-
23
- NeurIPS 2025 Paper Presentations - Yonsei University School of Computing
- ✍️ Paper Titles & Authors (Spotlight) 1. Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning - Yeongbin Seo, Dongha Lee, Jaehyung Kim, Jinyoung Yeo* 2. Web-Shepherd: Advancing PRMs for Reinforcing Web Agents - Hyungjoo Chae, Sunghwan Kim, Junhee Cho, Seungone Kim, Seungjun Moon, Gyeom Hwangbo , Dongha Lim, Minjin Kim, Yeonjun Hwang, Minju Gwak, Dongwook Choi, Minseok Kang, Gwanhoon Im, ByeongUng Cho, Hyojun Kim, Jun Hee Han, Taeyoon Kwon, Minju Kim, Beong-woo Kwak, Dongjin Kang, Jinyoung Yeo* 1. Controllable 3D Molecular Generation for Structure-Based Drug Design Through Bayesian Flow Networks and Gradient Integration - Seungyeon Choi, Hwanhee Kim, Chihyun Park, Dahyeon Lee, Seungyong Lee, Yoonju Kim, Hyoungjoon Park, Sein Kwon, Youngwan Jo, Sanghyun Park* 2. FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning - Woosung Kim, Jinho Lee, Jongmin Lee*, Byung-Jun Lee* 3. Improved Algorithms for Overlapping and Robust Clustering of Edge-Colored Hypergraphs: An LP-Based Combinatorial Approach - Changyeol Lee, Yongho Shin, Hyung-Chan An 4. Information-Theoretic Discrete Diffusion - Moongyu Jeon, Sangwoo Shin, Dongjae Jeon, Albert No 5. Interpreting vision transformers via residual replacement model - Jinyeong Kim*, Junhyeok Kim*, Yumin Shim, Joohyeok Kim, Sunyoung Jung, Seong Jae Hwang 6. Optimized Minimal 3D Gaussian Splatting - Joo Chan Lee, Jong Hwan Ko*, Eunbyung Park* 7. Rare Text Semantics Were Always There in Your Diffusion Transformer - Seil Kang*, Woojung Han*, Dayun Ju, Seong Jae Hwang 8. Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics - Dongyoung Kim, Sumin Park, Huiwon Jang, Jinwoo Shin, Jaehyung Kim*, Younggyo Seo* 9. SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment - Wonje Jeung, Sangyeon Yoon, Minsuk Kahng*, Albert No* 10. VideoTitans: Scalable Video Prediction with Integrated Short- and Long-term Memory - Young-Jae Park, Minseok Seo and Hae-Gon Jeon For more details, visit the NeurIPS official website https://neurips.cc
- 첨단컴퓨팅학부 2025.10.10
-
22
- EMNLP 2025 Paper Presentations - Yonsei University School of Computing
- ✍️ Paper Titles & Authors 1. AmpleHate: Amplifying the Attention for Versatile Implicit Hate Detection - Yejin Lee, Joonghyuk Hahn, Hyeseon Ahn and Yo-Sub Han 2. Can Large Language Models be Effective Online Opinion Miners? - Ryang Heo, Yongsik Seo, Junseong Lee, Dongha Lee 3. Improving Chemical Understanding of LLMs via SMILES Parsing - Yunhui Jang, Jaehyung Kim, Sungsoo Ahn 4. Mondrian: A Framework for Logical Abstract (Re)Structuring - Elizabeth Grace Orwig, Shinwoo Park, Hyundong Jin and Yo-Sub Han 5. Personalized Language Models via Privacy-Preserving Evolutionary Model Merging - Kyuyoung Kim, Jinwoo Shin, Jaehyung Kim 6. Personalized LLM Decoding via Contrasting Personal Preference - Hyungjune Bu*, Chanjoo Jung*, Minjae Kang, Jaehyung Kim 7. R-TOFU: Unlearning in Large Reasoning Models - Sangyeon Yoon, Wonje Jeung, Albert No 8. SEPS: A Separability Measure for Robust Unlearning in LLMs - Wonje Jeung*, Sangyeon Yoon*, Albert No (Findings) 1. LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences - Liangqi Yuan, Dong-Jun Han, Christopher Brinton, and Sabine Brunswicker 2. Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching - Seoyeon Kim, Huiseo Kim, Chanjun Park, Jinyoung Yeo, Dongha Lee 3. CodeComplex: Dataset for Worst-Case Time Complexity Prediction - SeungYeop Baik, Joonghyuk Hahn, Jungin Kim, Aditi, Mingi Jeon, Yo-Sub Han and Sang-Ki Ko 4. How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code - Seonghyeon Lee, Heejae Chon, Joonwon Jang, Dongha Lee*, Hwanjo Yu* 5. PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents - Namyoung Kim, Kai Tzu-iunn Ong, Yeonjun Hwang, Minseok Kang, Iiseo Jihn, Gayoung Kim, Minju Kim, Jinyoung Yeo* 6. Stop Playing the Guessing Game! Target-Free User Simulation for Evaluating Conversational Recommender Systems - Sunghwan Kim*, Kwangwook Seo*, Tongyoung Kim*, Jinyoung Yeo, Dongha Lee 7. ToolHaystack: Stress-Testing Tool-Augmented Language Models in Realistic Long-Term Interactions - Beong-woo Kwak, Minju Kim, Dongha Lim, Hyungjoo Chae, Dongjin Kang, Sunghwan Kim, Dongil Yang, Jinyoung Yeo* 8. Towards Personalized Conversational Sales Agents: Contextual User Profiling for Strategic Action - Tongyoung Kim*, Jeongeun Lee*, Soojin Yoon, Seonghwan Kim, Dongha Lee 9. TrapDoc: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documents - Hyundong Jin, Sicheol Sung, Shinwoo Park, SeungYeop Baik and Yo-Sub Han For more details, visit the EMNLP 2025 homepage https://2025.emnlp.or
- 첨단컴퓨팅학부 2025.10.10
-
21
- ICCV 2025 Paper Presentations - Yonsei University School of Computing
- ✍️ Paper Titles & Authors (Highlight) 1. Inverse Image-Based Rendering for Light Field Generation from Single Images - Hyunjun Jung and Hae-Gon Jeon 2. Test-Time Prompt Tuning for Zero-Shot Depth Completion - Chanhwi Jeong, Inhwan Bae, Jin-Hwi Park and Hae-Gon Jeon 1. CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy - Dongyoung Kim, Mahmoud Afifi, Dongyun Kim, Michael S. Brown, Seon Joo Kim 2. CRAIM: Caption-Based Autonomous Driving Scene Retrieval via Inclusive Text Matching - Minjoo Ki, Dae Jung Kim, Kisung Kim, Seon Joo Kim, Jinhan Lee 3. ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors - Minsu Kim, Subin Jeon, In Cho, Mijin Yoo, Seon Joo Kim 4. Fuzzy Contrastive Decoding to Alleviate Object Hallucination in Large Vision-Language Models - Jieun Kim, Jinmyeong Kim, Yoonji Kim and Sung-Bae Cho 5. Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs - Jeongseok Hyun, Sukjun Hwang, Su Ho Han, Taeoh Kim, Inwoong Lee, Dongyoon Wee, Joon-Young Lee, Seon Joo Kim*, Minho Shim* 6. Open-ended Hierarchical Streaming Video Understanding with Vision Language Models - Hyolim Kang, Yunsu Park, Youngbeom Yoo, Yeeun Choi, Seon Joo Kim 7. Representing 3D Shapes with 64 Latent Vectors for 3D Diffusion Models - In Cho, Youngbeom Yoo, Subin Jeon, Seon Joo Kim 8. Seam360GS: Seamless 360° Gaussian Splatting from Real-World Omnidirectional Images - Changha Shin, Woong Oh Cho, Seon Joo Kim 9. Video Color Grading via Look-Up Table Generation - Seunghyun Shin, Dongmin Shin, Jisu Shin, Hae-Gon Jeon* and Joon-Young Lee* 10. WAVE: Warp-Based View Guidance for Consistent Novel View Synthesis Using a Single Image - Jiwoo Park, Tae Eun Choi, Youngjun Jun, Seong Jae Hwang For more details, visit the ICCV conference site. https://iccv.thecvf.com
- 첨단컴퓨팅학부 2025.10.10
-
20
- Sonic Labs Provides Further Funding to Prof. Burgstaller's Research Lab to Drive Blockchain Virtual Machine Innovation
- Sonic Labs Provides Further Funding to Prof. Burgstaller's Research Lab to Drive Blockchain Virtual Machine Innovation Sept. 18, 2025 The Embedded Systems Languages and Compilers (ELC) Lab at Yonsei University has received an unrestricted gift of $70,000 from Sonic Labs, the core development team behind Sonic, a high-performance EVM layer-1 blockchain. This raises Sonic Labs's total giving to the ELC lab to $150,000. ``The ELC lab significantly contributed to the off-chain testing technology for smart contracts, which effectively reduced end-to-end tests of our blockchain from several weeks to a few hours,'' said Michael Kong, CEO of Sonic Labs. ``Their method has largely improved the testability of blockchain virtual machine infrastructures, thereby addressing a real need with today's fast-moving DeFi sector.'' The new gift will be instrumental in devising space-efficient state representations that facilitate the execution of transactions in isolation and at scale. ``We are deeply grateful for the confidence shown by Sonic Labs. Their commitment to an unrestricted gift underscores their commitment to blockchain research and the need for a scalable testing infrastructure for the next generation of DeFi applications'' stated Prof. Burgstaller, director of the ELC lab. Sonic is the highest-performing EVM blockchain platform. It is innovating within the blockchain industry and helping augment existing public distributed ledger technology. Sonic Labs: https://soniclabs.com/ ELC Lab: https://elc.yonsei.ac.kr/
- 첨단컴퓨팅학부 2025.09.18
-
19
- Professor Hyung‑Chan An’s Research Team Has a Paper Accepted to FOCS 2025
- A joint research paper by Professor Hyung‑Chan An’s team at Yonsei University and Professor Mong‑Jen Kao’s team at National Yang‑Ming Chiao‑Tung University, titled “Handling LP‑Rounding for Hierarchical Clustering and Fitting Distances by Ultrametrics,” has been accepted to FOCS 2025 (IEEE Symposium on Foundations of Computer Science)—one of the most prestigious conferences in theoretical computer science. FOCS is recognized as a premier venue where the world’s leading researchers present breakthroughs in algorithms, complexity theory, and other core areas of computer science. This achievement once again demonstrates our department’s internationally recognized research strength in theoretical computer science. The paper introduces a new algorithmic technique for hierarchical clustering, advancing the state of research in this area. It will be presented at FOCS 2025 in December. Conference: https://focs.computer.org/2025/accepted-papers/ Preprint: https://arxiv.org/abs/2504.06700
- 첨단컴퓨팅학부 2025.08.01
-
18
- Professor Hojung Cha’s Research Team Wins Best Paper Award at ACM MobiSys 2025, the Top Conference in Mobile Systems
- The research team led by Professor Hojung Cha from the Department of Computer Science and Engineering at Yonsei University has received the Best Paper Award at ACM MobiSys 2025, the world's most prestigious conference in the field of mobile systems. The conference was held in Anaheim, California, USA, from June 23 to 27. Their award-winning paper, titled "ARIA: Optimizing Vision Foundation Model Inference on Heterogeneous Mobile Processors for Augmented Reality" (Authors: Chanyoung Jung, Jeho Lee, Geonjung Kim, Jiweon Kim, Sunghoon Park, and Hojung Cha), proposes a groundbreaking system that significantly accelerates on-device inference performance of vision foundation models (VFMs) for high-quality, real-time visual prediction in mobile augmented reality (AR) applications. By leveraging the heterogeneity of mobile processors equipped with GPUs and NPUs, and applying parallel and selective inference techniques, the research team successfully designed a system that maintains both prediction accuracy and real-time performance for complex VFMs on mobile devices. The originality and technical excellence of this work were highly recognized by the conference. This research marks a significant technological advancement essential for enabling immersive and high-quality mobile AR experiences, and it is expected to contribute greatly to the future development of mobile AI and AR technologies. Winning the Best Paper Award at the most influential international conference in mobile systems and computing not only demonstrates the global competitiveness of Korean research in this field but also serves as a representative achievement proving that Yonsei University's School of Computing is leading the way in world-class research and global talent development. [Conference link: https://www.sigmobile.org/mobisys/2025/accepted_papers/] [Paper link: https://mobed.yonsei.ac.kr/mobed_pages/pdf/aria-mobisys25.pdf] [Go to Yonsei News] [Read Article]
- 첨단컴퓨팅학부 2025.07.03
-
17
- Three Papers from Yonsei University’s School of Computing Accepted at ICML 2025!
- Yonsei University to Present Groundbreaking Machine Learning Research at ICML 2025! Yonsei University's cutting-edge AI research is gaining global recognition. Several papers by our university’s faculty members have been accepted for presentation at the upcoming International Conference on Machine Learning (ICML 2025), to be held in Vancouver, Canada from July 13 to 19, 2025. ICML is one of the world’s top three AI conferences, alongside NeurIPS and ICLR. Only a select few papers are accepted for presentation following a rigorous review process from thousands of global submissions. ICML 2025 will serve as a dynamic platform for exchanging the latest research with leading scholars in machine learning from around the world. Accepted Papers from Yonsei University at ICML 2025: 1. Bayesian Neural Scaling Laws Extrapolation with Prior-Fitted Networks - Dongwoo Lee*, Dong Bok Lee*, Steven Adriaensen, Juho Lee, Sung Ju Hwaang, Frank Hutter, Seon Joo Kim, Hae Beom Lee 2. ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification - Hyunseok Lee, Seunghyuk Oh, Jaehyung Kim, Jinwoo Shin, and Jihoon Tack 3. Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes (Spotlight (top 2.6%)) - Dongjae Jeon*, Dueun Kim*, and Albert No Looking Ahead: ICML 2026 in Seoul! This achievement is just the beginning. ICML 2026 will be held in Seoul, South Korea, offering a remarkable opportunity for Korea—and Yonsei University—to take center stage in global AI research. This promotional post is based on official ICML 2025 information. Specific presentation schedules and paper details will be announced through the conference website and official channels at a later date. Image source: https://europe.naverlabs.com/updates/icml-2024
- 첨단컴퓨팅학부 2025.06.27
-
16
- Application-aware System Optimization Lab (Professor: Park, Yongjun (박영준)) Publishes Two Papers at CGO and Chairs a Sess
- Application-aware System Optimization Lab (Professor: Park, Yongjun (박영준)) Publishes Two Papers at CGO and Chairs a Session Students from the Application-aware System Optimization Lab (Professor: Park, Yongjun (박영준)) presented two papers at the International Symposium on Code Generation and Optimization 2025 (CGO ‘25), one of the top international conferences in the field of compilers. Additionally, Prof. Park, Yongjun (박영준) served as the session chair for the Architectures and Code Generation session at the conference. The first paper, titled “CUrator: An Efficient LLM Execution Engine with Optimized Integration of CUDA Libraries,” proposes a technique for efficiently executing large language model (LLM) inference by leveraging cuBLAS and CUTLASS libraries on various modern GPUs. This research demonstrates peak inference performance for LLMs across multiple GPUs and is expected to guide the future direction of next-generation optimization frameworks. Paper link The second paper, titled “Accelerating LLMs using an Efficient GEMM Library and Target-Aware Optimizations on Real-world PIM Devices,” introduces an optimized GEMM library designed for Processing-in-Memory (PIM) architectures and proposes additional optimization techniques to accelerate LLM inference. This study effectively utilizes PIM architectures to address the inference slowdown caused by the high data requirements of large language models, playing a crucial role in overcoming this challenge. Paper link
- 첨단컴퓨팅학부 2025.03.25
-
15
- Yonsei University’s School of Computing Professors Have Papers Accepted at CHI 2025, the World’s Leading HCI Conference
- Yonsei University’s School of Computing Professors Have Papers Accepted at CHI 2025, the World’s Leading HCI Conference Professors from Yonsei University’s School of Computing have had their research papers accepted at CHI 2025, the ACM Conference on Human Factors in Computing Systems, the most prestigious academic conference in the field of Human-Computer Interaction (HCI). CHI 2025 is a premier international conference where pioneering research in HCI is presented. It will take place in Yokohama, Japan, from April 26 to May 1, 2025. The theme of CHI 2025 is "Ikigai", meaning "a purpose in life." As research on how technology can positively impact human life is increasingly important, the contributions of Yonsei University researchers stand out even more. Their papers address research topics that have a tangible impact on people’s lives, making their acceptance at CHI 2025 a particularly meaningful achievement. This accomplishment further solidifies Yonsei University’s global leadership in HCI and AI research. The university remains committed to advancing technologies that bring real benefits to people’s lives through ongoing research and innovation. List of accepted papers: 1. Crafting Champions: An Observation Study of Esports Coaching Processes - Hanbyeol Lee*, Erica Kleinman*, Namsub Kim, Sangbeom Park, Casper Harteveld, Byungjoo Lee 2. Data Formulator 2: Iterative Creation of Data Visualizations, with AI Transforming Data Along the Way - Chenglong Wang, Bongshin Lee, Steven M. Drucker, Dan Marshall, Jianfeng Gao 3. DataSentry: Building Missing Data Management System for In-the-Wild Mobile Sensor Data Collection through Multi-Year Iterative Design Approach - Yugyeong Jung, Hei Yiu Law, Hazel Hadong Lee, Junmo Lee, Bongshin Lee, Uichin Lee 4. FluidTrack: Investigating Child-Parent Collaborative Tracking for Pediatric Voiding Dysfunction Management - Junhyung Moon, Sukhyun Lee, Youngchan Kim, Juhee Go, Han Mo Ku, Yeohyun Jung, Seonyeong Hwang, Bongshin Lee, Yong Seung Lee, Hyun-Kyung Lee, Kyoungwoo Lee*, Eun Kyoung Choe* 5. Hardware-Embedded Pointing Transfer Function Capable of Canceling OS Gains - Seonho Kim, Munjeong Kim, Jonghyun Kim, Donghyeon Kang, Sunjun Kim, Byungjoo Lee 6. Modeling User Performance in Multi-Lane Moving-Target Acquisition - Jonghyun Kim, Joongseok Kim, June-Seop Yoon, Hee-Seung Moon, Sunjun Kim, Byungjoo Lee 7. PlanTogether: Facilitating AI Application Planning Using Information Graphs and Large Language Models - Dae Hyun Kim*, Daeheon Jeong*, Shakhnozakhon Yadgarova, Hyungyu Shin, Jinho Son, Hariharan Subramonyam, Juho Kim In addition to the full papers mentioned above, two Late Breaking Work papers will also be presented as posters. [Late-Breaking Work (Poster)] 1. LLM Adoption in Data Curation Workflows: Industry Practices and Insights - Crystal Qian, Michael Xieyang Liu, Emily Reif, Grady Simon, Nada Hussein, Nathan Clement, James Wexler, Carrie J. Cai, Michael Terry, Minsuk Kahng 2. Who Helps the Helpers?: Complications and Considerations for ICT Instructors Teaching Older Adults - Jiwon Song, Bongshin Lee, Jinwook Seo*, Eun Kyoung Choe* #YonseiUniversity #CHI2025 #HCI #ResearchAchievement #AI #Ikigai Image Source:CHI 2025 Facebook (https://www.facebook.com/acmchi)
- 첨단컴퓨팅학부 2025.03.20
-
14
- Yonsei University’s School of Computing Has 9 Papers Accepted at CVPR 2025
- Yonsei University’s School of Computing Has 9 Papers Accepted at CVPR 2025 Professors from Yonsei University’s School of Computing have had 9 papers accepted at the Conference on Computer Vision and Pattern Recognition (CVPR) 2025. These papers present groundbreaking advancements in computer vision and pattern recognition, earning high praise from researchers worldwide. In particular, they introduce innovative methodologies applicable to cutting-edge fields such as deep learning-based image understanding, autonomous driving, and medical image analysis, drawing significant attention from both academia and industry. CVPR is one of the most prestigious international conferences, where top AI and computer vision researchers gather annually to present and discuss state-of-the-art research. With its highly competitive acceptance rate, CVPR stands as a premier venue for AI research. The acceptance of these papers once again demonstrates the global research competitiveness of Yonsei University’s School of Computing and solidifies its position as a leading institution in AI research. List of accepted papers: 1. Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation - Chanyoung Kim, Dayun Ju, Woojung Han, Ming-Hsuan Yang, Seong Jae Hwang 2. EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting - Dong In Lee, Hyeongcheol Park, Jiyoung Seo, Eunbyung Park, Hyunje Park, Ha Dam Baek, Shin Sangheon, Sangmin Kim, Sangpil Kim 3. Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction - Seungtae Nam*, Xiangyu Sun*, Gyeongjin Kang, Younggeun Lee, Seungjun Oh, Eunbyung Park 4. Latent space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models - Jinho Jeong, Sangmin Han, Jinwoo Kim, Seon Joo Kim 5. Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks - Miran Heo, Min-Hung Chen, De-An Huang, Sifei Liu, Subhashree Radhakrishnan, Seon Joo Kim, Yu-Chiang Frank Wang, Ryo Hachiuma - https://miranheo.github.io/omni-rgpt/ 6. ORIDa: Object-centric Real-world Image Composition Dataset - Jinwoo Kim, Sangmin Han, Jinho Jeong, Jiwoo Choi, Dongyoung Kim, Seon Joo Kim 7. SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting - Gyeongjin Kang*, Jisang Yoo*, Jihyeon Park, Seungtae Nam, Hyeonsoo Im, Sangheon Shin, Sangpil Kim, Eunbyung Park 8. Spatial Transport Optimization by Repositioning Attention Map for Training-Free Text-to-Image Synthesis - Woojung Han, Yeonkyung Lee, Chanyoung Kim, Kwanghyun Park, Seong Jae Hwang 9. Your Large Vision-Language Model Only Needs A Few Attention Heads for Visual Grounding - Seil Kang, Jinyoung Kim, Junhyeok Kim, Seong Jae Hwang Image Source:CVPR Official Website (https://cvpr.thecvf.com)
- 첨단컴퓨팅학부 2025.03.20