Our paper has been accepted to KDD.
Learning to Forget: Emotional Salience as a Compression Mechanism for Long-Term AI Memory SoYeop Yoo, Sunghoon Im† ACM SIGKDD Conference on Knowledge DIscovery and Data Minig (KDD), 2026
Five papers (including two findings) has been accepted to CVPR.
(1) TaskForce: Cooperative Multi-agent Reinforcement Learning for Multi-task Optimization Wonhyeok Choi, Kyumin Hwang, Jihun Park, Kyoungmin Lee, Seunghun Lee, Jaeyeul Kim, Minwoo Choi, Sunghoon Im† IEEE/CVF Conference on Computer Vision …
Our paper has been accepted to RAL.
Scale-invariant and View-relational Representation Learning for Full Surround Monocular Depth Kyumin Hwang*, Wonhyeok Choi*, Kiljoon Han, Wonjoon Choi, Minwoo Choi, Yongcheon Na, Minwoo Park, Sunghoon Im† IEEE Robotics and Automation …
Our paper has been accepted and selected as an Oral to AAAI.
Infinite-Story: A Training-Free Consistent Text-to-Image Generation Jihun Park*, Kyoungmin Lee*, Jongmin Gim*, Hyeonseo Jo, Minseok Oh, Wonhyeok Choi, Kyumin Hwang, Jaeyeul Kim, Minwoo Choi, Sunghoon Im† The Association for the …
Three papers have been accepted to ICCVw.
Semantic-Enhanced Monocular Depth Estimation via Fusion and Distillation of Foundation ModelsSanggyun Ma*, Wonjoon Choi*, Jihun Park, Jaeyeul Kim, Sunghoon Im†IEEE International Conference on Computer Vision Workshop (ICCVw), 2025 CAVIS: Context-Aware Video …
Four papers has been accepted to ICCV.
CAVIS: Context-Aware Video Instance SegmentaionSeunghun Lee*, Jiwan Seo*, Kiljoon Han, Minwoo Choi, Sunghoon Im†International Conference on Computer Vision (ICCV), 2025 Latest Object Memory Management for Temporally Consistent Video Instance SegmentationSeunghun …
Our paper has been selected as a highlight at CVPR.
Style-Editor: Text-driven object-centric style editingJihun Park*, Jongmin Gim*, Kyoungmin Lee*, Seunghun Lee, Sunghoon Im†IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025 Top 3.7% (483 out of 14,008 valid submissions)
Two papers has been accepted to CVPR.
Style-Editor: Text-driven object-centric style editingJihun Park*, Jongmin Gim*, Kyoungmin Lee*, Seunghun Lee, Sunghoon Im†IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025 Towards Lossless Implicit Neural Representation via Bit Plane DecompositionWoo Kyoung Han, …
Our paper has been accepted to RA-L.
Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow EstimationJaeyeul Kim, Jungwan Woo, Ukcheol Shin, Jean Oh, Sunghoon ImIEEE Robotics and Automation Letters (RA-L), 2025
Our paper has been accepted to ICLR.
Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet MiningWonhyeok Choi*, Kyumin Hwang*, Wei Peng, Minwoo Choi, Sunghoon ImInternational Conference on Learning Representations (ICLR), 2025