Cover Image

Test-time Alignment of Diffusion Models without Reward Over-optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Sunwoo, Kim, Minkyu, Park, Dongmin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Statistics Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

VLM-SubtleBench: How Far Are VLMs from Human-Level Subtle Comparative Reasoning?
by: Kim, Minkyu, et al.
Published: (2026)

Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance
by: Park, Dongmin, et al.
Published: (2024)

Text-Aware Image Restoration with Diffusion Models
by: Min, Jaewon, et al.
Published: (2025)

Gradient-Free Noise Optimization for Reward Alignment in Generative Models
by: Kim, Jeongsol, et al.
Published: (2026)

Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation
by: Kim, Taehoon, et al.
Published: (2025)

GARDO: Reinforcing Diffusion Models without Reward Hacking
by: He, Haoran, et al.
Published: (2025)

See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis
by: Park, Jaehyun, et al.
Published: (2026)

Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
by: Lee, Jeongjae, et al.
Published: (2026)

CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation
by: Jin, Seonghyun, et al.
Published: (2026)

VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide
by: Lee, Dohun, et al.
Published: (2024)

Similarity-based Outlier Detection for Noisy Object Re-Identification Using Beta Mixtures
by: Ahmad, Waqar, et al.
Published: (2025)

Indeterminate Probability Theory
by: Yang, Tao, et al.
Published: (2023)

Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model
by: Yang, Kai, et al.
Published: (2023)

Mean-field Chaos Diffusion Models
by: Park, Sungwoo, et al.
Published: (2024)

Text Change Detection in Multilingual Documents Using Image Comparison
by: Park, Doyoung, et al.
Published: (2024)

Learning Relative Representations for Fine-Grained Multimodal Alignment with Limited Data
by: Kim, Shiwon, et al.
Published: (2026)

Video Diffusion Alignment via Reward Gradients
by: Prabhudesai, Mihir, et al.
Published: (2024)

Geometric 4D Stitching for Grounded 4D Generation
by: Park, Sunwoo, et al.
Published: (2026)

Diffusion-Based Offline RL for Improved Decision-Making in Augmented ARC Task
by: Kim, Yunho, et al.
Published: (2024)

GrndCtrl: Grounding World Models via Self-Supervised Reward Alignment
by: He, Haoyang, et al.
Published: (2025)

Spectral Motion Alignment for Video Motion Transfer using Diffusion Models
by: Park, Geon Yeong, et al.
Published: (2024)

Federated Learning with Feedback Alignment
by: Baek, Incheol, et al.
Published: (2025)

CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models
by: Chung, Hyungjin, et al.
Published: (2024)

Stitched Value Model for Diffusion Alignment
by: Go, Hyojun, et al.
Published: (2026)

DreamSampler: Unifying Diffusion Sampling and Score Distillation for Image Manipulation
by: Kim, Jeongsol, et al.
Published: (2024)

Diffusion Models without Classifier-free Guidance
by: Tang, Zhicong, et al.
Published: (2025)

Step-level Denoising-time Diffusion Alignment with Multiple Objectives
by: Zhang, Qi, et al.
Published: (2026)

Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models
by: Lee, Jaa-Yeon, et al.
Published: (2026)

DiffBlender: Composable and Versatile Multimodal Text-to-Image Diffusion Models
by: Kim, Sungnyun, et al.
Published: (2023)

Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance
by: Ahn, Donghoon, et al.
Published: (2024)

Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment
by: Kim, Bryan Sangwoo, et al.
Published: (2025)

Regularization by Texts for Latent Diffusion Inverse Solvers
by: Kim, Jeongsol, et al.
Published: (2023)

Free$^2$Guide: Training-Free Text-to-Video Alignment using Image LVLM
by: Kim, Jaemin, et al.
Published: (2024)

DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection
by: Song, Jaewoo, et al.
Published: (2025)

AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment
by: Kao, Kuei-Chun, et al.
Published: (2026)

Identifiable Token Correspondence for World Models
by: Kim, Youngin, et al.
Published: (2026)

Effective Test-Time Scaling of Discrete Diffusion through Iterative Refinement
by: Lee, Sanghyun, et al.
Published: (2025)

Improved Sample Complexity Bounds for Diffusion Model Training
by: Gupta, Shivam, et al.
Published: (2023)

Psi-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
by: Yoon, Taehoon, et al.
Published: (2025)

Hierarchical Variational Policies for Reward-Guided Diffusion
by: Pandey, Kushagra, et al.
Published: (2026)