Image de couverture de livre

Self-Correcting Self-Consuming Loops for Generative Model Training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gillman, Nate, Freeman, Michael, Aggarwal, Daksh, Hsu, Chia-Hong, Luo, Calvin, Tian, Yonglong, Sun, Chen
Format:	Preprint
Publié:	2024
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

Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals
par: Gillman, Nate, et autres
Publié: (2025)

Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals
par: Gillman, Nate, et autres
Publié: (2026)

Fourier Head: Helping Large Language Models Learn Complex Probability Distributions
par: Gillman, Nate, et autres
Publié: (2024)

Self-Paced and Self-Corrective Masked Prediction for Movie Trailer Generation
par: Zhu, Sidan, et autres
Publié: (2025)

Beyond and Free from Diffusion: Invertible Guided Consistency Training
par: Hsu, Chia-Hong, et autres
Publié: (2025)

MicroViT: A Vision Transformer with Low Complexity Self Attention for Edge Device
par: Setyawan, Novendra, et autres
Publié: (2025)

Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens
par: Fan, Lijie, et autres
Publié: (2024)

Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning
par: Hsu, Chia-Hong, et autres
Publié: (2026)

Representation Fréchet Loss for Visual Generation
par: Yang, Jiawei, et autres
Publié: (2026)

Autoregressive Image Generation without Vector Quantization
par: Li, Tianhong, et autres
Publié: (2024)

Bridging Synthetic and Real-World Domains: A Human-in-the-Loop Weakly-Supervised Framework for Industrial Toxic Emission Segmentation
par: Tao, Yida, et autres
Publié: (2025)

Self-Corrected Image Generation with Explainable Latent Rewards
par: Luo, Yinyi, et autres
Publié: (2026)

Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback
par: Liang, Guotao, et autres
Publié: (2026)

Learning Vision from Models Rivals Learning Vision from Data
par: Tian, Yonglong, et autres
Publié: (2023)

Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models
par: Chen, Chubin, et autres
Publié: (2025)

Keypoint Counting Classifiers: Turning Vision Transformers into Self-Explainable Models Without Training
par: Wickstrøm, Kristoffer, et autres
Publié: (2025)

Radiologist-in-the-Loop Self-Training for Generalizable CT Metal Artifact Reduction
par: Ma, Chenglong, et autres
Publié: (2025)

Personalized Representation from Personalized Generation
par: Sundaram, Shobhita, et autres
Publié: (2024)

Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation
par: Wang, Zhenyu, et autres
Publié: (2024)

Self-Guidance: Boosting Flow and Diffusion Generation on Their Own
par: Li, Tiancheng, et autres
Publié: (2024)

McSc: Motion-Corrective Preference Alignment for Video Generation with Self-Critic Hierarchical Reasoning
par: Yang, Qiushi, et autres
Publié: (2025)

CoSAM: Self-Correcting SAM for Domain Generalization in 2D Medical Image Segmentation
par: Fu, Yihang, et autres
Publié: (2024)

Marmot: Object-Level Self-Correction via Multi-Agent Reasoning
par: Sun, Jiayang, et autres
Publié: (2025)

Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation
par: Yue, Xiaoyu, et autres
Publié: (2025)

VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction
par: Zhang, Jiahao, et autres
Publié: (2024)

Rethinking Multiple Instance Learning: Developing an Instance-Level Classifier via Weakly-Supervised Self-Training
par: Ma, Yingfan, et autres
Publié: (2024)

Latent Denoising Makes Good Tokenizers
par: Yang, Jiawei, et autres
Publié: (2025)

Mitigating Low-Level Visual Hallucinations Requires Self-Awareness: Database, Model and Training Strategy
par: Sun, Yinan, et autres
Publié: (2025)

A Self-Correcting Vision-Language-Action Model for Fast and Slow System Manipulation
par: Li, Chenxuan, et autres
Publié: (2024)

Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training?
par: Sun, Lingchen, et autres
Publié: (2026)

LaneCorrect: Self-supervised Lane Detection
par: Nie, Ming, et autres
Publié: (2024)

HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation
par: Zhang, Conglang, et autres
Publié: (2026)

Correcting Class Imbalances with Self-Training for Improved Universal Lesion Detection and Tagging
par: Shieh, Alexander, et autres
Publié: (2025)

CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training
par: Chen, Yuxi, et autres
Publié: (2026)

CSAKD: Knowledge Distillation with Cross Self-Attention for Hyperspectral and Multispectral Image Fusion
par: Hsu, Chih-Chung, et autres
Publié: (2024)

UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision
par: Han, Ruiyan, et autres
Publié: (2026)

SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning
par: Zhang, Lin, et autres
Publié: (2025)

Self-Adversarial One Step Generation via Condition Shifting
par: Liu, Deyuan, et autres
Publié: (2026)

IJmond Industrial Smoke Segmentation Dataset
par: Hsu, Yen-Chia, et autres
Publié: (2026)

LoopExpose: An Unsupervised Framework for Arbitrary-Length Exposure Correction
par: Li, Ao, et autres
Publié: (2025)