Cover Image

Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Dohyun, Lyu, Seungwoo, Kim, Seung Wook, Seo, Paul Hongsuck
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Image Diffusion Models Exhibit Emergent Temporal Propagation in Videos
by: Kim, Youngseo, et al.
Published: (2025)

Robust Image Self-Recovery against Tampering using Watermark Generation with Pixel Shuffling
by: Kim, Minyoung, et al.
Published: (2025)

Bridging Audio and Vision: Zero-Shot Audiovisual Segmentation by Connecting Pretrained Models
by: Lee, Seung-jae, et al.
Published: (2025)

Learning Correlation Structures for Vision Transformers
by: Kim, Manjin, et al.
Published: (2024)

Multi-Granularity Video Object Segmentation
by: Lim, Sangbeom, et al.
Published: (2024)

COIN: Confidence Score-Guided Distillation for Annotation-Free Cell Segmentation
by: Jo, Sanghyun, et al.
Published: (2025)

Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers
by: Kim, Chaehyun, et al.
Published: (2025)

Breaking the Visual Shortcuts in Multimodal Knowledge-Based Visual Question Answering
by: Lee, Dosung, et al.
Published: (2025)

Spectral-Adaptive Modulation Networks for Visual Perception
by: Yun, Guhnoo, et al.
Published: (2025)

Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels
by: Shin, Heeseong, et al.
Published: (2024)

CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation
by: Cho, Seokju, et al.
Published: (2023)

Pseudo-RIS: Distinctive Pseudo-supervision Generation for Referring Image Segmentation
by: Yu, Seonghoon, et al.
Published: (2024)

ScoreCL: Augmentation-Adaptive Contrastive Learning via Score-Matching Function
by: Kim, Jin-Young, et al.
Published: (2023)

PropFly: Learning to Propagate via On-the-Fly Supervision from Pre-trained Video Diffusion Models
by: Seo, Wonyong, et al.
Published: (2026)

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization
by: Peng, Liang, et al.
Published: (2025)

Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization
by: Liu, Xinxin, et al.
Published: (2026)

Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals
by: Stojanov, Stefan, et al.
Published: (2025)

Rethinking Direct Preference Optimization in Diffusion Models
by: Kang, Junyong, et al.
Published: (2025)

Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models
by: Fu, Minghao, et al.
Published: (2025)

Captioning for Text-Video Retrieval via Dual-Group Direct Preference Optimization
by: Lee, Ji Soo, et al.
Published: (2025)

DialNav: Multi-turn Dialog Navigation with a Remote Guide
by: Han, Leekyeung, et al.
Published: (2025)

As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion Priors
by: Yoo, Seungwoo, et al.
Published: (2023)

Discriminator-Free Direct Preference Optimization for Video Diffusion
by: Cheng, Haoran, et al.
Published: (2025)

EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models
by: Namekata, Koichi, et al.
Published: (2024)

Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents
by: Choi, Wonje, et al.
Published: (2024)

Revisiting Weakly-Supervised Video Scene Graph Generation via Pair Affinity Learning
by: Kang, Minseok, et al.
Published: (2026)

VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning
by: Lee, Ji Soo, et al.
Published: (2025)

Benchmarking Direct Preference Optimization for Medical Large Vision-Language Models
by: Kim, Dain, et al.
Published: (2026)

ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization
by: Shen, Wenhao, et al.
Published: (2025)

DeDPO: Debiased Direct Preference Optimization for Diffusion Models
by: Pham, Khiem, et al.
Published: (2026)

ProtoFair: Fair Self-Supervised Contrastive Learning via Pseudo-Counterfactual Pairs
by: Halawa, Marah, et al.
Published: (2026)

WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space
by: Schwarz, Katja, et al.
Published: (2023)

Consistency-Preserving Concept Erasure via Unsafe-Safe Pairing and Directional Fisher-weighted Adaptation
by: Kim, Yongwoo, et al.
Published: (2026)

V.I.P. : Iterative Online Preference Distillation for Efficient Video Diffusion Models
by: Kim, Jisoo, et al.
Published: (2025)

Proxy-Free Gaussian Splats Deformation with Splat-Based Surface Estimation
by: Kim, Jaeyeong, et al.
Published: (2025)

Learning from Convolution-based Unlearnable Datasets
by: Kim, Dohyun, et al.
Published: (2024)

Enhancing Contrastive Learning with Efficient Combinatorial Positive Pairing
by: Kim, Jaeill, et al.
Published: (2024)

Boost Your Human Image Generation Model via Direct Preference Optimization
by: Na, Sanghyeon, et al.
Published: (2024)

Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models
by: Ling, Huan, et al.
Published: (2023)

OSPO: Object-Centric Self-Improving Preference Optimization for Text-to-Image Generation
by: Oh, Yoonjin, et al.
Published: (2025)