Publications

[P7] VaLoP: Value Gradient Lookahead and Pullback for Reward-Guided Diffusion
Preprint

[P7] VaLoP: Value Gradient Lookahead and Pullback for Reward-Guided Diffusion

Kwanyoung Kim

Preprint2026
[P6] GenTri: Generative Triangulation for Occlusion-Robust 3D Mouse Pose Estimation
Preprint

[P6] GenTri: Generative Triangulation for Occlusion-Robust 3D Mouse Pose Estimation

Daeyeon Kim, Kwanyoung Kim†, Jiyeon Kang†† Co-Corresponding Author

Preprint2026
[P5] MaDeL : Manifold-Decomposed Feature Losses for Generative Modeling
Preprint

[P5] MaDeL : Manifold-Decomposed Feature Losses for Generative Modeling

Beomsu Kim, Jong Chul Ye†, Kwanyoung Kim†† Co-Corresponding Author

Preprint2026
[P4] Adjoint Guidance Flow: Amortized Critic Guidance for VLA Policies
Preprint

[P4] Adjoint Guidance Flow: Amortized Critic Guidance for VLA Policies

Jeongsol Kim, Youngjun Jun, Kyumin Choi, Youngmin Kim, Seonghyun Jin, Sunwoo Park, Jangho Park, Kwanyoung Kim†, Jong Chul Ye†† Co-Corresponding Author

Preprint2026
[P3] VGAS: Variance-Reduced Guidance and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusion
Preprint

[P3] VGAS: Variance-Reduced Guidance and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusion

Kwanyoung Kim

Preprint2026
[P2] Directional Attention Guidance for Diffusion Models via Sparse Hopfield Retrieval
Preprint

[P2] Directional Attention Guidance for Diffusion Models via Sparse Hopfield Retrieval

Kwanyoung Kim

Preprint2026
[P1] UNICORN: Ultrasound Nakagami Imaging with Score Matching and Adaptation for Assessing Hepatic Steatosis
Preprint

[P1] UNICORN: Ultrasound Nakagami Imaging with Score Matching and Adaptation for Assessing Hepatic Steatosis

Kwanyoung Kim*, Jaa-yeon Lee*, Youngjun Ko, GunWoo Lee, Jong Chul Ye* Equal Contribution

Preprint2026
[C16] Single-Step Bidirectional Unpaired Image Translation Using Implicit Bridge Consistency Distillation
Top-tier

[C16] Single-Step Bidirectional Unpaired Image Translation Using Implicit Bridge Consistency Distillation

Suhyeon Lee*, Kwanyoung Kim*, Jong-Chul Ye* Equal Contribution

WACV 20272027
[C15] Adjoint Guidance Flow for Efficient Critic-Guided Vision-Language-Action Models
Workshop

[C15] Adjoint Guidance Flow for Efficient Critic-Guided Vision-Language-Action Models

Jeongsol Kim, Kwanyoung Kim†, Jong Chul Ye†† Co-Corresponding Author

NeurIPS 2026 Workshop (WRL)2026
[C14] GRAS: Guided Reduced-Variance Proposals and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusion
OralWorkshop

[C14] GRAS: Guided Reduced-Variance Proposals and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusion

Kwanyoung Kim

NeurIPS 2026 Workshop (BeNTo), Oral2026
[C13] Reward Sharpness-Aware Fine-Tuning for Diffusion Models
Top-tier

[C13] Reward Sharpness-Aware Fine-Tuning for Diffusion Models

Kwanyoung Kim*, Byeoung Su Sim** Equal Contribution

CVPR 20262026
[C12] Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model
Top-tier

[C12] Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model

Kwanyoung Kim, Sanghyun Kim

ICLR 20262026
[C11] Toward the Frontiers of Reliable Diffusion Sampling via Adversarial Sinkhorn Attention Guidance
Top-tier

[C11] Toward the Frontiers of Reliable Diffusion Sampling via Adversarial Sinkhorn Attention Guidance

Kwanyoung Kim

AAAI 20262026
[C10] PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity
Top-tier

[C10] PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity

Kwanyoung Kim, Byeongsu Sim

ICCV 20252025
[J2] End-to-End Breast Cancer Radiotherapy Planning via LMMs with Consistency Embedding
Impact Factor: 11.8

[J2] End-to-End Breast Cancer Radiotherapy Planning via LMMs with Consistency Embedding

Kwanyoung Kim*, Yujin Oh*, Sangjoon Park*, Hwa Kyung Byun, Jin Sung Kim, Yong Bae Kim, Jong-Chul Ye* Equal Contribution

Medical Image Analysis (MedIA)2025
[C9] OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation
Top-tier

[C9] OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation

Kwanyoung Kim*, Yujin Oh*, Jong-Chul Ye* Equal Contribution

ECCV 20242024
[C8] Unpaired Image-to-Image Translation via Neural Schrödinger Bridge
Top-tier

[C8] Unpaired Image-to-Image Translation via Neural Schrödinger Bridge

Beomsu Kim, Gihyun Kwon, Kwanyoung Kim, Jong-Chul Ye

ICLR 20242024
[C7] Noise2One: One-Shot Image Denoising with Local Implicit Learning
Oral

[C7] Noise2One: One-Shot Image Denoising with Local Implicit Learning

Kwanyoung Kim, Jong-Chul Ye

ICASSP 20242024
[C6] Noise Distribution Adaptive Self-Supervised Image Denoising using Tweedie Distribution and Score Matching
Top-tier

[C6] Noise Distribution Adaptive Self-Supervised Image Denoising using Tweedie Distribution and Score Matching

Kwanyoung Kim, Taesung Kwon, Jong-Chul Ye

CVPR 20222022
[C5] Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Images
Top-tier

[C5] Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Images

Kwanyoung Kim, Jong-Chul Ye

NeurIPS 20212021
[C4] Task-Aware Variational Adversarial Active Learning
Top-tier

[C4] Task-Aware Variational Adversarial Active Learning

Kwanyoung Kim, Dongwon Park, Kwang In Kim, Se Young Chun

CVPR 20212021
[J1] Unsupervised Training of Denoisers for Low-Dose CT Reconstruction Without Full-Dose Ground Truth
Impact Factor: 6.7

[J1] Unsupervised Training of Denoisers for Low-Dose CT Reconstruction Without Full-Dose Ground Truth

Kwanyoung Kim, Shakarim Soltanayev, Se Young Chun

IEEE Journal of Selected Topics in Signal Processing2021
[C3] NTIRE 2019 Challenge on Video Super-Resolution: Methods and Results
Workshop

[C3] NTIRE 2019 Challenge on Video Super-Resolution: Methods and Results

Seungjun Nah, Radu Timofte, Including (Kwanyoung Kim)

CVPRW 20192019
[C2] Efficient Module Based Single Image Super Resolution for Multiple Problems
Workshop

[C2] Efficient Module Based Single Image Super Resolution for Multiple Problems

Dongwon Park*, Kwanyoung Kim*, Se Young Chun* Equal Contribution

CVPRW 20182018
[C1] NTIRE 2018 Challenge on Single Image Super-Resolution: Methods and Results
Workshop

[C1] NTIRE 2018 Challenge on Single Image Super-Resolution: Methods and Results

Radu Timofte, Including (Kwanyoung Kim)

CVPRW 20182018

Create a free website with Framer, the website builder loved by startups, designers and agencies.