Cover Image

Don't drop your samples! Coherence-aware training benefits Conditional diffusion

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dufour, Nicolas, Besnier, Victor, Kalogeiton, Vicky, Picard, David
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation
by: Dufour, Nicolas, et al.
Published: (2024)

MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency
by: Dufour, Nicolas, et al.
Published: (2025)

Analysis of Classifier-Free Guidance Weight Schedulers
by: Wang, Xi, et al.
Published: (2024)

Training-Free Synthetic Data Generation with Dual IP-Adapter Guidance
by: Boudier, Luc, et al.
Published: (2025)

PoM: Efficient Image and Video Generation with the Polynomial Mixer
by: Picard, David, et al.
Published: (2024)

E.T. the Exceptional Trajectories: Text-to-camera-trajectory generation with character awareness
by: Courant, Robin, et al.
Published: (2024)

T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning
by: Mordacq, Julie, et al.
Published: (2025)

ADAPT: Multimodal Learning for Detecting Physiological Changes under Missing Modalities
by: Mordacq, Julie, et al.
Published: (2024)

Don't Judge by the Look: Towards Motion Coherent Video Representation
by: Zhang, Yitian, et al.
Published: (2024)

Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddings
by: Zhu, Yuanzhi, et al.
Published: (2025)

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

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

One-step Diffusion Models with Bregman Density Ratio Matching
by: Zhu, Yuanzhi, et al.
Published: (2025)

Supervised Anomaly Detection for Complex Industrial Images
by: Baitieva, Aimira, et al.
Published: (2024)

Don't trust your eyes: on the (un)reliability of feature visualizations
by: Geirhos, Robert, et al.
Published: (2023)

Collaborating Foundation Models for Domain Generalized Semantic Segmentation
by: Benigmim, Yasser, et al.
Published: (2023)

Don't Reach for the Stars: Rethinking Topology for Resilient Federated Learning
by: Konstantin, Mirko, et al.
Published: (2025)

The Geometry of Noise: Why Diffusion Models Don't Need Noise Conditioning
by: Sahraee-Ardakan, Mojtaba, et al.
Published: (2026)

Surely Large Multimodal Models (Don't) Excel in Visual Species Recognition?
by: Liu, Tian, et al.
Published: (2025)

Don't Look Twice: Faster Video Transformers with Run-Length Tokenization
by: Choudhury, Rohan, et al.
Published: (2024)

How far can we go with ImageNet for Text-to-Image generation?
by: Degeorge, L., et al.
Published: (2025)

How to train your ViT for OOD Detection
by: Mueller, Maximilian, et al.
Published: (2024)

Show, Don't Tell: Detecting Novel Objects by Watching Human Videos
by: Akl, James, et al.
Published: (2026)

Unified Latents (UL): How to train your latents
by: Heek, Jonathan, et al.
Published: (2026)

Pulp Motion: Framing-aware multimodal camera and human motion generation
by: Courant, Robin, et al.
Published: (2025)

Don't Play Favorites: Minority Guidance for Diffusion Models
by: Um, Soobin, et al.
Published: (2023)

You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning
by: Moutakanni, Théo, et al.
Published: (2024)

Adapt, But Don't Forget: Fine-Tuning and Contrastive Routing for Lane Detection under Distribution Shift
by: Khan, Mohammed Abdul Hafeez, et al.
Published: (2025)

Fast constrained sampling in pre-trained diffusion models
by: Graikos, Alexandros, et al.
Published: (2024)

Scale, Don't Fine-tune: Guiding Multimodal LLMs for Efficient Visual Place Recognition at Test-Time
by: Cheng, Jintao, et al.
Published: (2025)

Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs
by: Janjua, Muhammad Kamran, et al.
Published: (2026)

Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions
by: Parmar, Mihir, et al.
Published: (2022)

Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings
by: Dhimoïla, Grégoire, et al.
Published: (2026)

Test-Time Conditioning with Representation-Aligned Visual Features
by: Sereyjol-Garros, Nicolas, et al.
Published: (2026)

Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images
by: Yu, Zhuoran, et al.
Published: (2023)

Don't Get Me Wrong: How to Apply Deep Visual Interpretations to Time Series
by: Loeffler, Christoffer, et al.
Published: (2022)

Studying Image Diffusion Features for Zero-Shot Video Object Segmentation
by: Delatolas, Thanos, et al.
Published: (2025)

Augmentation-aware Self-supervised Learning with Conditioned Projector
by: Przewięźlikowski, Marcin, et al.
Published: (2023)

Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins
by: Ray, Rahul D
Published: (2026)

From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling
by: Renaud, Marien, et al.
Published: (2025)