Copertina

Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Croitoru, Florinel-Alin, Hondru, Vlad, Ionescu, Radu Tudor, Sebe, Nicu, Shah, Mubarak
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Curriculum Direct Preference Optimization for Diffusion and Consistency Models
di: Croitoru, Florinel-Alin, et al.
Pubblicazione: (2024)

Masked Image Modeling: A Survey
di: Hondru, Vlad, et al.
Pubblicazione: (2024)

Reverse Stable Diffusion: What prompt was used to generate this image?
di: Croitoru, Florinel-Alin, et al.
Pubblicazione: (2023)

Diffusion Models in Vision: A Survey
di: Croitoru, Florinel-Alin, et al.
Pubblicazione: (2022)

PRNU-Bench: A Novel Benchmark and Model for PRNU-Based Camera Identification
di: Croitoru, Florinel Alin, et al.
Pubblicazione: (2025)

Learning Rate Curriculum
di: Croitoru, Florinel-Alin, et al.
Pubblicazione: (2022)

MAVOS-DD: Multilingual Audio-Video Open-Set Deepfake Detection Benchmark
di: Croitoru, Florinel-Alin, et al.
Pubblicazione: (2025)

CBM: Curriculum by Masking
di: Jarca, Andrei, et al.
Pubblicazione: (2024)

DLCR: A Generative Data Expansion Framework via Diffusion for Clothes-Changing Person Re-ID
di: Siddiqui, Nyle, et al.
Pubblicazione: (2024)

Towards Few-Call Model Stealing via Active Self-Paced Knowledge Distillation and Diffusion-Based Image Generation
di: Hondru, Vlad, et al.
Pubblicazione: (2023)

MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectors
di: Bercean, Bogdan Alexandru, et al.
Pubblicazione: (2026)

Task-Informed Anti-Curriculum by Masking Improves Downstream Performance on Text
di: Jarca, Andrei, et al.
Pubblicazione: (2025)

Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation
di: Croitoru, Florinel-Alin, et al.
Pubblicazione: (2022)

Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors
di: Ristea, Nicolae-Catalin, et al.
Pubblicazione: (2023)

Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook
di: Croitoru, Florinel-Alin, et al.
Pubblicazione: (2024)

ExDDV: A New Dataset for Explainable Deepfake Detection in Video
di: Hondru, Vlad, et al.
Pubblicazione: (2025)

Curriculum Multi-Task Self-Supervision Improves Lightweight Architectures for Onboard Satellite Hyperspectral Image Segmentation
di: Carlesso, Hugo, et al.
Pubblicazione: (2025)

Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study
di: Crivoi, Carla, et al.
Pubblicazione: (2025)

Multi-Level Feature Distillation of Joint Teachers Trained on Distinct Image Datasets
di: Iordache, Adrian, et al.
Pubblicazione: (2024)

AVC-DPO: Aligned Video Captioning via Direct Preference Optimization
di: Tang, Jiyang, et al.
Pubblicazione: (2025)

Asymmetric GANs for Image-to-Image Translation
di: Tang, Hao, et al.
Pubblicazione: (2019)

DreamBoothDPO: Improving Personalized Generation using Direct Preference Optimization
di: Ayupov, Shamil, et al.
Pubblicazione: (2025)

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

CL-MAE: Curriculum-Learned Masked Autoencoders
di: Madan, Neelu, et al.
Pubblicazione: (2023)

GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models
di: D'Incà, Moreno, et al.
Pubblicazione: (2024)

Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models
di: Li, Jinlong, et al.
Pubblicazione: (2026)

SEE-DPO: Self Entropy Enhanced Direct Preference Optimization
di: Shekhar, Shivanshu, et al.
Pubblicazione: (2024)

Enhanced Multi-Scale Cross-Attention for Person Image Generation
di: Tang, Hao, et al.
Pubblicazione: (2025)

PQPP: A Joint Benchmark for Text-to-Image Prompt and Query Performance Prediction
di: Poesina, Eduard, et al.
Pubblicazione: (2024)

VQPP: Video Query Performance Prediction Benchmark
di: Lutu, Adrian Catalin, et al.
Pubblicazione: (2026)

MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models
di: Liu, Ziyu, et al.
Pubblicazione: (2024)

SegMate: Asymmetric Attention-Based Lightweight Architecture for Efficient Multi-Organ Segmentation
di: Bunea, Andrei-Alexandru, et al.
Pubblicazione: (2026)

HuViDPO:Enhancing Video Generation through Direct Preference Optimization for Human-Centric Alignment
di: Jiang, Lifan, et al.
Pubblicazione: (2025)

Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation
di: Du, Jie, et al.
Pubblicazione: (2025)

FocusDPO: Dynamic Preference Optimization for Multi-Subject Personalized Image Generation via Adaptive Focus
di: Jin, Qiaoqiao, et al.
Pubblicazione: (2025)

Multi-focal Conditioned Latent Diffusion for Person Image Synthesis
di: Liu, Jiaqi, et al.
Pubblicazione: (2025)

Vision+X: A Survey on Multimodal Learning in the Light of Data
di: Zhu, Ye, et al.
Pubblicazione: (2022)

ESPLoRA: Enhanced Spatial Precision with Low-Rank Adaption in Text-to-Image Diffusion Models for High-Definition Synthesis
di: Rigo, Andrea, et al.
Pubblicazione: (2025)

CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP
di: Xing, Songlong, et al.
Pubblicazione: (2025)

GeMix: Conditional GAN-Based Mixup for Improved Medical Image Augmentation
di: Carlesso, Hugo, et al.
Pubblicazione: (2025)