Paul Hongsuck Seo

Venues

Frequent coauthors

Papers

1. GOAT: A Training Framework for Goal-Oriented Agent with Tools
   ACL 2026 ·

   Hyunji Min

   DBLP profile ↗ORCID search ↗
2. Bridging Audio and Vision: Zero-Shot Audiovisual Segmentation by Connecting Pretrained Models
   InterSpeech 2025 ·

   Seung-jae Lee

   DBLP profile ↗ORCID search ↗
3. Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries
   InterSpeech 2025 ·

   Minyoung Kim

   DBLP profile ↗ORCID search ↗
4. DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization
   InterSpeech 2025 ·

   Geonyoung Lee

   DBLP profile ↗ORCID search ↗
5. DialNav: Multi-Turn Dialog Navigation with a Remote Guide
   ICCV 2025 ·

   Leekyeung Han

   DBLP profile ↗ORCID search ↗
6. LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs
   NAACL 2025 ·

   Sumin An

   DBLP profile ↗ORCID search ↗
7. Multi-Granularity Video Object Segmentation
   AAAI 2025 ·

   Sangbeom Lim

   DBLP profile ↗ORCID search ↗
8. Random Conditioning for Diffusion Model Compression with Distillation
   CVPR 2025 ·

   Dohyun Kim

   DBLP profile ↗ORCID search ↗
9. ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervision
   ACL 2025 ·

   Dosung Lee

   DBLP profile ↗ORCID search ↗
10. ReTAG: Retrieval-Enhanced, Topic-Augmented Graph-Based Global Sensemaking
    EMNLP 2025 ·

    Boyoung Kim

    DBLP profile ↗ORCID search ↗
11. Seg4Diff: Unveiling Open-Vocabulary Semantic Segmentation in Text-to-Image Diffusion Transformers
    NeurIPS 2025 ·

    Chaehyun Kim

    DBLP profile ↗ORCID search ↗
12. CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation
    CVPR 2024 ·

    Seokju Cho

    DBLP profile ↗ORCID search ↗
13. Learning Correlation Structures for Vision Transformers
    CVPR 2024 ·

    Manjin Kim

    DBLP profile ↗ORCID search ↗
14. Pseudo-RIS: Distinctive Pseudo-Supervision Generation for Referring Image Segmentation
    ECCV 2024 ·

    Seonghoon Yu

    DBLP profile ↗ORCID search ↗
15. Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels
    NeurIPS 2024 ·

    Heeseong Shin

    DBLP profile ↗ORCID search ↗
16. TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation
    NeurIPS 2024 ·

    Seong Hyeon Park

    DBLP profile ↗ORCID search ↗