Image de couverture de livre

Gradient-Free Noise Optimization for Reward Alignment in Generative Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kim, Jeongsol, Kim, Hongeun, Wang, Jian, Ye, Jong Chul
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
par: Lee, Jeongjae, et autres
Publié: (2026)

Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment
par: Kim, Bryan Sangwoo, et autres
Publié: (2025)

Extreme Blind Image Restoration via Prompt-Conditioned Information Bottleneck
par: Kim, Hongeun, et autres
Publié: (2025)

Generalized Consistency Trajectory Models for Image Manipulation
par: Kim, Beomsu, et autres
Publié: (2024)

Latent Schrodinger Bridge: Prompting Latent Diffusion for Fast Unpaired Image-to-Image Translation
par: Kim, Jeongsol, et autres
Publié: (2024)

FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing
par: Kim, Jeongsol, et autres
Publié: (2025)

FlowDPS: Flow-Driven Posterior Sampling for Inverse Problems
par: Kim, Jeongsol, et autres
Publié: (2025)

DreamSampler: Unifying Diffusion Sampling and Score Distillation for Image Manipulation
par: Kim, Jeongsol, et autres
Publié: (2024)

CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models
par: Chung, Hyungjin, et autres
Publié: (2024)

Aligning Text to Image in Diffusion Models is Easier Than You Think
par: Lee, Jaa-Yeon, et autres
Publié: (2025)

Free$^2$Guide: Training-Free Text-to-Video Alignment using Image LVLM
par: Kim, Jaemin, et autres
Publié: (2024)

Regularization by Texts for Latent Diffusion Inverse Solvers
par: Kim, Jeongsol, et autres
Publié: (2023)

Diffusion Posterior Sampling for General Noisy Inverse Problems
par: Chung, Hyungjin, et autres
Publié: (2022)

Diverse Text-to-Image Generation via Contrastive Noise Optimization
par: Kim, Byungjun, et autres
Publié: (2025)

Boost-and-Skip: A Simple Guidance-Free Diffusion for Minority Generation
par: Um, Soobin, et autres
Publié: (2025)

PCPO: Proportionate Credit Policy Optimization for Aligning Image Generation Models
par: Lee, Jeongjae, et autres
Publié: (2025)

PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment
par: Lee, Suhyeon, et autres
Publié: (2025)

Minority-Focused Text-to-Image Generation via Prompt Optimization
par: Um, Soobin, et autres
Publié: (2024)

Align Your Query: Representation Alignment for Multimodality Medical Object Detection
par: Seo, Ara, et autres
Publié: (2025)

Align Your Tangent: Training Better Consistency Models via Manifold-Aligned Tangents
par: Kim, Beomsu, et autres
Publié: (2025)

Self-Guided Generation of Minority Samples Using Diffusion Models
par: Um, Soobin, et autres
Publié: (2024)

Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models
par: Lee, Jaa-Yeon, et autres
Publié: (2026)

MotionCFG: Boosting Motion Dynamics via Stochastic Concept Perturbation
par: Kim, Byungjun, et autres
Publié: (2026)

OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation
par: Kim, Kwanyoung, et autres
Publié: (2024)

CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation
par: Jin, Seonghyun, et autres
Publié: (2026)

Unpaired Image-to-Image Translation via Neural Schrödinger Bridge
par: Kim, Beomsu, et autres
Publié: (2023)

Training-Free Reward-Guided Image Editing via Trajectory Optimal Control
par: Chang, Jinho, et autres
Publié: (2025)

MindFormer: Semantic Alignment of Multi-Subject fMRI for Brain Decoding
par: Han, Inhwa, et autres
Publié: (2024)

Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolution
par: Kim, Bryan Sangwoo, et autres
Publié: (2026)

Optical-Flow Guided Prompt Optimization for Coherent Video Generation
par: Nam, Hyelin, et autres
Publié: (2024)

Solving Video Inverse Problems Using Image Diffusion Models
par: Kwon, Taesung, et autres
Publié: (2024)

VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide
par: Lee, Dohun, et autres
Publié: (2024)

Spectral Motion Alignment for Video Motion Transfer using Diffusion Models
par: Park, Geon Yeong, et autres
Publié: (2024)

Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models
par: Jeong, Hyeonho, et autres
Publié: (2023)

VISION-XL: High Definition Video Inverse Problem Solver using Latent Image Diffusion Models
par: Kwon, Taesung, et autres
Publié: (2024)

LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation
par: Lee, Suhyeon, et autres
Publié: (2023)

Hyperspherical Autoencoder for High-Fidelity Image Reconstruction and Generation
par: Chang, Hun, et autres
Publié: (2026)

Geometric 4D Stitching for Grounded 4D Generation
par: Park, Sunwoo, et autres
Publié: (2026)

FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction
par: Jin, Seonghyun, et autres
Publié: (2026)

FlowLPS: Langevin-Proximal Sampling for Flow-based Inverse Problem Solvers
par: Park, Jonghyun, et autres
Publié: (2025)