News

Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World ModelDongwon Kim, Gawon Seo, Jinsung Lee, Minsu Cho, Suha KwakIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Denver, 2026FlashDecoder: Real-Time Latent-to-Pixel Streaming Decoder with TransformersMinguk Kang,..

Exploring State-Space Models for Data-Specific Neural RepresentationJinsung Lee and Suha Kwak International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, 2026

We won six paper awards including the gold prize at IPIU 2026.Gold Prize Event-Centric Chain-of-Thought for Reasoning Temporal Localization in Videos (Youngkil Song, Yoonjae Baek, Dongwon Kim, Inho Kim, Dongkeun Kim, Suha Kwak)Bronze Prize생성적 복원을 통한 RGBD 영상에서의 3차원 행동유도성 인식 학습 (Chunghyun Park, S..

Dayoung Gong, Chunghyun Park, Namhun Kim and Yeho Gwon won the POSTECHIAN fellowship award. Congratulations!

GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank AdaptationSohyun Lee, Yeho Gwon, Lukas Hoyer and Suha KwakAdvances in Neural Information Processing Systems (NeurIPS), San Diego, 2025Part-Aware Bottom-Up Group Reasoning for Fine-Grained Social Interaction DetectionDongkeun Kim, Minsu Ch..

Enhancing Cost Efficiency in Active Learning with Candidate Set QueryYeho Gwon, Sehyun Hwang, Hoyoung Kim, Jungseul Ok, and Suha KwakTransactions on Machine Learning Research (TMLR), 2025

Latent Expression Generation for Referring Image Segmentation and GroundingSeonghoon Yu, Junbeom Hong, Joonseok Lee, Jeany SonIEEE/CVF International Conference on Computer Vision (ICCV), Honolulu, Hawaii, 2025Online Generic Event Boundary DetectionHyung Rok Jung*, Daneul Kim*, Seunggyun Lim, Jeany S..

Profs. Cho and Kwak serve as Senior Area Chair (SAC) for ICCV 2025.

Yeho Gwon won the Best Research Project Award. Congratulations!

GENIUS: A Generative Framework for Universal Multimodal SearchSungyeon Kim, Xinliang Zhu, Xiaofan Lin, Muhammet Bastan, Douglas Gray, Suha KwakIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 2025Improving Sound Source Localization with Joint Slot Attention on Image ..

Decoupled Finetuning for Domain Generalizable Semantic SegmentationJaehyun Pahk, Donghyeon Kwon, Seong Joon Oh, Suha KwakInternational Conference on Learning Representations (ICLR), Singapore, 2025

Profs. Cho and Kwak serve as Senior Area Chair (SAC) and Area Chair (AC), respectively, for CVPR 2025.