SJ
Sanghyun Jo
cs.CVcs.AIcs.CLcs.LG
On Valency
published · living versionsW_bhauer8q·v1 · currentpublished
Edited Endpoints as Partial Goals for Image-to-Video Generation
with Sihyun Kim, Kyungsu Kim
1 version
Preprints & journals
12 papers in the corpus · 2022–2026ReState: Noise-Level-Aware State Correction for Training-Free Object Removal in Few-Step Diffusion Models2610.21287v1 · Donghwan Lee, Sanghyun Jo, Sihyun Kim et al.2026 · 0 citationsarXiv
Depth-to-RGB: Repurposing a Frozen Depth Estimator for Geometry-Guided Compositing2610.09125v1 · Sanghyun Jo, Chae Yeon Lim, Donghwan Lee et al.2026 · 0 citationsarXiv
PatchGate: Narrowing the Verbalization Gap with Intrinsic Object Inventories in Frozen Vision-Language Models2608.21819v1 · Jihyung Ko, Eunji Jung, Hyeongsub Kim et al.2026 · 0 citationsarXiv
One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation2605.29429v2 · Sanghyun Jo, Seo Jin Lee, Seohyung Hong et al.2026 · 0 citationsarXiv
EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal2512.21545v2 · Sanghyun Jo, Donghwan Lee, Eunji Jung et al.2025 · 0 citationsarXiv
Early Timestep Zero-Shot Candidate Selection for Instruction-Guided Image Editing2504.13490v2 · Joowon Kim, Ziseok Lee, Donghyeon Cho et al.2025 · 1 citationarXiv
COIN: Confidence Score-Guided Distillation for Annotation-Free Cell Segmentation2503.11439v4 · Sanghyun Jo, Seo Jin Lee, Seungwoo Lee et al.2025 · 0 citationsarXiv
TRACE: Your Diffusion Model is Secretly an Instance Edge Detector2503.07982v4 · Sanghyun Jo, Ziseok Lee, Wooyeol Lee et al.2025 · 0 citationsarXiv
DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation2404.00380v2 · Sanghyun Jo, Fei Pan, In-Jae Yu et al.2024 · 5 citationsarXiv
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias2404.00384v2 · Sanghyun Jo, Soohyun Ryu, Sungyub Kim et al.2024 · 3 citationsarXiv
MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation2304.09913v1 · Sanghyun Jo, In-Jae Yu, Kyungsu Kim2023 · 33 citationsarXiv
RecurSeed and EdgePredictMix: Pseudo-Label Refinement Learning for Weakly Supervised Semantic Segmentation across Single- and Multi-Stage Frameworks2204.06754v4 · Sanghyun Jo, In-Jae Yu, Kyungsu Kim2022 · 4 citationsarXiv
Career total: 13 works. 12 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.