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

Dynamic neuron approach to deep neural networks: Decoupling neurons for renormalization group analysis

Donghee Lee, Hye-Sung Lee, Jaeok Yi

机构 * Department of Physics, Korea Advanced Institute of Science and Technology（韩国科学技术院物理系） 纠错

Comments Version matching the publication

Journal ref Phys. Rev. Research 7, 023276 (2025)

A Miniature High-Resolution Tension Sensor Based on a Photo-Reflector for Robotic Hands and Grippers

Hyun-Bin Kim, Kyung-Soo Kim

机构 * Mechatronics, Systems and Control (MSC) laboratory, Korea Advanced Institute of Science and Technology (KAIST)（机电系统与控制（MSC）实验室，韩国科学技术院（KAIST）） 纠错

Instruct-4DGS: Efficient Dynamic Scene Editing via 4D Gaussian-based Static-Dynamic Separation

Joohyun Kwon, Hanbyel Cho, Junmo Kim

机构 * DGIST ； KAIST（韩国国立科学技术院） 纠错

Comments Accepted to CVPR 2025. The first two authors contributed equally

Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback

Kyuyoung Kim, Ah Jeong Seo, Hao Liu, Jinwoo Shin, Kimin Lee

机构 * KAIST（韩国科学技术院） ； UC Berkeley（加州大学伯克利分校） 纠错

Comments EMNLP 2024 Findings

ReCo: Reminder Composition Mitigates Hallucinations in Vision-Language Models

Sotirios Panagiotis Chytas, Miso Choi, Hyunwoo J. Kim, Vikas Singh

机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； Korea University（韩国大学） ； KAIST（韩国科学技术院） 纠错

Remote Sensing Large Vision-Language Model: Semantic-augmented Multi-level Alignment and Semantic-aware Expert Modeling

Sungjune Park, Yeongyun Kim, Se Yeon Kim, 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）） 纠错

Comments 13 pages including reference pages, 7 tables, and 6 figures

StarFT: Robust Fine-tuning of Zero-shot Models via Spuriosity Alignment

Younghyun Kim, Jongheon Jeong, Sangkyung Kwak, Kyungmin Lee, Juho Lee, Jinwoo Shin

机构 * Samsung（三星） ； Korea University（韩国大学） ； General Robotics（通用机器人） ； KAIST（韩国科学技术院） 纠错

Comments IJCAI 2025; Code is available at https://github.com/alinlab/StarFT

Tabular Feature Discovery With Reasoning Type Exploration

Sungwon Han, Sungkyu Park, Seungeon Lee

机构 * GIST（韩国科学技术院） ； KDI School of Public Policy and Management（KDI公共政策与管理学院） ； KAIST（韩国科学技术院） 纠错

Diffusion Models Through a Global Lens: Are They Culturally Inclusive?

Zahra Bayramli, Ayhan Suleymanzade, Na Min An, Huzama Ahmad, Eunsu Kim, Junyeong Park, James Thorne, Alice Oh

机构 * School of Computing, KAIST（韩国成均馆大学计算机学院） ； Graduate School of AI, KAIST（韩国成均馆大学人工智能研究生院） 纠错

Comments 17 pages, 17 figures, 3 tables

MambaOutRS: A Hybrid CNN-Fourier Architecture for Remote Sensing Image Classification

Minjong Cheon, Changbae Mun

机构 * KAIST Applied Science Research Institute（韩国釜山科学技术院应用科学研究所） ； Department of Electrical, Electronic & Communication Engineering（电子电气与通信工程系） 纠错

Low-Complexity Semantic Packet Aggregation for Token Communication via Lookahead Search

Seunghun Lee, Jihong Park, Jinho Choi, Hyuncheol Park

机构 * School of Electrical Engineering, Korea Advanced Institute of Science and Technology（韩国科学技术院电子工程学院） ； ISTD Pillar, Singapore University of Technology and Design（新加坡科技设计大学ISTD支柱） ； School of Electrical and Mechanical Engineering, The University of Adelaide（阿德莱德大学电气与机械工程学院） 纠错

Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation

Jisu Shin, Juhyun Oh, Eunsu Kim, Hoyun Song, Alice Oh

机构 * School of Computing（计算机学院） ； Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院） 纠错

Comments Findings of ACL 2025; github repo: https://github.com/ddindidu/atomic-persona-evaluation/

Object-aware Sound Source Localization via Audio-Visual Scene Understanding

Sung Jin Um, Dongjin Kim, Sangmin Lee, Jung Uk Kim

机构 * Kyung Hee University（庆熙大学） ； KAIST AI（韩国科学技术院人工智能研究所） ； Sungkyunkwan University（成均馆大学） 纠错

Comments Accepted at CVPR 2025

Journal ref Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), 2025, pp. 8342-8351

Rethinking Decoder Design: Improving Biomarker Segmentation Using Depth-to-Space Restoration and Residual Linear Attention

Saad Wazir, Daeyoung Kim

机构 * School of Computing, KAIST, Republic of Korea（韩国科学技术院计算机学院） 纠错

Comments Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), 2025, pp. 30861-30871

Pathwise Explanation of ReLU Neural Networks

Seongwoo Lim, Won Jo, Joohyung Lee, Jaesik Choi

机构 * Ulsan National Institute of Science and Technology (UNIST)（乌山国立科学技术研究院） ； Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院） ； Arizona State University（亚利桑那州立大学） ； Samsung Research（三星研究院） ； INEEJI 纠错

Comments In Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:4645-4653, 2024

SELFI: Selective Fusion of Identity for Generalizable Deepfake Detection

Younghun Kim, Minsuk Jang, Myung-Joon Kwon, Wonjun Lee, Changick Kim

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

Global Context-aware Representation Learning for Spatially Resolved Transcriptomics

Yunhak Oh, Junseok Lee, Yeongmin Kim, Sangwoo Seo, Namkyeong Lee, Chanyoung Park

机构 * Graduate School of Data Science, KAIST, Daejeon, Republic of Korea ； Department of Industrial \& Systems Engineering, KAIST, Daejeon, Republic of Korea ； Department of Mathematical Sciences, KAIST, Daejeon, Republic of Korea 纠错

Comments ICML 2025

A Large-Scale Real-World Evaluation of LLM-Based Virtual Teaching Assistant

Sunjun Kweon, Sooyohn Nam, Hyunseung Lim, Hwajung Hong, Edward Choi

机构 * KAIST（韩国科学技术院） 纠错

Comments ACL 2025 Industry Track

On Training-Test (Mis)alignment in Unsupervised Combinatorial Optimization: Observation, Empirical Exploration, and Analysis

Fanchen Bu, Kijung Shin

机构 * School of Electrical Engineering, KAIST（韩国庆熙大学电气工程学院） ； AI4CO Open-Source Community（AI4CO开源社区） ； Kim Jaechul Graduate School of Artificial Intelligence, KAIST（韩国庆熙大学人工智能研究生院） 纠错

Comments 2nd Workshop on Test-Time Adaptation: Putting Updates to the Test @ ICML 2025

Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification

Langzhang Liang, Fanchen Bu, Zixing Song, Zenglin Xu, Shirui Pan, Kijung Shin

机构 * Kim Jaechul Graduate School of Artificial Intelligence, KAIST, Seoul, Republic of Korea（韩国釜山科学技术院人工智能研究生院） ； School of Electrical Engineering, KAIST, Daejeon, Republic of Korea（韩国釜山科学技术院电子工程学院） ； Department of Engineering, University of Cambridge, Cambridge, United Kingdom（剑桥大学工程系） ； Incubation Institute, Fudan University, Shanghai, China（复旦大学孵化院） ； Shanghai Academy of Artificial Intelligence for Science, Shanghai, China（上海人工智能科学研究院） ； School of Information and Communication Technology, Griffith University, Gold Coast, Australia（格里菲斯大学信息与通信技术学院） 纠错

Comments Published as a conference paper at ICML 2025

Towards Classifying Histopathological Microscope Images as Time Series Data

Sungrae Hong, Hyeongmin Park, Youngsin Ko, Sol Lee, Bryan Wong, Mun Yong Yi

机构 * Korea Advanced Institute of Science and Technology（韩国科学技术院） ； Seegene Medical Foundation（Seegene医疗基金会） 纠错

Comments 5 pages, 4 figures, Accepted by International Symposium on Biomedical Imaging (ISBI) 2025

Hierarchical and Modular Network on Non-prehensile Manipulation in General Environments

Yoonyoung Cho, Junhyek Han, Jisu Han, Beomjoon Kim

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

Comments http://unicorn-hamnet.github.io/

When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and Class

Yujin Kim, Hyunsoo Kim, Hyunwoo J. Kim, Suhyun Kim

机构 * Korea University（韩国大学） ； Korea Advanced Institute of Science and Technology（韩国科学技术院） ； Kyung Hee University（庆熙大学） ； Korea Institute of Science（韩国科学研究院） 纠错

Comments Published at ICML 2025

Efficient Navigation Among Movable Obstacles using a Mobile Manipulator via Hierarchical Policy Learning

Taegeun Yang, Jiwoo Hwang, Jeil Jeong, Minsung Yoon, Sung-Eui Yoon

机构 * School of Computing in Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院计算机学院） ； Robotics Program at the same institute, KAIST（韩国科学技术院机器人项目） 纠错

Comments 8 pages, 6 figures, Accepted to IROS 2025. Supplementary Video: https://youtu.be/sZ8_z7sYVP0

DreamGen: Unlocking Generalization in Robot Learning through Video World Models

Joel Jang, Seonghyeon Ye, Zongyu Lin, Jiannan Xiang, Johan Bjorck, Yu Fang, Fengyuan Hu, Spencer Huang, Kaushil Kundalia, Yen-Chen Lin, Loic Magne, Ajay Mandlekar, Avnish Narayan, You Liang Tan, Guanzhi Wang, Jing Wang, Qi Wang, Yinzhen Xu, Xiaohui Zeng, Kaiyuan Zheng, Ruijie Zheng, Ming-Yu Liu, Luke Zettlemoyer, Dieter Fox, Jan Kautz, Scott Reed, Yuke Zhu, Linxi Fan

机构 * NVIDIA ； University of Washington（华盛顿大学） ； KAIST（韩国科学技术院） ； UCLA（加州大学洛杉矶分校） ； UCSD（加州大学圣地亚哥分校） ； CalTech（加州理工学院） ； NTU（国立台湾大学） ； University of Maryland（马里兰大学） ； UT Austin（得克萨斯大学奥斯汀分校） 纠错

Comments See website for videos: https://research.nvidia.com/labs/gear/dreamgen

Efficient multi-view training for 3D Gaussian Splatting

Minhyuk Choi, Injae Kim, Hyunwoo J. Kim

机构 * Korea University（韩国大学） ； KAIST（韩国科学技术院） 纠错

Flat Posterior Does Matter For Bayesian Model Averaging

Sungjun Lim, Jeyoon Yeom, Sooyon Kim, Hoyoon Byun, Jinho Kang, Yohan Jung, Jiyoung Jung, Kyungwoo Song

机构 * KAIST（韩国科学技术院） 纠错

Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry

Junyoung Seo, Jisang Han, Jaewoo Jung, Siyoon Jin, Joungbin Lee, Takuya Narihira, Kazumi Fukuda, Takashi Shibuya, Donghoon Ahn, Shoukang Hu, Seungryong Kim, Yuki Mitsufuji

机构 * KAIST AI（韩国科学技术院人工智能研究所） ； Sony AI（索尼人工智能实验室） ； Sony Group Corporation（索尼集团） 纠错

Comments Our project page can be found at https://cvlab-kaist.github.io/Vid-CamEdit/

Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models

Tung Minh Luu, Younghwan Lee, Donghoon Lee, Sunho Kim, Min Jun Kim, Chang D. Yoo

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

Comments Accepted to ICML 2025

PDEfuncta: Spectrally-Aware Neural Representation for PDE Solution Modeling

Minju Jo, Woojin Cho, Uvini Balasuriya Mudiyanselage, Seungjun Lee, Noseong Park, Kookjin Lee

机构 * LG CNS ； TelePIX ； SCAI ； Arizona State University（亚利桑那州立大学） ； Brookhaven National Laboratory（布鲁克海文国家实验室） ； KAIST（韩国科学技术院） 纠错