Copertina

ReDiF: Reinforced Distillation for Few Step Diffusion

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tighkhorshid, Amirhossein, Dehghanian, Zahra, Aminian, Gholamali, Shi, Chengchun, Rabiee, Hamid R.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

UPL: Uncertainty-aware Pseudo-labeling for Imbalance Transductive Node Classification
di: Teimuri, Mohammad T., et al.
Pubblicazione: (2025)

CineLOG: A Training Free Approach for Cinematic Long Video Generation
di: Dehghanian, Zahra, et al.
Pubblicazione: (2025)

Few-Step Diffusion via Score identity Distillation
di: Zhou, Mingyuan, et al.
Pubblicazione: (2025)

SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation
di: Wu, Zhuguanyu, et al.
Pubblicazione: (2026)

Redefining Generalization in Visual Domains: A Two-Axis Framework for Fake Image Detection with FusionDetect
di: Amanzadi, Amirtaha, et al.
Pubblicazione: (2025)

Camera Trajectory Generation: A Comprehensive Survey of Methods, Metrics, and Future Directions
di: Dehghanian, Zahra, et al.
Pubblicazione: (2025)

Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning
di: Zhang, Ziyi, et al.
Pubblicazione: (2025)

Optimizing Few-Step Generation with Adaptive Matching Distillation
di: Bai, Lichen, et al.
Pubblicazione: (2026)

Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning
di: Behnamnia, Armin, et al.
Pubblicazione: (2025)

Aligning Few-Step Diffusion Models with Dense Reward Difference Learning
di: Zhang, Ziyi, et al.
Pubblicazione: (2024)

LensCraft: Your Professional Virtual Cinematographer
di: Dehghanian, Zahra, et al.
Pubblicazione: (2025)

FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity
di: Tang, Jian, et al.
Pubblicazione: (2026)

One-Step Diffusion Distillation via Deep Equilibrium Models
di: Geng, Zhengyang, et al.
Pubblicazione: (2023)

RealDrag: The First Dragging Benchmark with Real Target Image
di: Zafarani, Ahmad, et al.
Pubblicazione: (2025)

pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
di: Chen, Hansheng, et al.
Pubblicazione: (2025)

DiRe: Diversity-promoting Regularization for Dataset Condensation
di: Mohanty, Saumyaranjan, et al.
Pubblicazione: (2025)

Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Learnable Linear Extrapolation
di: Zhang, Jiawei, et al.
Pubblicazione: (2025)

CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation
di: Mei, Kangfu, et al.
Pubblicazione: (2023)

$R_\text{dm}$: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillation
di: Fan, Linqian, et al.
Pubblicazione: (2026)

Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation
di: Chadebec, Clément, et al.
Pubblicazione: (2024)

DistillKac: Few-Step Image Generation via Damped Wave Equations
di: Han, Weiqiao, et al.
Pubblicazione: (2025)

One-Step Diffusion Distillation through Score Implicit Matching
di: Luo, Weijian, et al.
Pubblicazione: (2024)

Di$\mathtt{[M]}$O: Distilling Masked Diffusion Models into One-step Generator
di: Zhu, Yuanzhi, et al.
Pubblicazione: (2025)

Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
di: Zhou, Mingyuan, et al.
Pubblicazione: (2024)

ReDistill: Residual Encoded Distillation for Peak Memory Reduction of CNNs
di: Chen, Fang, et al.
Pubblicazione: (2024)

TerDiT: Ternary Diffusion Models with Transformers
di: Lu, Xudong, 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)

On Distilling the Displacement Knowledge for Few-Shot Class-Incremental Learning
di: Fang, Pengfei, et al.
Pubblicazione: (2024)

Improving Diversity in Black-box Few-shot Knowledge Distillation
di: Vo, Tri-Nhan, et al.
Pubblicazione: (2026)

Fast-DiM: Towards Fast Diffusion Morphs
di: Blasingame, Zander W., et al.
Pubblicazione: (2023)

Highlight Every Step: Knowledge Distillation via Collaborative Teaching
di: Zhao, Haoran, et al.
Pubblicazione: (2019)

Diffusion Reinforcement Learning via Centered Reward Distillation
di: Zhu, Yuanzhi, et al.
Pubblicazione: (2026)

Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step
di: Zhou, Mingyuan, et al.
Pubblicazione: (2024)

Semi-supervised Batch Learning From Logged Data
di: Aminian, Gholamali, et al.
Pubblicazione: (2022)

Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation
di: Chen, Tianyu, et al.
Pubblicazione: (2025)

DiWA: Diffusion Policy Adaptation with World Models
di: Chandra, Akshay L, et al.
Pubblicazione: (2025)

One Step Diffusion via Shortcut Models
di: Frans, Kevin, et al.
Pubblicazione: (2024)

DiC: Rethinking Conv3x3 Designs in Diffusion Models
di: Tian, Yuchuan, et al.
Pubblicazione: (2024)

DiCTI: Diffusion-based Clothing Designer via Text-guided Input
di: Lampe, Ajda, et al.
Pubblicazione: (2024)

Qua$^2$SeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models
di: Mills, Keith G., et al.
Pubblicazione: (2024)