计算机科学与工程学院) College of Professional and Continuing Education, The Hong Kong Polytechnic University(香港理工大学专业及继续教育学院) School of Robotics and Advanced Manufacture, Harbin Institute of Technology(哈尔滨工业大学机器人与先进制造学院) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) School of Computer Science and Technology, Tongji University(同济大学计算机科学与技术学院)

AI总结 本文提出基于拓扑形态演化的软提示微调优化方法,通过拓扑持久同调量化结构表示,改进模型收敛速度和微调性能,提升可解释性。

Comments This manuscript has been submitted to IEEE Transactions on Knowledge and Data Engineering (TKDE) for peer review

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.17863 2026-02-19 cs.CV cs.AI

A Survey: Spatiotemporal Consistency in Video Generation

综述:视频生成中的时空一致性

Zhiyu Yin, Kehai Chen, Xuefeng Bai, Ruili Jiang, Juntao Li, Hongdong Li, Jin Liu, Yang Xiang, Jun Yu, Min Zhang

机构 * School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳)计算机科学与技术学院) School of Computer Science and Engineering, Central South University(中南大学计算机科学与工程学院) Peng Cheng Laboratory(鹏城实验室) School of Computer Science and Technology, Soochow University(苏州大学计算机科学与技术学院)

AI总结 本文综述了视频生成中时空一致性的最新进展,涵盖生成模型、特征表示、训练策略等,探讨了未来研究方向和挑战。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.16209 2026-02-19 cs.LG cs.AI

Geometric Neural Operators via Lie Group-Constrained Latent Dynamics

通过李群约束的潜在动态实现几何神经算子

Jiaquan Zhang, Fachrina Dewi Puspitasari, Songbo Zhang, Yibei Liu, Kuien Liu, Caiyan Qin, Fan Mo, Peng Wang, Yang Yang, Chaoning Zhang

机构 * School of Information and Software Engineering, University of Electronic Science and Technology of China(信息与软件工程学院,电子科学与技术大学) Computer Science and Engineering, University of Electronic Science and Technology of China(计算机科学与工程,电子科学与技术大学) Institute of Software Chinese Academy of Sciences, Beijing, China(软件研究所,中国科学院) School of Robotics and Advanced Manufacture, Harbin Institute of Technology, Shenzhen, China(机器人与先进制造学院,哈尔滨工业大学(深圳)) Department of Computer Science, University of Oxford, Oxford, United Kingdom(计算机科学系,牛津大学)

AI总结 本文提出了一种基于李群约束的潜在动态方法,用于改进神经算子的几何诱导偏差,从而提高长期预测的保真度。

详情

展开后加载摘要…

URL PDF HTML 收藏