Byeongsu Sim

5 papers · 2022–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird

Venues

CVPR (3) ICCV (1) NeurIPS (1)

Top co-authors

Hyungjin Chung (3) Jong Chul Ye (3) Kwanyoung Kim (2) Won Jun Kim (1) Jaemin Kim (1) Dohoon Ryu (1) Sangmin Lee (1)

Research topics

Deep Learning (5) Models (5) Machine Learning (4) Optimization & Theory (3) Artificial Intelligence (2) Computer Vision (2) Core AI (2) Learning Types · Deep Learning (2) Learning Types · Machine Learning (2) Processing (2) Application Areas (1) Core Methods (1)

Keywords

diffusion model (4) image restoration (2) image inpainting (2) manifold constraint (2) inverse problem (2) reward hacking (1) perceptual quality (1) classifier-free guidance (1) inference optimization (1) sparse attention (1) sampling acceleration (1) black-box model (1) computed tomography (1) counterfactual generation (1) ensemble kalman filter (1) stochastic contraction (1) diffusion reinforcement learning (1) manifold learning (1) reward sharpness-aware fine-tuning (1) explainable ai (1)

Papers

Reward Sharpness-Aware Fine-Tuning for Diffusion Models CVPR 2026 Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI CVPR 2025 PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity ICCV 2025 Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems Through Stochastic Contraction CVPR 2022 Improving Diffusion Models for Inverse Problems using Manifold Constraints NeurIPS 2022