Jong Chul Ye

PCPO: Proportionate Credit Policy Optimization for Preference Alignment of Image Generation Models

Diverse Text-to-Image Generation via Contrastive Noise Optimization

Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs

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

Extreme Blind Image Restoration via Prompt-Conditioned Information Bottleneck

Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies

TokenDrop: Efficient Image Editing by Source Token Drop with Consistency Regularization

Align Your Tangent: Training Better Consistency Models via Manifold-Aligned Tangents

Training-Free Reward-Guided Image Editing via Trajectory Optimal Control

Zero4D: Training-Free 4D Video Generation From Single Video Using Off-the-Shelf Video Diffusion Models

Align Your Query: Representation Alignment for Multimodality Medical Object Detection

FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing

All Convolution, No Attention: Designing Diffusion with Convolutions

Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment

Contrastive CFG: Guiding Diffusion Sampling by Contrasting Positive and Negative Concepts

CellPainTR: Generalizable Representation Learning for Cross-Dataset Cell Painting Analysis

Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment

Regularization by Texts for Latent Diffusion Inverse Solvers

Boost-and-Skip: A Simple Guidance-Free Diffusion for Minority Generation

ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler

Simple ReFlow: Improved Techniques for Fast Flow Models

TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation

Solving Video Inverse Problems Using Image Diffusion Models

InvFusion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems

Guided Diffusion Sampling on Function Spaces with Applications to PDEs

Generalized Consistency Trajectory Models for Image Manipulation

Aligning Text to Image in Diffusion Models is Easier Than You Think

CellPainTR: Contrastive Batch Corrected Transformer for Large Scale Cell Painting

LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Models

Implicit Bridge Consistency Distillation for One-Step Unpaired Image Translation

LDMol: Text-to-Molecule Diffusion Model with Structurally Informative Latent Space

CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models

MinorityPrompt: Text to Minority Image Generation via Prompt Optimization

DreamMakeup: Face Makeup Customization using Latent Diffusion Models

ACDC: Autoregressive Coherent Multimodal Generation using Diffusion Correction

VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide

MindFormer: Semantic Alignment of Multi-Subject fMRI for Brain Decoding

Amortized Posterior Sampling with Diffusion Prior Distillation