arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Korea Advanced Institute of Science and Technology(韩国科学技术院)

共收录 1472
2511.16133 2025-11-27 cs.HC cs.RO

Heterogeneous Stroke: Using Unique Vibration Cues to Improve the Wrist-Worn Spatiotemporal Tactile Display

异质性笔触:利用独特的振动线索提高腕戴式时空触觉显示的识别精度

Taejun Kim, Youngbo Aram Shim, Geehyuk Lee

机构 * HCI Lab, KAIST(韩国釜山科学技术院人机交互实验室)

AI总结 异质性笔触通过为每个触觉器分配独特振动刺激,提高腕戴式触觉显示在不同手臂姿势下的字母数字识别精度。

Comments ACM CHI 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.02315 2025-11-26 cs.LG stat.ML

Improving Constrained Language Generation via Self-Distilled Twisted Sequential Monte Carlo

通过自蒸馏扭曲序列蒙特卡洛改进约束语言生成

Sooyeon Kim, Giung Nam, Byoungwoo Park, Juho Lee

机构 * Seoul National University(首尔国立大学) Korea Advanced Institute of Science and Technology(韩国科学技术院)

AI总结 本文通过自蒸馏扭曲序列蒙特卡洛方法改进约束语言生成,提升生成质量。

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.04704 2025-11-26 cs.CV cs.AI

HoliSafe: Holistic Safety Benchmarking and Modeling for Vision-Language Model

HoliSafe: 视觉-语言模型的综合安全性评估与建模

Youngwan Lee, Kangsan Kim, Kwanyong Park, Ilcahe Jung, Soojin Jang, Seanie Lee, Yong-Ju Lee, Sung Ju Hwang

机构 * ETRI KAIST AI(韩国科学技术院人工智能研究所) University of Seoul(首尔大学)

AI总结 HoliSafe提出了一种模块化框架和视觉守护模块,通过综合安全性数据集提升视觉-语言模型的安全性,展现其在多个基准中的优越表现。

Comments Project page: https://youngwanlee.github.io/holisafe

详情

展开后加载摘要…

URL PDF HTML 收藏
2205.14839 2025-11-26 cs.LG stat.ML

Adversarial Bandits against Arbitrary Strategies

对抗任意策略的对抗性老虎机

Jung-hun Kim, Se-Young Yun

机构 * CREST, ENSAE, IP Paris(CREST,ENSAE,IP巴黎) FairPlay joint team, France(FairPlay联合团队,法国) KAIST AI, South Korea(韩国KAIST AI)

AI总结 本文提出了一种对抗任意策略的老虎机算法,通过主-从框架和自适应学习率的在线镜像下降方法,实现了在切换次数S和方差项ρ下的最优时间复杂度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19542 2025-11-26 cs.CV

Proxy-Free Gaussian Splats Deformation with Splat-Based Surface Estimation

无代理高斯喷射变形与基于喷射的表面估计

Jaeyeong Kim, Seungwoo Yoo, Minhyuk Sung

机构 * KAIST(韩国科学技术院)

AI总结 SpLap通过构建表面感知的喷射图,利用拉普拉斯算子实现无代理高斯喷射变形,提升渲染质量与细节保持能力。

Comments 17 pages, Accepted to 3DV 2026 (IEEE/CVF International Conference on 3D Vision)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.16301 2025-11-25 cs.CV

Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling

Upsample Anything: 一种简单且难以被超越的特征上采样基线

Minseok Seo, Mark Hamilton, Changick Kim

机构 * KAIST(韩国科学技术院) MIT(麻省理工学院) Microsoft(微软公司)

AI总结 Upsample Anything通过简单每张图像优化方法实现高效特征上采样,适用于多种像素级任务,性能优于现有方法。

Comments 15 pages, 12 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.04622 2025-11-25 cs.LG eess.SP

Forecasting-based Biomedical Time-series Data Synthesis for Open Data and Robust AI

基于预测的生物医学时间序列数据合成用于开放数据和鲁棒AI

Youngjoon Lee, Seongmin Cho, Yehhyun Jo, Jinu Gong, Hyunjoo Jenny Lee, Joonhyuk Kang

机构 * School of Electrical Engineering, KAIST, Daejeon, Republic of Korea(韩国成均馆大学电气工程学院) Department of Applied AI, Hansung University, Seoul, Republic of Korea(汉城市立大学应用人工智能系)

AI总结 本文提出基于预测模型的生物医学时间序列数据合成方法,通过高保真复现EEG和EMG信号,提升AI模型性能并促进开放数据共享。

Comments 22 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.11461 2025-11-25 cs.RO

Doppler Correspondence: Non-Iterative Scan Matching With Doppler Velocity-Based Correspondence

多普勒对应:基于多普勒速度的非迭代扫描匹配

Jiwoo Kim, Geunsik Bae, Changseung Kim, Jinwoo Lee, Woojae Shin, Hyondong Oh

机构 * Department of Mechanical Engineering, Ulsan National Institute of Science and Technology, Republic of Korea(韩国乌山国立科学与技术研究院机械工程系) Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Republic of Korea(韩国先进科学技术研究院机械工程系)

AI总结 本文提出基于多普勒速度的非迭代扫描匹配方法,通过利用4D激光雷达和雷达的多普勒信息,提高在恶劣环境下的里程计鲁棒性和计算效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.11254 2025-11-25 cs.LG

Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction

Delta Attention: 通过Delta校正实现快速且准确的稀疏注意力推理

Jeffrey Willette, Heejun Lee, Sung Ju Hwang

机构 * KAIST(韩国国立科学技术院)

AI总结 Delta Attention通过Delta校正解决稀疏注意力推理中的分布偏移问题,提升性能并保持高稀疏度,使模型在处理大规模预填充时速度显著提高。

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.08016 2025-11-24 q-bio.NC cs.AI cs.CL

Emergence of psychopathological computations in large language models

大语言模型中精神病理计算的出现

Soo Yong Lee, Hyunjin Hwang, Taekwan Kim, Yuyeong Kim, Kyuri Park, Jaemin Yoo, Denny Borsboom, Kijung Shin

机构 * KAIST, Kim Jaechul Graudate School of AI(KAIST人工智能研究生院) KAIST, School of Electrical Engineering(KAIST电子工程学院) UCL, Mental Health Neuroscience Department(伦敦大学学院心理健康神经科学系) UvA, Informatics Institute(乌得勒支大学信息学院) UvA, Department of Psychology(乌得勒支大学心理学系)

AI总结 本研究通过建立计算理论框架,证明大语言模型中已出现精神病理学的网络计算结构,并揭示其可能带来的安全风险。

Comments pre-print

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.14138 2025-11-21 eess.AS cs.SD

FxSearcher: gradient-free text-driven audio transformation

FxSearcher: 无梯度文本驱动音频变换

Hojoon Ki, Jongsuk Kim, Minchan Kwon, Junmo Kim

机构 * Korea Advanced Institute of Science and Technology, KAIST(韩国科学技术院)

AI总结 FxSearcher通过无梯度框架和引导提示,实现基于文本提示的高质量音频变换,有效提升音频效果配置的优化效率与人类偏好匹配度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15276 2025-11-20 cs.LG

SNAP: Low-Latency Test-Time Adaptation with Sparse Updates

Hyeongheon Cha, Dong Min Kim, Hye Won Chung, Taesik Gong, Sung-Ju Lee

机构 * School of Electrical Engineering, KAIST, Daejeon, Republic of Korea(韩国科学技术院电子工程学院) Department of Computer Science and Engineering, UNIST, Ulsan, Republic of Korea(全南国立大学计算机科学与工程系)

Journal ref Advances in Neural Information Processing Systems 39 (NeurIPS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.19646 2025-11-20 cs.LG

Energy-based generator matching: A neural sampler for general state space

Dongyeop Woo, Minsu Kim, Minkyu Kim, Kiyoung Seong, Sungsoo Ahn

机构 * Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.19067 2025-11-20 cs.CV

MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation

Minhyun Lee, Seungho Lee, Song Park, Dongyoon Han, Byeongho Heo, Hyunjung Shim

机构 * AI Center, Samsung Electronics(三星电子人工智能中心) NAVER AI Lab(NAVER人工智能实验室) Korea Advanced Institute of Science & Technology (KAIST)(韩国科学技术院)

Comments Accepted to TMLR 2025. First two authors contributed equally

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.01689 2025-11-20 cs.CV

InvFusion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems

Noam Elata, Hyungjin Chung, Jong Chul Ye, Tomer Michaeli, Michael Elad

机构 * Technion(技术学院) EverEx KAIST(韩国科学技术院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.17052 2025-11-19 cs.CL cs.AI

SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs

Jinwoo Park, Seunggeun Cho, Dongsu Han

机构 * KAIST(韩国科学技术院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.14248 2025-11-19 cs.AI

Enhancing Regional Airbnb Trend Forecasting Using LLM-Based Embeddings of Accessibility and Human Mobility

Hongju Lee, Youngjun Park, Jisun An, Dongman Lee

机构 * Graduate School of Data Science, KAIST(韩国科学技术院数据科学研究生院) School of Computing, KAIST(韩国科学技术院计算机科学学院) Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington(印第安纳大学布卢明顿分校信息学、计算与工程学院)

Comments Accepted at ASONAM 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.07029 2025-11-19 cs.CV cs.AI

Availability-aware Sensor Fusion via Unified Canonical Space

Dong-Hee Paek, Seung-Hyun Kong

机构 * CCS Graduate School of Mobility(移动系统联合研究生院) KAIST(韩国科学技术院)

Comments Accepted at NeurIPS 2025

Journal ref Proceedings of the Neural Information Processing Systems (NeurIPS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01215 2025-11-18 cs.CL cs.LG

Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers

Woomin Song, Sai Muralidhar Jayanthi, Srikanth Ronanki, Kanthashree Mysore Sathyendra, Jinwoo Shin, Aram Galstyan, Shubham Katiyar, Sravan Babu Bodapati

机构 * KAIST(韩国科学技术院) Amazon AGI(亚马逊人工智能实验室)

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12405 2025-11-18 cs.CV

VLA-R: Vision-Language Action Retrieval toward Open-World End-to-End Autonomous Driving

Hyunki Seong, Seongwoo Moon, Hojin Ahn, Jehun Kang, David Hyunchul Shim

机构 * School of Electrical Engineering, KAIST(韩国科学技术院电子工程学院)

Comments 9 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12027 2025-11-18 cs.CV cs.AI

GCAgent: Long-Video Understanding via Schematic and Narrative Episodic Memory

Jeong Hun Yeo, Sangyun Chung, Sungjune Park, Dae Hoe Kim, Jinyoung Moon, Yong Man Ro

机构 * Integrated Vision and Language Lab., School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST)(整合视觉与语言实验室,电气工程学院,韩国科学技术院(KAIST)) Visual Intelligence Research Section, Superintelligence Creative Research Laboratory, Electronics and Telecommunications Research Institute (ETRI)(视觉智能研究部,超智能创意研究实验室,电子电信研究院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09167 2025-11-13 cs.LG

Compact Memory for Continual Logistic Regression

Yohan Jung, Hyungi Lee, Wenlong Chen, Thomas Möllenhoff, Yingzhen Li, Juho Lee, Mohammad Emtiyaz Khan

机构 * RIKEN Center for AI Project(RIKEN人工智能研究中心) Kookmin University(韩国庆熙大学) Imperial College London(伦敦帝国理工学院) KAIST(韩国科学技术院)

Journal ref NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09142 2025-11-13 cs.RO

LODESTAR: Degeneracy-Aware LiDAR-Inertial Odometry with Adaptive Schmidt-Kalman Filter and Data Exploitation

Eungchang Mason Lee, Kevin Christiansen Marsim, Hyun Myung

机构 * KAIST InnoCORE LLM, KAIST(KAIST信息学院LLM研究中心,KAIST)

Comments 8 pages, 5 figures, 6 tables, accepted for the publication in IEEE Robotics and Automation Letters

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09135 2025-11-13 cs.CL cs.HC

One-Topic-Doesn't-Fit-All: Transcreating Reading Comprehension Test for Personalized Learning

Jieun Han, Daniel Lee, Haneul Yoo, Jinsung Yoon, Junyeong Park, Suin Kim, So-Yeon Ahn, Alice Oh

机构 * KAIST(韩国科学技术院) Salesforce AI Research(Salesforce人工智能研究) Google Cloud(谷歌云) Elice

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08748 2025-11-13 cs.CV

WiCV at CVPR 2025: The Women in Computer Vision Workshop

Estefania Talavera, Deblina Bhattacharjee, Himangi Mittal, Mengwei Ren, Karen Sanchez, Carla Muntean, JungEun Kim, Mona Jalal

机构 * University of Twente(特文特大学) University of Bath(巴斯大学) Carnegie Mellon University(卡内基梅隆大学) Adobe(Adobe公司) KAUST(科威特人工智能研究所以及先进技术中心) Microsoft(微软公司) KAIST(韩国科学技术院) General Robotics(通用机器人公司) Toyota Material Handling North America(丰田物流北美公司)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.04834 2025-11-13 cs.LG cs.AI cs.CV

Prompt-Based Safety Guidance Is Ineffective for Unlearned Text-to-Image Diffusion Models

Jiwoo Shin, Byeonghu Na, Mina Kang, Wonhyeok Choi, Il-Chul Moon

机构 * KAIST(韩国科学技术院)

Comments Accepted at NeurIPS 2025 Workshop on Generative and Protective AI for Content Creation

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08319 2025-11-12 cs.CL cs.AI cs.MA

Adaptive Multi-Agent Response Refinement in Conversational Systems

Soyeong Jeong, Aparna Elangovan, Emine Yilmaz, Oleg Rokhlenko

机构 * KAIST(韩国科学技术院) Amazon(亚马逊) Collate University College London(伦敦大学学院)

Comments LaCATODA Workshop @ AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.21402 2025-11-12 cs.LG cs.CV

Disentangled Representation Learning via Modular Compositional Bias

Whie Jung, Dong Hoon Lee, Seunghoon Hong

机构 * KAIST(韩国科学技术院)

Journal ref Advances in Neural Information Processing Systems (NeurIPS), 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.16565 2025-11-12 cs.CL cs.AI cs.LG

Language over Content: Tracing Cultural Understanding in Multilingual Large Language Models

Seungho Cho, Changgeon Ko, Eui Jun Hwang, Junmyeong Lee, Huije Lee, Jong C. Park

机构 * KAIST(韩国釜山科学技术院)

Comments Accepted to CIKM 2025 Workshop on Human Centric AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.12728 2025-11-12 physics.optics cs.CV cs.LG

Generalizable Holographic Reconstruction via Amplitude-Only Diffusion Priors

Jeongsol Kim, Chanseok Lee, Jongin You, Jong Chul Ye, Mooseok Jang

机构 * Department of Bio and Brain Engineering(生物与脑工程系) Department of Mechanical Engineering(机械工程系) Kim Jaechul Graduate School of AI(Kim Jaechul人工智能研究生院) KAIST Institute for Health Science and Technology(KAIST健康科学与技术研究所)

Comments Keywords: Diffusion model, phase retrieval, inline-holography, inverse problem

详情

展开后加载摘要…

URL PDF HTML 收藏