Mehdi Cherti

Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang et al. · allen-ai, stanford

Multimodal datasets are a critical component in recent breakthroughs such as Stable Diffusion and GPT-4, yet their design does not receive the same research attention as model architectures or training algorithms. To address this shortcoming in the ML ecosystem, we introduce DataComp, a testbed for dataset experiments centered around a new candidate pool of 12.8 billion image-text pairs from Common Crawl. Participants in our benchmark design new filtering techniques or curate new data sources and then evaluate their new dataset by running our standardized CLIP training code and testing the resulting model on 38 downstream test sets. Our benchmark consists of multiple compute scales spanning four orders of magnitude, which enables the study of scaling trends and makes the benchmark accessible to researchers with varying resources. Our baseline experiments show that the DataComp workflow leads to better training sets. In particular, our best baseline, DataComp-1B, enables training a CLIP ViT-L/14 from scratch to 79.2% zero-shot accuracy on ImageNet, outperforming OpenAI's CLIP ViT-L/14 by 3.7 percentage points while using the same training procedure and compute. We release DataComp and all accompanying code at www.datacomp.ai.

Karsten Roth, Vishaal Udandarao, Sebastian Dziadzio et al. · cambridge

Multimodal foundation models serve numerous applications at the intersection of vision and language. Still, despite being pretrained on extensive data, they become outdated over time. To keep models updated, research into continual pretraining mainly explores scenarios with either (1) infrequent, indiscriminate updates on large-scale new data, or (2) frequent, sample-level updates. However, practical model deployment often operates in the gap between these two limit cases, as real-world applications often demand adaptation to specific subdomains, tasks or concepts -- spread over the entire, varying life cycle of a model. In this work, we complement current perspectives on continual pretraining through a research test bed as well as provide comprehensive guidance for effective continual model updates in such scenarios. We first introduce FoMo-in-Flux, a continual multimodal pretraining benchmark with realistic compute constraints and practical deployment requirements, constructed over 63 datasets with diverse visual and semantic coverage. Using FoMo-in-Flux, we explore the complex landscape of practical continual pretraining through multiple perspectives: (1) A data-centric investigation of data mixtures and stream orderings that emulate real-world deployment situations, (2) a method-centric investigation ranging from simple fine-tuning and traditional continual learning strategies to parameter-efficient updates and model merging, (3) meta learning rate schedules and mechanistic design choices, and (4) the influence of model and compute scaling. Together, our insights provide a practitioner's guide to continual multimodal pretraining for real-world deployment. Our benchmark and code is here: https://github.com/ExplainableML/fomo_in_flux.

Mehdi Cherti, Romain Beaumont, Ross Wightman et al.

Scaling up neural networks has led to remarkable performance across a wide range of tasks. Moreover, performance often follows reliable scaling laws as a function of training set size, model size, and compute, which offers valuable guidance as large-scale experiments are becoming increasingly expensive. However, previous work on scaling laws has primarily used private data \& models or focused on uni-modal language or vision learning. To address these limitations, we investigate scaling laws for contrastive language-image pre-training (CLIP) with the public LAION dataset and the open-source OpenCLIP repository. Our large-scale experiments involve models trained on up to two billion image-text pairs and identify power law scaling for multiple downstream tasks including zero-shot classification, retrieval, linear probing, and end-to-end fine-tuning. We find that the training distribution plays a key role in scaling laws as the OpenAI and OpenCLIP models exhibit different scaling behavior despite identical model architectures and similar training recipes. We open-source our evaluation workflow and all models, including the largest public CLIP models, to ensure reproducibility and make scaling laws research more accessible. Source code and instructions to reproduce this study will be available at https://github.com/LAION-AI/scaling-laws-openclip

Christoph Schuhmann, Romain Beaumont, Richard Vencu et al.

Groundbreaking language-vision architectures like CLIP and DALL-E proved the utility of training on large amounts of noisy image-text data, without relying on expensive accurate labels used in standard vision unimodal supervised learning. The resulting models showed capabilities of strong text-guided image generation and transfer to downstream tasks, while performing remarkably at zero-shot classification with noteworthy out-of-distribution robustness. Since then, large-scale language-vision models like ALIGN, BASIC, GLIDE, Flamingo and Imagen made further improvements. Studying the training and capabilities of such models requires datasets containing billions of image-text pairs. Until now, no datasets of this size have been made openly available for the broader research community. To address this problem and democratize research on large-scale multi-modal models, we present LAION-5B - a dataset consisting of 5.85 billion CLIP-filtered image-text pairs, of which 2.32B contain English language. We show successful replication and fine-tuning of foundational models like CLIP, GLIDE and Stable Diffusion using the dataset, and discuss further experiments enabled with an openly available dataset of this scale. Additionally we provide several nearest neighbor indices, an improved web-interface for dataset exploration and subset generation, and detection scores for watermark, NSFW, and toxic content detection. Announcement page https://laion.ai/laion-5b-a-new-era-of-open-large-scale-multi-modal-datasets/

Mehdi Cherti, Alexander Czernik, Stefan Kesselheim et al.

Solar activity is one of the main drivers of variability in our solar system and the key source of space weather phenomena that affect Earth and near Earth space. The extensive record of high resolution extreme ultraviolet (EUV) observations from the Solar Dynamics Observatory (SDO) offers an unprecedented, very large dataset of solar images. In this work, we make use of this comprehensive dataset to investigate capabilities of current state-of-the-art generative models to accurately capture the data distribution behind the observed solar activity states. Starting from StyleGAN-based methods, we uncover severe deficits of this model family in handling fine-scale details of solar images when training on high resolution samples, contrary to training on natural face images. When switching to the diffusion based generative model family, we observe strong improvements of fine-scale detail generation. For the GAN family, we are able to achieve similar improvements in fine-scale generation when turning to ProjectedGANs, which uses multi-scale discriminators with a pre-trained frozen feature extractor. We conduct ablation studies to clarify mechanisms responsible for proper fine-scale handling. Using distributed training on supercomputers, we are able to train generative models for up to 1024x1024 resolution that produce high quality samples indistinguishable to human experts, as suggested by the evaluation we conduct. We make all code, models and workflows used in this study publicly available at \url{https://github.com/SLAMPAI/generative-models-for-highres-solar-images}.

Jan Lewen, Max Pargmann, Mehdi Cherti et al.

Concentrating Solar Power (CSP) plants play a crucial role in the global transition towards sustainable energy. A key factor in ensuring the safe and efficient operation of CSP plants is the distribution of concentrated flux density on the receiver. However, the non-ideal flux density generated by individual heliostats can undermine the safety and efficiency of the power plant. The flux density from each heliostat is influenced by its precise surface profile, which includes factors such as canting and mirror errors. Accurately measuring these surface profiles for a large number of heliostats in operation is a formidable challenge. Consequently, control systems often rely on the assumption of ideal surface conditions, which compromises both safety and operational efficiency. In this study, we introduce inverse Deep Learning Ray Tracing (iDLR), an innovative method designed to predict heliostat surfaces based solely on target images obtained during heliostat calibration. Our simulation-based investigation demonstrates that sufficient information regarding the heliostat surface is retained in the flux density distribution of a single heliostat, enabling deep learning models to accurately predict the underlying surface with deflectometry-like precision for the majority of heliostats. Additionally, we assess the limitations of this method, particularly in relation to surface accuracy and resultant flux density predictions. Furthermore, we are presenting a new comprehensive heliostat model using Non-Uniform Rational B-Spline (NURBS) that has the potential to become the new State of the Art for heliostat surface parameterization. Our findings reveal that iDLR has significant potential to enhance CSP plant operations, potentially increasing the overall efficiency and energy output of the power plants.

Marianna Nezhurina, Tomer Porian, Giovanni Pucceti et al.

In studies of transferable learning, scaling laws are obtained for various important foundation models to predict their properties and performance at larger scales. We show here how scaling law derivation can also be used for model and dataset comparison, allowing to decide which procedure is to be preferred for pre-training. For the first time, full scaling laws based on dense measurements across a wide span of model and samples seen scales are derived for two important language-vision learning procedures, CLIP and MaMMUT, that use either contrastive only or contrastive and captioning text generative loss. Ensuring sufficient prediction accuracy for held out points, we use derived scaling laws to compare both models, obtaining evidence for MaMMUT's stronger improvement with scale and better sample efficiency than standard CLIP. To strengthen validity of the comparison, we show scaling laws for various downstream tasks, classification, retrieval, and segmentation, and for different open datasets, DataComp, DFN and Re-LAION, observing consistently the same trends. We show that comparison can also be performed when deriving scaling laws with a constant learning rate schedule, reducing compute cost. Accurate derivation of scaling laws provides thus means to perform model and dataset comparison across scale spans, avoiding misleading conclusions based on measurements from single reference scales only, paving the road for systematic comparison and improvement of open foundation models and datasets for their creation. We release all the pre-trained models with their intermediate checkpoints, including openMaMMUT-L/14, which achieves $80.3\%$ zero-shot ImageNet-1k accuracy, trained on 12.8B samples from DataComp-1.4B. Code for reproducing experiments in the paper and raw experiments data can be found at https://github.com/LAION-AI/scaling-laws-for-comparison.

Adhiraj Ghosh, Vishaal Udandarao, Thao Nguyen et al.

What data should a vision-language model be trained on? To answer this question, many data curation efforts center on the quality of a dataset. However, most of these existing methods are (i) offline, i.e. they produce a static dataset from a set of predetermined filtering criteria, and (ii) concept-agnostic, i.e. they use model-based filters which induce additional data biases. In this work, we go beyond such offline, concept-agnostic methods and advocate for more flexible, task-adaptive online concept-based curation. Our first contribution is DataConcept, a collection of 128M web-crawled image-text pairs annotated with fine-grained details about their concept composition. Building on DataConcept, we introduce Concept-Aware Batch Sampling (CABS), a simple yet effective batch sampling framework that flexibly constructs batches on-the-fly based on specific target distributions. We propose two variants: (i) Diversity Maximization (CABS-DM) to curate batches with a broad coverage of available concepts, and (ii) Frequency Maximization (CABS-FM) to curate batches with high object multiplicity. Through extensive evaluations across 28 benchmarks, we demonstrate that our CABS method significantly benefits CLIP/SigLIP model classes and yields highly performant models. Overall, CABS represents a strong open-source alternative to proprietary online data curation algorithms, enabling practitioners to define custom concept distributions that optimize for specific downstream tasks.

Stefania L. Moroianu, Christian Bluethgen, Pierre Chambon et al. · stanford

Achieving robust performance and fairness across diverse patient populations remains a challenge in developing clinically deployable deep learning models for diagnostic imaging. Synthetic data generation has emerged as a promising strategy to address limitations in dataset scale and diversity. We introduce RoentGen-v2, a text-to-image diffusion model for chest radiographs that enables fine-grained control over both radiographic findings and patient demographic attributes, including sex, age, and race/ethnicity. RoentGen-v2 is the first model to generate clinically plausible images with demographic conditioning, facilitating the creation of a large, demographically balanced synthetic dataset comprising over 565,000 images. We use this large synthetic dataset to evaluate optimal training pipelines for downstream disease classification models. In contrast to prior work that combines real and synthetic data naively, we propose an improved training strategy that leverages synthetic data for supervised pretraining, followed by fine-tuning on real data. Through extensive evaluation on over 137,000 chest radiographs from five institutions, we demonstrate that synthetic pretraining consistently improves model performance, generalization to out-of-distribution settings, and fairness across demographic subgroups. Across datasets, synthetic pretraining led to a 6.5% accuracy increase in the performance of downstream classification models, compared to a modest 2.7% increase when naively combining real and synthetic data. We observe this performance improvement simultaneously with the reduction of the underdiagnosis fairness gap by 19.3%. These results highlight the potential of synthetic imaging to advance equitable and generalizable medical deep learning under real-world data constraints. We open source our code, trained models, and synthetic dataset at https://github.com/StanfordMIMI/RoentGen-v2 .

Marianna Nezhurina, Lucia Cipolina-Kun, Mehdi Cherti et al.

Large Language Models (LLMs) are often described as instances of foundation models that possess strong generalization obeying scaling laws, and therefore transfer robustly across various conditions in few- or zero-shot manner. Such claims rely on standardized benchmarks that suppose to measure generalization and reasoning, where state-of-the-art (SOTA) models score high. We demonstrate here a dramatic breakdown of generalization and basic reasoning of all SOTA models claiming strong function, including large scale advanced models like GPT-4 or Claude 3 Opus, using a simple, short common sense math problem formulated in concise natural language, easily solvable by humans (AIW problem). The breakdown is dramatic as it manifests on a simple problem in both low average performance and strong performance fluctuations on natural variations in problem template that do not change either problem structure or its difficulty at all. By testing models on further control problems with similar form, we rule out that breakdown might be rooted in minor low-level issues like natural language or numbers parsing. We also observe strong overconfidence in the wrong solutions, expressed in form of plausible sounding explanation-like confabulations. Various standard interventions in an attempt to get the right solution, like chain-of-thought prompting, or urging the models to reconsider the wrong solutions again by multi step re-evaluation, fail. We use these observations to stimulate re-assessment of the capabilities of current generation of LLMs as claimed by standardized benchmarks. Such re-assessment also requires common action to create standardized benchmarks that would allow proper detection of such deficits in generalization and reasoning that obviously remain undiscovered by current state-of-the-art evaluation procedures, where SOTA LLMs manage to score high. Code: https://github.com/LAION-AI/AIW

Vishaal Udandarao, Mehdi Cherti, Shyamgopal Karthik et al. · cambridge

We investigate 17 benchmarks (e.g. SugarCREPE, VALSE) commonly used for measuring compositional understanding capabilities of vision-language models (VLMs). We scrutinize design choices in their construction, including data source (e.g. MS-COCO) and curation procedures (e.g. constructing negative images/captions), uncovering several inherent biases across most benchmarks. We find that blind heuristics (e.g. token-length, log-likelihood under a language model) perform on par with CLIP models, indicating that these benchmarks do not effectively measure compositional understanding. We demonstrate that the underlying factor is a distribution asymmetry between positive and negative images/captions, induced by the benchmark construction procedures. To mitigate these issues, we provide a few key recommendations for constructing more robust vision-language compositional understanding benchmarks, that would be less prone to such simple attacks.

Jan Lewen, Max Pargmann, Jenia Jitsev et al.

Concentrating Solar Power (CSP) plants are a key technology in the transition toward sustainable energy. A critical factor for their safe and efficient operation is the distribution of concentrated solar flux on the receiver. However, flux distributions from individual heliostats are sensitive to surface imperfections. Measuring these surfaces across many heliostats remains impractical in real-world deployments. As a result, control systems often assume idealized heliostat surfaces, leading to suboptimal performance and potential safety risks. To address this, inverse Deep Learning Raytracing (iDLR) has been introduced as a novel method for inferring heliostat surface profiles from target images recorded during standard calibration procedures. In this work, we present the first successful Sim-to-Real transfer of iDLR, enabling accurate surface predictions directly from real-world target images. We evaluate our method on 63 heliostats under real operational conditions. iDLR surface predictions achieve a median mean absolute error (MAE) of 0.17 mm and show good agreement with deflectometry ground truth in 84% of cases. When used in raytracing simulations, it enables flux density predictions with a mean accuracy of 90% compared to deflectometry over our dataset, and outperforms the commonly used ideal heliostat surface assumption by 26%. We tested this approach in a challenging double-extrapolation scenario-involving unseen sun positions and receiver projection-and found that iDLR maintains high predictive accuracy, highlighting its generalization capabilities. Our results demonstrate that iDLR is a scalable, automated, and cost-effective solution for integrating realistic heliostat surface models into digital twins. This opens the door to improved flux control, more precise performance modeling, and ultimately, enhanced efficiency and safety in future CSP plants.

Stefan Kesselheim, Andreas Herten, Kai Krajsek et al.

In this article, we present JUWELS Booster, a recently commissioned high-performance computing system at the Jülich Supercomputing Center. With its system architecture, most importantly its large number of powerful Graphics Processing Units (GPUs) and its fast interconnect via InfiniBand, it is an ideal machine for large-scale Artificial Intelligence (AI) research and applications. We detail its system architecture, parallel, distributed model training, and benchmarks indicating its outstanding performance. We exemplify its potential for research application by presenting large-scale AI research highlights from various scientific fields that require such a facility.

Mehdi Cherti, Jenia Jitsev

Increasing model, data and compute budget scale in the pre-training has been shown to strongly improve model generalization and transfer learning in vast line of work done in language modeling and natural image recognition. However, most studies on the positive effect of larger scale were done in scope of in-domain setting, with source and target data being in close proximity. To study effect of larger scale for both in-domain and out-of-domain setting when performing full and few-shot transfer, we combine here for the first time large, openly available medical X-Ray chest imaging datasets to reach a scale for medical imaging domain comparable to ImageNet-1k, routinely used for pre-training in natural image domain. We then conduct supervised pre-training, while varying network size and source data scale and domain, being either large natural (ImageNet-1k/21k) or large medical chest X-Ray datasets, and transfer pre-trained models to different natural or medical targets. We observe strong improvement due to larger pre-training scale for intra-domain natural-natural and medical-medical transfer. For inter-domain natural-medical transfer, we find improvements due to larger pre-training scale on larger X-Ray targets in full shot regime, while for smaller targets and for few-shot regime the improvement is not visible. Remarkably, large networks pre-trained on very large natural ImageNet-21k are as good or better than networks pre-trained on largest available medical X-Ray data when performing transfer to large X-Ray targets. We conclude that substantially increasing model and generic, medical domain-agnostic natural image source data scale in the pre-training can enable high quality out-of-domain transfer to medical domain specific targets, removing dependency on large medical domain-specific source data often not available in the practice.

Léonard Boussioux, Tomás Giro-Larraz, Charles Guille-Escuret et al.

Insects play such a crucial role in ecosystems that a shift in demography of just a few species can have devastating consequences at environmental, social and economic levels. Despite this, evaluation of insect demography is strongly limited by the difficulty of collecting census data at sufficient scale. We propose a method to gather and leverage observations from bystanders, hikers, and entomology enthusiasts in order to provide researchers with data that could significantly help anticipate and identify environmental threats. Finally, we show that there is indeed interest on both sides for such collaboration.

Balázs Kégl, Mehdi Cherti, Akın Kazakçı

Traditional wisdom in generative modeling literature is that spurious samples that a model can generate are errors and they should be avoided. Recent research, however, has shown interest in studying or even exploiting such samples instead of eliminating them. In this paper, we ask the question whether such samples can be eliminated all together without sacrificing coverage of the generating distribution. For the class of models we consider, we experimentally demonstrate that this is not possible without losing the ability to model some of the test samples. While our results need to be confirmed on a broader set of model families, these initial findings provide partial evidence that spurious samples share structural properties with the learned dataset, which, in turn, suggests they are not simply errors but a feature of deep generative nets.

Laetitia Le, Camille Marini, Alexandre Gramfort et al.

Monoclonal antibodies constitute one of the most important strategies to treat patients suffering from cancers such as hematological malignancies and solid tumors. In order to guarantee the quality of those preparations prepared at hospital, quality control has to be developed. The aim of this study was to explore a noninvasive, nondestructive, and rapid analytical method to ensure the quality of the final preparation without causing any delay in the process. We analyzed four mAbs (Inlfiximab, Bevacizumab, Ramucirumab and Rituximab) diluted at therapeutic concentration in chloride sodium 0.9% using Raman spectroscopy. To reduce the prediction errors obtained with traditional chemometric data analysis, we explored a data-driven approach using statistical machine learning methods where preprocessing and predictive models are jointly optimized. We prepared a data analytics workflow and submitted the problem to a collaborative data challenge platform called Rapid Analytics and Model Prototyping (RAMP). This allowed to use solutions from about 300 data scientists during five days of collaborative work. The prediction of the four mAbs samples was considerably improved with a misclassification rate and the mean error rate of 0.8% and 4%, respectively.