多模态大模型 - arXivDaily 专题

2510.01970 2025-10-03 cs.LG 50%

Moon: A Modality Conversion-based Efficient Multivariate Time Series Anomaly Detection

Yuanyuan Yao, Yuhan Shi, Lu Chen, Ziquan Fang, Yunjun Gao, Leong Hou U, Yushuai Li, Tianyi Li

机构 * College of Computer Science, Zhejiang University（浙江大学计算机科学学院）； Department of Computer and Information Science, University of Macau（澳门大学计算机与信息科学系）； Department of Computer Science, Aalborg University（奥胡斯大学计算机科学系）

专题命中多模态训练与对齐：multimodal(abstract)

2510.01634 2025-10-03 cs.LG 50%

CAT: Curvature-Adaptive Transformers for Geometry-Aware Learning

Ryan Y. Lin, Siddhartha Ojha, Nicholas Bai

机构 * Division of Engineering and Applied Science（工程与应用科学系）； California Institute of Technology（加州理工学院）

专题命中多模态训练与对齐：multimodal(abstract)

2507.09404 2025-10-03 cs.LG 50%

Scaling Laws for Optimal Data Mixtures

Mustafa Shukor, Louis Bethune, Dan Busbridge, David Grangier, Enrico Fini, Alaaeldin El-Nouby, Pierre Ablin

机构 * Sorbonne University（索邦大学）； Apple（苹果公司）

专题命中多模态训练与对齐：multimodal(abstract)

2509.24381 2025-09-30 cs.DC 50%

RServe: Overlapping Encoding and Prefill for Efficient LMM Inference

Tianyu Guo, Tianming Xu, Xianjie Chen, Junru Chen, Nong Xiao, Xianwei Zhang

专题命中多模态训练与对齐：multimodal(abstract)

2509.22195 2025-09-29 cs.RO 50%

Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting

Asher J. Hancock, Xindi Wu, Lihan Zha, Olga Russakovsky, Anirudha Majumdar

机构 * Princeton University（普林斯顿大学）

专题命中多模态训练与对齐：multimodal(abstract)

2509.19521 2025-09-25 cs.RO 50%

A Bimanual Gesture Interface for ROS-Based Mobile Manipulators Using TinyML and Sensor Fusion

Najeeb Ahmed Bhuiyan, M. Nasimul Huq, Sakib H. Chowdhury, Rahul Mangharam

机构 * †‡Department of Mechatronics Engineering, Rajshahi University of Engineering \& Technology, Kazla, Rajshahi-6204, Bangladesh §Department of Electrical \& Systems Engineering, School of Engineering \& Applied Science, University of Pennsylvania, Philadelphia, PA 19104, United States Email: , †, ‡, §

专题命中多模态训练与对齐：multimodal(abstract)

Comments 12 pages, 11 figures

2410.18353 2025-09-22 cs.LG 50%

A Data-Driven Review of Remote Sensing-Based Data Fusion in Precision Agriculture from Foundational to Transformer-Based Techniques

Mahdi Saki, Rasool Keshavarz, Daniel Franklin, Mehran Abolhasan, Justin Lipman, Negin Shariati

专题命中多模态训练与对齐：multimodal(abstract)

Comments 22 pages, 13 figures, 3 tables, Journal

2509.08830 2025-09-12 eess.SP cs.LG 50%

A Masked Representation Learning to Model Cardiac Functions Using Multiple Physiological Signals

Seong-A Park, Jong-Eui Chae, Sungdong Kim, Hyung-Chul Lee, Hyun-Lim Yang

机构 * Seoul National University Hospital（首尔国立大学医院）； Seoul National University（首尔国立大学）； KAIST AI（韩国科学技术院人工智能研究所）

专题命中多模态训练与对齐：multi-modal(abstract)

Comments 16 pages, 5 figures

2509.08174 2025-09-11 physics.optics cond-mat.mtrl-sci 50%

Comparing Machine Learning and Physics-Based Nanoparticle Geometry Determinations Using Far-Field Spectral Properties

Mengqi Sun, Zixu Huang, Muammer Y. Yaman, Maxim Ziatdinov, Sergei V. Kalinin, David S. Ginger

专题命中多模态训练与对齐：multimodal(abstract)

2509.02602 2025-09-04 eess.IV 50%

Masked Autoencoder Pretraining and BiXLSTM ResNet Architecture for PET/CT Tumor Segmentation

Moona Mazher, Steven A Niederer, Abdul Qayyum

专题命中多模态训练与对齐：multimodal(abstract)

2509.02011 2025-09-03 cs.RO 50%

Generalizing Unsupervised Lidar Odometry Model from Normal to Snowy Weather Conditions

Beibei Zhou, Zhiyuan Zhang, Zhenbo Song, Jianhui Guo, Hui Kong

机构 * Shanghai Polytechnic University（上海理工大学）； Singapore Management University（新加坡国立大学）； Nanjing University of Science and Technology（南京理工大学）； University of Macau（澳门大学）

专题命中多模态训练与对齐：multi-modal(abstract)

2509.01611 2025-09-03 cs.RO 50%

A Hybrid Input based Deep Reinforcement Learning for Lane Change Decision-Making of Autonomous Vehicle

Ziteng Gao, Jiaqi Qu, Chaoyu Chen

专题命中多模态训练与对齐：multi-modal(abstract)

2504.06156 2025-09-03 cs.RO 50%

ViTaMIn: Learning Contact-Rich Tasks Through Robot-Free Visuo-Tactile Manipulation Interface

Fangchen Liu, Chuanyu Li, Yihua Qin, Jing Xu, Pieter Abbeel, Rui Chen

机构 * Tsinghua University（清华大学）； University of California, Berkeley（加州大学伯克利分校）

专题命中多模态训练与对齐：multimodal(abstract)

2506.17761 2025-09-03 cs.LG 50%

Towards a Unified Textual Graph Framework for Spectral Reasoning via Physical and Chemical Information Fusion

Jiheng Liang, Ziru Yu, Zujie Xie, Yuchen Guo, Yulan Guo, Xiangyang Yu

专题命中多模态训练与对齐：multi-modal(abstract)

Comments We need to further modify and supplement the experiment

2503.19338 2025-09-03 cs.LG cs.CR 50%

Membership Inference Attacks on Large-Scale Models: A Survey

Hengyu Wu, Yang Cao

机构 * Institute of Science Tokyo（东京科学研究所）

专题命中多模态训练与对齐：multimodal(abstract)

Comments Preprint. Submitted for peer review. The final version may differ

2508.18058 2025-08-26 q-bio.QM 50%

Comprehensively stratifying MCIs into distinct risk subtypes based on brain imaging genetics fusion learning

Muheng Shang, Jin Zhang, Junwei Han, Lei Du

专题命中多模态训练与对齐：multimodal(abstract)

2508.12418 2025-08-19 cs.LG 50%

Bi-Axial Transformers: Addressing the Increasing Complexity of EHR Classification

Rachael DeVries, Casper Christensen, Marie Lisandra Zepeda Mendoza, Ole Winther

机构 * University of Copenhagen（哥本哈根大学）； Novo Nordisk A/S（诺华北欧制药有限公司）； Novo Nordisk Research Center Oxford Ltd.（诺华奥克斯研究中心）； Technical University of Denmark（丹麦技术大学）

专题命中多模态训练与对齐：multi-modal(abstract)

Comments 18 pages, 7 figures. Submitted to the IEEE for possible publication

2504.14835 2025-08-13 eess.SP 50%

Aligning Beam with Imbalanced Multi-modality: A Generative Federated Learning Approach

Jiahui Liang, Miaowen Wen, Shuoyao Wang, Yuxuan Liang, Shijian Gao

专题命中多模态训练与对齐：multi-modal(abstract)

2508.07738 2025-08-12 cs.LG 50%

Separation and Collaboration: Two-Level Routing Grouped Mixture-of-Experts for Multi-Domain Continual Learning

Jialu Zhou, Dianxi Shi, Shaowu Yang, Xinyu Wei, Mingyue Yang, Leqian Li, Mengzhu Wang, Chunping Qiu

专题命中多模态训练与对齐：multimodal(abstract)

2508.07717 2025-08-12 eess.SP 50%

Touch-Augmented Gaussian Splatting for Enhanced 3D Scene Reconstruction

Yuchen Gao, Xiao Xu, Eckehard Steinbach, Daniel E. Lucani, Qi Zhang

专题命中多模态训练与对齐：multimodal(abstract)

2508.04739 2025-08-08 q-bio.GN cs.LG 50%

CodonMoE: DNA Language Models for mRNA Analyses

Shiyi Du, Litian Liang, Jiayi Li, Carl Kingsford

机构 * School of Computer Science, Carnegie Mellon University（计算机科学系，卡内基梅隆大学）

专题命中多模态训练与对齐：multi-modal(abstract)

2508.04391 2025-08-07 cs.HC 50%

Plant-Centric Metaverse: A Biocentric-Creation Framework for Ecological Art and Digital Symbiosis

Ze Gao, Mengyao Guo, Zheng Wang, Xiaolin Zhang, Sihuang Man

专题命中多模态训练与对齐：multimodal(abstract)

2508.04251 2025-08-07 cs.LG 50%

T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusion

Abdul Monaf Chowdhury, Rabeya Akter, Safaeid Hossain Arib

专题命中多模态训练与对齐：cross-modal(abstract)

2508.02423 2025-08-05 q-bio.TO 50%

Evolutionary Paradigms in Histopathology Serial Sections technology

Zhenfeng Zhuang, Min Cen, Lei Jiang, Qiong Peng, Yihuang Hu, Hong-Yu Zhou, Liansheng Wang

专题命中多模态训练与对齐：multimodal(abstract)

2302.12024 2025-08-05 stat.ML cs.LG hep-ex hep-ph 50%

Comparison of Affine and Rational Quadratic Spline Coupling and Autoregressive Flows through Robust Statistical Tests

Andrea Coccaro, Marco Letizia, Humberto Reyes-Gonzalez, Riccardo Torre

机构 * INFN（意大利国家核物理研究所）； MaLGa - DIBRIS（马尔盖-迪布里兹）； University of Genova（热那亚大学）； Department of Physics（物理系）； RWTH Aachen（亚琛工业大学）

专题命中多模态训练与对齐：multimodal(abstract)

Comments v3: published version; 25 pages, 3 figures, 3 tables

Journal ref Symmetry 2024, 16(8), 942

2508.01599 2025-08-05 cs.OH 50%

Lessons Learned from the Real-World Deployment of Multi-Sensor Fusion for Proactive Work Zone Safety Application

Minhaj Uddin Ahmad, Sagar Dasgupta, Mizanur Rahman, Sakib Khan, Md Wasiul Haque, Suhala Rabab Saba, David Bodoh, Nathan Huynh, Li Zhao, Eren Erman Ozguven

专题命中多模态训练与对齐：multi-modal(abstract)

2508.01375 2025-08-05 cs.IR 50%

SaviorRec: Semantic-Behavior Alignment for Cold-Start Recommendation

Yining Yao, Ziwei Li, Shuwen Xiao, Boya Du, Jialin Zhu, Junjun Zheng, Xiangheng Kong, Yuning Jiang

专题命中多模态训练与对齐：multimodal(abstract)

2508.00862 2025-08-05 cs.DL 50%

A survey on proximity monitoring and warning in construction

Yuexiong Ding, Qiong Liu, Ankang Ji, Xiaowei Luo, Wen Yi, Albert P. C. Chan

专题命中多模态训练与对齐：multimodal(abstract)

2508.00258 2025-08-04 cs.RO 50%

Topology-Inspired Morphological Descriptor for Soft Continuum Robots

Zhiwei Wu, Siyi Wei, Jiahao Luo, Jinhui Zhang

专题命中多模态训练与对齐：multimodal(abstract)

2503.02198 2025-08-04 cs.RO 50%

FalconGym: A Photorealistic Simulation Framework for Zero-Shot Sim-to-Real Vision-Based Quadrotor Navigation

Yan Miao, Will Shen, Sayan Mitra

机构 * Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign（电气与计算机工程系，伊利诺伊大学厄巴纳-香槟分校）

专题命中多模态训练与对齐：multi-modal(abstract)

Comments Accepted in IROS 2025

1. 多模态训练与对齐 6942 篇

Moon: A Modality Conversion-based Efficient Multivariate Time Series Anomaly Detection

CAT: Curvature-Adaptive Transformers for Geometry-Aware Learning

Scaling Laws for Optimal Data Mixtures

RServe: Overlapping Encoding and Prefill for Efficient LMM Inference

Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting

A Bimanual Gesture Interface for ROS-Based Mobile Manipulators Using TinyML and Sensor Fusion

A Data-Driven Review of Remote Sensing-Based Data Fusion in Precision Agriculture from Foundational to Transformer-Based Techniques

A Masked Representation Learning to Model Cardiac Functions Using Multiple Physiological Signals

Comparing Machine Learning and Physics-Based Nanoparticle Geometry Determinations Using Far-Field Spectral Properties

Masked Autoencoder Pretraining and BiXLSTM ResNet Architecture for PET/CT Tumor Segmentation

Generalizing Unsupervised Lidar Odometry Model from Normal to Snowy Weather Conditions

A Hybrid Input based Deep Reinforcement Learning for Lane Change Decision-Making of Autonomous Vehicle

ViTaMIn: Learning Contact-Rich Tasks Through Robot-Free Visuo-Tactile Manipulation Interface

Towards a Unified Textual Graph Framework for Spectral Reasoning via Physical and Chemical Information Fusion

Membership Inference Attacks on Large-Scale Models: A Survey

Comprehensively stratifying MCIs into distinct risk subtypes based on brain imaging genetics fusion learning

Bi-Axial Transformers: Addressing the Increasing Complexity of EHR Classification

Aligning Beam with Imbalanced Multi-modality: A Generative Federated Learning Approach

Separation and Collaboration: Two-Level Routing Grouped Mixture-of-Experts for Multi-Domain Continual Learning

Touch-Augmented Gaussian Splatting for Enhanced 3D Scene Reconstruction

CodonMoE: DNA Language Models for mRNA Analyses

Plant-Centric Metaverse: A Biocentric-Creation Framework for Ecological Art and Digital Symbiosis

T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusion

Evolutionary Paradigms in Histopathology Serial Sections technology

Comparison of Affine and Rational Quadratic Spline Coupling and Autoregressive Flows through Robust Statistical Tests

Lessons Learned from the Real-World Deployment of Multi-Sensor Fusion for Proactive Work Zone Safety Application

SaviorRec: Semantic-Behavior Alignment for Cold-Start Recommendation

A survey on proximity monitoring and warning in construction

Topology-Inspired Morphological Descriptor for Soft Continuum Robots

FalconGym: A Photorealistic Simulation Framework for Zero-Shot Sim-to-Real Vision-Based Quadrotor Navigation