语言大模型 / LLM - arXivDaily 专题

2510.05674 2025-10-10 cs.CV 50%

Context Matters: Learning Global Semantics via Object-Centric Representation

Jike Zhong, Yuxiang Lai, Xiaofeng Yang, Konstantinos Psounis

机构 * University of Southern California（美国南加州大学）； Emory University（埃默里大学）

专题命中知识编辑与模型理解：language model(abstract)

2506.13430 2025-10-09 cs.CV 50%

Uncertainty-Aware Remaining Lifespan Prediction from Images

Tristan Kenneweg, Philip Kenneweg, Barbara Hammer

机构 * University of Bielefeld（比勒菲尔德大学）

专题命中知识编辑与模型理解：foundation model(abstract)

Comments Submitted to ISVC 2025

2506.13367 2025-10-09 cs.RO 50%

Uncertainty-Informed Active Perception for Open Vocabulary Object Goal Navigation

Utkarsh Bajpai, Julius Rückin, Cyrill Stachniss, Marija Popović

机构 * Center for Robotics, University of Bonn（波恩大学机器人中心）； MAVLab, TU Delft（代尔夫特理工大学MAVLab）； Lamarr Institute for Machine Learning and Artificial Intelligence（机器学习与人工智能拉马尔研究所）

专题命中知识编辑与模型理解：language model(abstract)

Comments 7 pages, 3 figures

Journal ref Proceedings of the 2025 European Conference on Mobile Robots (ECMR)

2510.05586 2025-10-08 cs.CV 50%

CalibCLIP: Contextual Calibration of Dominant Semantics for Text-Driven Image Retrieval

Bin Kang, Bin Chen, Junjie Wang, Yulin Li, Junzhi Zhao, Zhuotao Tian

机构 * Chengdu Institute of Computer Applications, Chinese Academy of Sciences（成都计算机应用研究所，中国科学院）； University of Chinese Academy of Sciences（中国科学院大学）； International Research Institute for Artificial Intelligence, Harbin Institute of Technology (Shenzhen)（人工智能国际研究院，哈尔滨工业大学（深圳））； Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））； Southwest Jiaotong University（西南交通大学）； Tencent（腾讯）

专题命中知识编辑与模型理解：language model(abstract)

Comments ACMMM2025(oral)

2503.07399 2025-10-07 cs.CV 50%

Exploring Representation Invariance in Finetuning

Wenqiang Zu, Shenghao Xie, Hao Chen, Zhiqiang Chen, Liwen Hu, Yuanhao Xi, Yiming Liang, Junliang Ye, Bo Lei, Tiejun Huang, Guoqi Li, Lei Ma

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； Peking University（北京大学）； University of Chinese Academy of Sciences（中国科学院大学）； University of Göttingen（哥廷根大学）； Tsinghua University（清华大学）； Beijing Academy of Artificial Intelligence（北京人工智能研究院）

专题命中知识编辑与模型理解：foundation model(abstract)

2510.00721 2025-10-02 physics.chem-ph 50%

Flexible Uncertainty Calibration for Machine-Learned Interatomic Potentials

Cheuk Hin Ho, Christoph Ortner, Yangshuai Wang

专题命中知识编辑与模型理解：foundation model(abstract)

2510.00683 2025-10-02 cs.CV 50%

ProtoMask: Segmentation-Guided Prototype Learning

Steffen Meinert, Philipp Schlinge, Nils Strodthoff, Martin Atzmueller

机构 * AI4Health Division, Faculty VI Carl von Ossietzky Universität Oldenburg（AI4Health部门，第六学院卡尔·冯·奥西特齐克大学）； Semantic Information Systems Group Osnabrück University（语义信息系统小组奥尔纳布里克大学）

专题命中知识编辑与模型理解：foundation model(abstract)

2509.23849 2025-09-30 cs.CV 50%

CE-FAM: Concept-Based Explanation via Fusion of Activation Maps

Michihiro Kuroki, Toshihiko Yamasaki

机构 * The University of Tokyo（东京大学）

专题命中知识编辑与模型理解：language model(abstract)

Comments This paper has been accepted to ICCV 2025

2509.23838 2025-09-30 cs.CV 50%

2nd Place Report of MOSEv2 Challenge 2025: Concept Guided Video Object Segmentation via SeC

Zhixiong Zhang, Shuangrui Ding, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Jiaqi Wang

机构 * Shanghai Jiao Tong University（上海交通大学）； Shanghai Innovation Institute（上海创新研究院）； Shanghai AI Laboratory（上海人工智能实验室）； The Chinese University of Hong Kong（香港中文大学）

专题命中知识编辑与模型理解：language model(abstract)

2509.19562 2025-09-25 cs.CV 50%

CURE: Centroid-guided Unsupervised Representation Erasure for Facial Recognition Systems

Fnu Shivam, Nima Najafzadeh, Yenumula Reddy, Prashnna Gyawali

机构 * West Virginia University（西弗吉尼亚大学）

专题命中知识编辑与模型理解：prompting(abstract)

2509.17914 2025-09-23 cs.DC 50%

XaaS Containers: Performance-Portable Representation With Source and IR Containers

Marcin Copik, Eiman Alnuaimi, Alok Kamatar, Valerie Hayot-Sasson, Alberto Madonna, Todd Gamblin, Kyle Chard, Ian Foster, Torsten Hoefler

专题命中知识编辑与模型理解：LLM(abstract)

Comments Accepted at the International Conference for High Performance Computing, Networking, Storage and Analysis (SC'25)

2507.07620 2025-09-22 cs.CV 50%

ViLU: Learning Vision-Language Uncertainties for Failure Prediction

Marc Lafon, Yannis Karmim, Julio Silva-Rodríguez, Paul Couairon, Clément Rambour, Raphaël Fournier-Sniehotta, Ismail Ben Ayed, Jose Dolz, Nicolas Thome

专题命中知识编辑与模型理解：language model(abstract)

Journal ref International Conference on Computer Vision, ICCV 2025

2509.14688 2025-09-19 cs.RO 50%

exUMI: Extensible Robot Teaching System with Action-aware Task-agnostic Tactile Representation

Yue Xu, Litao Wei, Pengyu An, Qingyu Zhang, Yong-Lu Li

机构 * Shanghai Jiao Tong University（上海交通大学）； Shanghai Innovation Institute（上海创新研究院）

专题命中知识编辑与模型理解：pretraining(abstract)

Comments Accepted at CoRL 2025

2509.12039 2025-09-16 cs.CV 50%

RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration

Zilong Zhang, Chujie Qin, Chunle Guo, Yong Zhang, Chao Xue, Ming-Ming Cheng, Chongyi Li

机构 * VCIP, CS, Nankai University（VCIP、计算机科学系、南开大学）； Chongqing Chang’an Wangjiang Industrial Group Co., Ltd（重庆长安王江工业集团有限公司）； Tiandy Technologies（天鼎科技）

专题命中知识编辑与模型理解：pretraining(abstract)

Comments 18 pages, 22 figures

2503.22104 2025-09-16 eess.AS 50%

M2D-CLAP: Exploring General-purpose Audio-Language Representations Beyond CLAP

Daisuke Niizumi, Daiki Takeuchi, Masahiro Yasuda, Binh Thien Nguyen, Yasunori Ohishi, Noboru Harada

专题命中知识编辑与模型理解：LLM(abstract)

Comments Formerly M2D2, reverted to M2D-CLAP. 15 pages, 7 figures, 13 tables. Accepted by IEEE Access

2410.00609 2025-09-15 quant-ph 50%

Distributed Quantum Computing: Applications and Challenges

Juan C. Boschero, Niels M. P. Neumann, Ward van der Schoot, Thom Sijpesteijn, Robert Wezeman

专题命中知识编辑与模型理解：prompting(abstract)

Comments 9 pages, 1 figure

2411.17784 2025-09-08 cs.CV 50%

HypDAE: Hyperbolic Diffusion Autoencoders for Hierarchical Few-shot Image Generation

Lingxiao Li, Kaixuan Fan, Boqing Gong, Xiangyu Yue

机构 * MMLab, The Chinese University of Hong Kong（香港中文大学）； Boston University（波士顿大学）

专题命中知识编辑与模型理解：foundation model(abstract)

Comments ICCV 2025, Code is available at: https://github.com/lingxiao-li/HypDAE

2505.20537 2025-09-01 cs.RO 50%

CoRI: Communication of Robot Intent for Physical Human-Robot Interaction

Junxiang Wang, Emek Barış Küçüktabak, Rana Soltani Zarrin, Zackory Erickson

专题命中知识编辑与模型理解：language model(abstract)

Comments To be published in Proceedings of the 9th Conference on Robot Learning (CoRL). 34 pages, 10 figures

2508.16652 2025-08-28 cs.CV 50%

Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability

Ashwath Vaithinathan Aravindan, Abha Jha, Mihir Kulkarni

机构 * University of Southern California（南加州大学）

专题命中知识编辑与模型理解：language model(abstract)

Comments To be published in Explainable Computer Vision: Quo Vadis? workshop at ICCV'25

2507.22675 2025-08-27 cs.CV 50%

MergeSAM: Unsupervised change detection of remote sensing images based on the Segment Anything Model

Meiqi Hu, Lingzhi Lu, Chengxi Han, Xiaoping Liu

专题命中知识编辑与模型理解：foundation model(abstract)

Comments 4 pages

2508.15972 2025-08-25 cs.RO cs.CV 50%

UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimation

Zhaodong Jiang, Ashish Sinha, Tongtong Cao, Yuan Ren, Bingbing Liu, Binbin Xu

机构 * Huawei Noah’s Ark Lab, Canada（华为诺亚实验室，加拿大）； University of Toronto, Canada（多伦多大学，加拿大）

专题命中知识编辑与模型理解：foundation model(abstract)

Comments Published at the Conference on Robot Learning (CoRL) 2025. For more details please visit https://frankzhaodong.github.io/UnPose

2508.14562 2025-08-21 cs.CV 50%

Locality-aware Concept Bottleneck Model

Sujin Jeon, Hyundo Lee, Eungseo Kim, Sanghack Lee, Byoung-Tak Zhang, Inwoo Hwang

机构 * Seoul National University（首尔国立大学）； Columbia University（哥伦比亚大学）

专题命中知识编辑与模型理解：foundation model(abstract)

Comments 34 pages, 25 figures

2508.14493 2025-08-21 cs.IR 50%

Global-Distribution Aware Scenario-Specific Variational Representation Learning Framework

Moyu Zhang, Yujun Jin, Jinxin Hu, Yu Zhang

专题命中知识编辑与模型理解：prompting(abstract)

Comments Accepted by CIKM 2025, 6 pages, 1 figures, 5 tables

2506.18678 2025-08-20 cs.CV cs.RO 50%

MCN-SLAM: Multi-Agent Collaborative Neural SLAM with Hybrid Implicit Neural Scene Representation

Tianchen Deng, Guole Shen, Xun Chen, Shenghai Yuan, Hongming Shen, Guohao Peng, Zhenyu Wu, Jingchuan Wang, Lihua Xie, Danwei Wang, Hesheng Wang, Weidong Chen

专题命中知识编辑与模型理解：foundation model(abstract)

2506.12609 2025-08-19 cs.CV 50%

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation

Lexiang Tang, Xianwei Zhuang, Bang Yang, Zhiyuan Hu, Hongxiang Li, Lu Ma, Jinghan Ru, Yuexian Zou

专题命中知识编辑与模型理解：language model(abstract)

2507.15227 2025-08-19 cs.CV 50%

Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders

Krishna Kanth Nakka

机构 * institutetext: Bavaria, Germany（巴伐利亚，德国）

专题命中知识编辑与模型理解：foundation model(abstract)

Comments Accepted at Deep Breast Imaging workshop, MICCAI 2025

2503.05245 2025-08-12 eess.IV cs.CV 50%

L-FUSION: Laplacian Fetal Ultrasound Segmentation & Uncertainty Estimation

Johanna P. Müller, Robert Wright, Thomas G. Day, Lorenzo Venturini, Samuel F. Budd, Hadrien Reynaud, Joseph V. Hajnal, Reza Razavi, Bernhard Kainz

机构 * King's College London, London, UK（伦敦国王学院）； Imperial College London, London, UK（伦敦帝国学院）

专题命中知识编辑与模型理解：foundation model(abstract)

Comments Accepted at MICCAI ASMUS 2025

2508.04148 2025-08-07 cs.NE 50%

STARE: Predicting Decision Making Based on Spatio-Temporal Eye Movements

Moshe Unger, Alexander Tuzhilin, Michel Wedel

专题命中知识编辑与模型理解：foundation model(abstract)

2406.08328 2025-08-06 eess.AS 50%

Multimodal Representation Loss Between Timed Text and Audio for Regularized Speech Separation

Tsun-An Hsieh, Heeyoul Choi, Minje Kim

专题命中知识编辑与模型理解：language model(abstract)

Journal ref Interspeech 2024

2508.03370 2025-08-06 cs.CE cs.MA 50%

A Closed-Loop Multi-Agent Framework for Aerodynamics-Aware Automotive Styling Design

Xinyu Jin, Shengmao Yan, Qingtao Wang, Shisong Deng, Yanzhen Jiang, Shuangyao Zhao

专题命中知识编辑与模型理解：LLM(abstract)

1. 知识编辑与模型理解 7608 篇

Context Matters: Learning Global Semantics via Object-Centric Representation

Uncertainty-Aware Remaining Lifespan Prediction from Images

Uncertainty-Informed Active Perception for Open Vocabulary Object Goal Navigation

CalibCLIP: Contextual Calibration of Dominant Semantics for Text-Driven Image Retrieval

Exploring Representation Invariance in Finetuning

Flexible Uncertainty Calibration for Machine-Learned Interatomic Potentials

ProtoMask: Segmentation-Guided Prototype Learning

CE-FAM: Concept-Based Explanation via Fusion of Activation Maps

2nd Place Report of MOSEv2 Challenge 2025: Concept Guided Video Object Segmentation via SeC

CURE: Centroid-guided Unsupervised Representation Erasure for Facial Recognition Systems

XaaS Containers: Performance-Portable Representation With Source and IR Containers

ViLU: Learning Vision-Language Uncertainties for Failure Prediction

exUMI: Extensible Robot Teaching System with Action-aware Task-agnostic Tactile Representation

RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration

M2D-CLAP: Exploring General-purpose Audio-Language Representations Beyond CLAP

Distributed Quantum Computing: Applications and Challenges

HypDAE: Hyperbolic Diffusion Autoencoders for Hierarchical Few-shot Image Generation

CoRI: Communication of Robot Intent for Physical Human-Robot Interaction

Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability

MergeSAM: Unsupervised change detection of remote sensing images based on the Segment Anything Model

UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimation

Locality-aware Concept Bottleneck Model

Global-Distribution Aware Scenario-Specific Variational Representation Learning Framework

MCN-SLAM: Multi-Agent Collaborative Neural SLAM with Hybrid Implicit Neural Scene Representation

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation

Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders

L-FUSION: Laplacian Fetal Ultrasound Segmentation & Uncertainty Estimation

STARE: Predicting Decision Making Based on Spatio-Temporal Eye Movements

Multimodal Representation Loss Between Timed Text and Audio for Regularized Speech Separation

A Closed-Loop Multi-Agent Framework for Aerodynamics-Aware Automotive Styling Design