Imagen de Portada

Understanding Flatness in Generative Models: Its Role and Benefits

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lee, Taehwan, Seo, Kyeongkook, Yoo, Jaejun, Yoon, Sung Whan
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

What Linear Probes Miss: Multi-View Probing for Weight-Space Learning
por: Heo, Eunwoo, et al.
Publicado: (2026)

PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models
por: Seo, Kyeongkook, et al.
Publicado: (2025)

Benchmarking Federated Learning for Semantic Datasets: Federated Scene Graph Generation
por: Ha, SeungBum, et al.
Publicado: (2024)

TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models
por: Kim, Pum Jun, et al.
Publicado: (2023)

Diversify and Conquer: Open-set Disagreement for Robust Semi-supervised Learning with Outliers
por: Kong, Heejo, et al.
Publicado: (2025)

A Flat Minima Perspective on Understanding Augmentations and Model Robustness
por: Yoo, Weebum, et al.
Publicado: (2025)

Sequential Flow Straightening for Generative Modeling
por: Yoon, Jongmin, et al.
Publicado: (2024)

Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing
por: Kim, Jaihoon, et al.
Publicado: (2025)

Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video
por: Choi, Chanhyuk, et al.
Publicado: (2026)

BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation
por: Lee, Daeun, et al.
Publicado: (2024)

Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement
por: Kim, Hyeonjin, et al.
Publicado: (2024)

PosterLlama: Bridging Design Ability of Langauge Model to Contents-Aware Layout Generation
por: Seol, Jaejung, et al.
Publicado: (2024)

Data Augmentation For Small Object using Fast AutoAugment
por: Yoon, DaeEun, et al.
Publicado: (2025)

EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens
por: Hwang, Sunil, et al.
Publicado: (2022)

High-Fidelity Text-to-Image Generation from Pre-Trained Vision-Language Models via Distribution-Conditioned Diffusion Decoding
por: Hong, Ji Woo, et al.
Publicado: (2026)

Do Pre-trained Models Benefit Equally in Continual Learning?
por: Lee, Kuan-Ying, et al.
Publicado: (2022)

Continual Learning: Forget-free Winning Subnetworks for Video Representations
por: Kang, Haeyong, et al.
Publicado: (2023)

STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment
por: Lee, Jaewoo, et al.
Publicado: (2023)

Why Fine-grained Labels in Pretraining Benefit Generalization?
por: Hong, Guan Zhe, et al.
Publicado: (2024)

CW-BASS: Confidence-Weighted Boundary-Aware Learning for Semi-Supervised Semantic Segmentation
por: Tarubinga, Ebenezer, et al.
Publicado: (2025)

Progressive Fourier Neural Representation for Sequential Video Compilation
por: Kang, Haeyong, et al.
Publicado: (2023)

Concept-skill Transferability-based Data Selection for Large Vision-Language Models
por: Lee, Jaewoo, et al.
Publicado: (2024)

Conditional Unbalanced Optimal Transport Maps: An Outlier-Robust Framework for Conditional Generative Modeling
por: Yoon, Jiwoo, et al.
Publicado: (2026)

DQE-CIR: Distinctive Query Embeddings through Learnable Attribute Weights and Target Relative Negative Sampling in Composed Image Retrieval
por: Park, Geon, et al.
Publicado: (2026)

Grid Diffusion Models for Text-to-Video Generation
por: Lee, Taegyeong, et al.
Publicado: (2024)

STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models
por: Kim, Pum Jun, et al.
Publicado: (2024)

Variational Positive-incentive Noise: How Noise Benefits Models
por: Zhang, Hongyuan, et al.
Publicado: (2023)

ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation
por: Min, Yunhong, et al.
Publicado: (2025)

In Search of a Data Transformation That Accelerates Neural Field Training
por: Seo, Junwon, et al.
Publicado: (2023)

MCAQ-YOLO: Morphological Complexity-Aware Quantization for Efficient Object Detection with Curriculum Learning
por: Seo, Yoonjae, et al.
Publicado: (2025)

By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting
por: Yoon, Hyungjun, et al.
Publicado: (2024)

Improving Diffusion-Based Generative Models via Approximated Optimal Transport
por: Kim, Daegyu, et al.
Publicado: (2024)

Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models
por: Zhang, Gengwei, et al.
Publicado: (2026)

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

Delta Rectified Flow Sampling for Text-to-Image Editing
por: Beaudouin, Gaspard, et al.
Publicado: (2025)

MultiDreamer3D: Multi-concept 3D Customization with Concept-Aware Diffusion Guidance
por: Song, Wooseok, et al.
Publicado: (2025)

FARCLUSS: Fuzzy Adaptive Rebalancing and Contrastive Uncertainty Learning for Semi-Supervised Semantic Segmentation
por: Tarubinga, Ebenezer, et al.
Publicado: (2025)

Flatness Improves Backbone Generalisation in Few-shot Classification
por: Li, Rui, et al.
Publicado: (2024)

Make Continual Learning Stronger via C-Flat
por: Bian, Ang, et al.
Publicado: (2024)

MultiFloodSynth: Multi-Annotated Flood Synthetic Dataset Generation
por: Kang, YoonJe, et al.
Publicado: (2025)