1.2k citations · 2.2k across the 48 of their papers we have counts for
44 papers · 1 filter
FeaTok: Feature-Loss Tokenization for Image Generation
Zhang Xiaofeng, Samuel Lavoie, Nicolas Beltran-Velez +6
Discrete image generators learn the distribution of tokens produced by an image tokenizer. These token representations should be easy for generators to model, not merely enable fai…
Inference-time Physics Alignment of Video Generative Models with Latent World Models
Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich +7
State-of-the-art video generative models produce promising visual content yet often violate basic physics principles, limiting their utility. While some attribute this deficiency t…
GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation
Ye Zhu, Kaleb S. Newman, Johannes F. Lutzeyer +3
Despite high semantic alignment, modern text-to-image (T2I) generative models still struggle to synthesize diverse images from a given prompt. In this work, we enhance the T2I dive…
Unified Text-Image Generation with Weakness-Targeted Post-Training
Jiahui Chen, Philippe Hansen-Estruch, Xiaochuang Han +7
Unified multimodal generation architectures that jointly produce text and images have recently emerged as a promising direction for text-to-image (T2I) synthesis. However, many exi…
Improving the Physics of Video Generation with VJEPA-2 Reward Signal
Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich +7
This is a short technical report describing the winning entry of the PhysicsIQ Challenge, presented at the Perception Test Workshop at ICCV 2025. State-of-the-art video generative…
The Intricate Dance of Prompt Complexity, Quality, Diversity, and Consistency in T2I Models
Zhang Xiaofeng, Aaron Courville, Michal Drozdzal +1
Text-to-image (T2I) models offer great potential for creating virtually limitless synthetic data, a valuable resource compared to fixed and finite real datasets. Previous works eva…
Controlling Multimodal LLMs via Reward-guided Decoding
Oscar Mañas, Pierluca D'Oro, Koustuv Sinha +3
As Multimodal Large Language Models (MLLMs) gain widespread applicability, it is becoming increasingly desirable to adapt them for diverse user needs. In this paper, we study the a…
Increasing the Utility of Synthetic Images through Chamfer Guidance
Nicola Dall'Asen, Xiaofeng Zhang, Reyhane Askari Hemmat +4
Conditional image generative models hold considerable promise to produce infinite amounts of synthetic training data. Yet, recent progress in generation quality has come at the exp…
Multimodal Language Models as Text-to-Image Model Evaluators
Jiahui Chen, Candace Ross, Reyhane Askari-Hemmat +5
The steady improvements of text-to-image (T2I) generative models lead to slow deprecation of automatic evaluation benchmarks that rely on static datasets, motivating researchers to…
Entropy Rectifying Guidance for Diffusion and Flow Models
Tariq Berrada Ifriqi, Adriana Romero-Soriano, Michal Drozdzal +2
Guidance techniques are commonly used in diffusion and flow models to improve image quality and input consistency for conditional generative tasks such as class-conditional and tex…
Object-centric Binding in Contrastive Language-Image Pretraining
Rim Assouel, Pietro Astolfi, Florian Bordes +2
Recent advances in vision language models (VLM) have been driven by contrastive models such as CLIP, which learn to associate visual information with their corresponding text descr…
EvalGIM: A Library for Evaluating Generative Image Models
Melissa Hall, Oscar Mañas, Reyhane Askari-Hemmat +14
As the use of text-to-image generative models increases, so does the adoption of automatic benchmarking methods used in their evaluation. However, while metrics and datasets abound…
Boosting Latent Diffusion with Perceptual Objectives
Tariq Berrada, Pietro Astolfi, Melissa Hall +6
Latent diffusion models (LDMs) power state-of-the-art high-resolution generative image models. LDMs learn the data distribution in the latent space of an autoencoder (AE) and produ…
On Improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
Tariq Berrada Ifriqi, Pietro Astolfi, Melissa Hall +8
Large-scale training of latent diffusion models (LDMs) has enabled unprecedented quality in image generation. However, the key components of the best performing LDM training recipe…
Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance
Reyhane Askari Hemmat, Melissa Hall, Alicia Sun +3
With the growing popularity of text-to-image generative models, there has been increasing focus on understanding their risks and biases. Recent work has found that state-of-the-art…
Consistency-diversity-realism Pareto fronts of conditional image generative models
Pietro Astolfi, Marlene Careil, Melissa Hall +5
Building world models that accurately and comprehensively represent the real world is the utmost aspiration for conditional image generative models as it would enable their use as…
Towards Geographic Inclusion in the Evaluation of Text-to-Image Models
Melissa Hall, Samuel J. Bell, Candace Ross +3
Rapid progress in text-to-image generative models coupled with their deployment for visual content creation has magnified the importance of thoroughly evaluating their performance…
Improving Text-to-Image Consistency via Automatic Prompt Optimization
Oscar Mañas, Pietro Astolfi, Melissa Hall +6
Impressive advances in text-to-image (T2I) generative models have yielded a plethora of high performing models which are able to generate aesthetically appealing, photorealistic im…
Feedback-guided Data Synthesis for Imbalanced Classification
Reyhane Askari Hemmat, Mohammad Pezeshki, Florian Bordes +2
Current status quo in machine learning is to use static datasets of real images for training, which often come from long-tailed distributions. With the recent advances in generativ…
DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity
Melissa Hall, Candace Ross, Adina Williams +3
The unprecedented photorealistic results achieved by recent text-to-image generative systems and their increasing use as plug-and-play content creation solutions make it crucial to…
Improved baselines for vision-language pre-training
Enrico Fini, Pietro Astolfi, Adriana Romero-Soriano +2
Contrastive learning has emerged as an efficient framework to learn multimodal representations. CLIP, a seminal work in this area, achieved impressive results by training on paired…
Controllable Image Generation via Collage Representations
Arantxa Casanova, Marlène Careil, Adriana Romero-Soriano +3
Recent advances in conditional generative image models have enabled impressive results. On the one hand, text-based conditional models have achieved remarkable generation quality,…
Instance-Conditioned GAN Data Augmentation for Representation Learning
Pietro Astolfi, Arantxa Casanova, Jakob Verbeek +3
Data augmentation has become a crucial component to train state-of-the-art visual representation models. However, handcrafting combinations of transformations that lead to improved…
ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations
Badr Youbi Idrissi, Diane Bouchacourt, Randall Balestriero +7
Deep learning vision systems are widely deployed across applications where reliability is critical. However, even today's best models can fail to recognize an object when its pose,…