Sungroh Yoon

Venues

Frequent coauthors

Papers

1. CANDI: Curated Test-Time Adaptation for Multivariate Time-Series Anomaly Detection Under Distribution Shift
   AAAI 2026 ·

   HyunGi Kim

   DBLP profile ↗ORCID search ↗
2. DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy
   WACV 2026 ·

   Jaewoo Song

   DBLP profile ↗ORCID search ↗
3. GDoFS: Gaussian DoF Separation for Plausible 3D Geometry in Sparse-View 3DGS
   WACV 2026 ·

   Yongsung Kim

   DBLP profile ↗ORCID search ↗
4. Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignment
   WACV 2026 ·

   Sangha Park

   DBLP profile ↗ORCID search ↗
5. SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination
   WACV 2026 ·

   Sangha Park

   DBLP profile ↗ORCID search ↗
6. Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions
   ACL 2026 ·

   Dongwook Lee

   DBLP profile ↗ORCID search ↗
7. Style-Friendly SNR Sampler for Style-Driven Generation
   WACV 2026 ·

   Jooyoung Choi

   DBLP profile ↗ORCID search ↗
8. Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning
   ACL 2026 ·

   Sangkwon Park

   DBLP profile ↗ORCID search ↗
9. Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptation
   AAAI 2025 ·

   HyunGi Kim

   DBLP profile ↗ORCID search ↗
10. Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection
    ICML 2025 ·

    HyunGi Kim

    DBLP profile ↗ORCID search ↗
11. Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment
    NAACL 2025 ·

    Sangwon Yu

    DBLP profile ↗ORCID search ↗
12. DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection
    CVPR 2025 ·

    Jaewoo Song

    DBLP profile ↗ORCID search ↗
13. Disentangled Motion Modeling for Video Frame Interpolation
    AAAI 2025 ·

    Jaihyun Lew

    DBLP profile ↗ORCID search ↗
14. Does Your Voice Assistant Remember? Analyzing Conversational Context Recall and Utilization in Voice Interaction Models
    ACL 2025 ·

    Heeseung Kim

    DBLP profile ↗ORCID search ↗
15. EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models
    ACL 2025 ·

    Che Hyun Lee

    DBLP profile ↗ORCID search ↗
16. Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis
    ACL 2025 ·

    Jisoo Mok

    DBLP profile ↗ORCID search ↗
17. Interpretable Next-token Prediction via the Generalized Induction Head
    NeurIPS 2025 ·

    Eunji Kim

    DBLP profile ↗ORCID search ↗
18. Know "No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP
    ICCV 2025 ·

    Junsung Park

    DBLP profile ↗ORCID search ↗
19. Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator
    CVPR 2025 ·

    Chaehun Shin

    DBLP profile ↗ORCID search ↗
20. RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models
    NeurIPS 2025 ·

    Yeongtak Oh

    DBLP profile ↗ORCID search ↗
21. Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion
    CVPR 2025 ·

    Eunji Kim

    DBLP profile ↗ORCID search ↗
22. Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage
    ICML 2025 ·

    Saehyung Lee

    DBLP profile ↗ORCID search ↗
23. Unleashing Multi-Hop Reasoning Potential in Large Language Models through Repetition of Misordered Context
    NAACL 2025 ·

    Sangwon Yu

    DBLP profile ↗ORCID search ↗
24. Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models
    ICML 2025 ·

    Mingi Jung

    DBLP profile ↗ORCID search ↗
25. CKNN: Cleansed k-Nearest Neighbor for Unsupervised Video Anomaly Detection
    CIKM 2024 ·

    Jihun Yi

    DBLP profile ↗ORCID search ↗
26. ControlDreamer: Blending Geometry and Style in Text-to-3D
    BMVC 2024 ·

    Yeongtak Oh

    DBLP profile ↗ORCID search ↗
27. Controlled Text Generation for Black-box Language Models via Score-based Progressive Editor
    ACL 2024 ·

    Sangwon Yu

    DBLP profile ↗ORCID search ↗
28. DAFA: Distance-Aware Fair Adversarial Training
    ICLR 2024 ·

    Hyungyu Lee

    DBLP profile ↗ORCID search ↗
29. Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation
    ECCV 2024 ·

    Yeongtak Oh

    DBLP profile ↗ORCID search ↗
30. Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors
    ICLR 2024 ·

    Jonghyun Lee

    DBLP profile ↗ORCID search ↗
31. Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach
    ACL 2024 ·

    Saehyung Lee

    DBLP profile ↗ORCID search ↗
32. Introducing Spectral Attention for Long-Range Dependency in Time Series Forecasting
    NeurIPS 2024 ·

    Bong Gyun Kang

    DBLP profile ↗ORCID search ↗
33. LLM-based Frameworks for API Argument Filling in Task-Oriented Conversational Systems
    NAACL 2024 ·

    Jisoo Mok

    DBLP profile ↗ORCID search ↗
34. Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation
    NeurIPS 2024 ·

    Heeseung Kim

    DBLP profile ↗ORCID search ↗
35. SF(DA)2: Source-free Domain Adaptation Through the Lens of Data Augmentation
    ICLR 2024 ·

    Uiwon Hwang

    DBLP profile ↗ORCID search ↗
36. Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP
    EMNLP 2024 ·

    Eunji Kim

    DBLP profile ↗ORCID search ↗
37. Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection
    NeurIPS 2024 ·

    Saehyung Lee

    DBLP profile ↗ORCID search ↗
38. Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization
    NeurIPS 2024 ·

    Sanghyeob Song

    DBLP profile ↗ORCID search ↗
39. VoiceTailor: Lightweight Plug-In Adapter for Diffusion-Based Personalized Text-to-Speech
    InterSpeech 2024 ·

    Heeseung Kim

    DBLP profile ↗ORCID search ↗