A curated list of applications of the tabular foundation model TabPFN, grouped by industry.
- Healthcare and Life Sciences — 103 use cases
- Financial Services, Banking, and Insurance — 9 use cases
- Energy and Utilities — 27 use cases
- Industrial and Manufacturing — 41 use cases
- Other Industries — 34 use cases
| # | Application | Link |
|---|---|---|
| 1 | TabPFN enabled non-invasive early detection of pancreatic cancer by integrating NMR metabolomics with clinical and protein biomarkers | Paper |
| 2 | TabPFN enables highly accurate and cost-efficient molecular property prediction by pairing in-context learning with frozen molecular embeddings and descriptor | Paper |
| 3 | TabPFN enabled robust prediction of silica nanoparticle cytotoxicity | Paper |
| 4 | TabPFN was combined with BulkFormer to improve prediction accuracy of post-transplant kidney function for better assessment of organ viability during machine perfusion or cold storage | Paper |
| 5 | TabPFN enhances survival analysis, leading to superior performance compared to specialized methods | Paper |
| 6 | TabPFN demonstrated superior performance and translational feasibility for liver fibrosis staging | Paper |
| 7 | TabPFN was leveraged in cardiovascular disease diagnosis | Paper |
| 8 | TabPFN enabled accurate prediction of ALM from multimodal clinical data and improved sarcopenia screening by maintaining robust performance despite missing modalities | Paper |
| 9 | TabPFN was employed in the winning solution for predicting walking function | Paper |
| 10 | TabPFN demonstrated high accuracy and specificity in matching cell line transcriptomes to reference kidney cell types using curated kidney marker gene lists, enhancing robust assessment of cell line identity | Paper |
| 11 | TabPFN was used to enhance prediction accuracy of protein coupling based on structural features, improving biological insight into protein interactions | Paper |
| 12 | TabPFN supports risk stratification and adverse event prediction in chemotherapy-based stem cell mobilization, enabling improved ward management and resource allocation | Paper |
| 13 | TabPFN used with other ML models to improve radiomics-based breast cancer diagnosis, enhancing feature-combination performance and classification accuracy | Paper |
| 14 | TabPFN enhances model interpretability and accuracy in differentiating complex spinal infections, aiding clinical decision-making in ambiguous diagnostic cases | Repo |
| 15 | TabPFN enables improved data quality and predictive model reliability by integrating unstructured clinical text with automated pipelines, enhancing early disease prediction and clinical decision-making | Paper |
| 16 | TabPFN improved severity classification performance in diabetic retinopathy, supporting more accurate staging and treatment planning | Paper |
| 17 | TabPFN was integrated into the multimodal MuCB-tabpfn framework, enabling high predictive accuracy in estimating pollutant concentrations in human blood | Paper |
| 18 | TabPFN enables better generalization and accuracy in modeling complex drug formulation data, improving AI-driven formulation design workflows | Paper |
| 19 | TabPFN enables state-of-the-art real-time stress detection by enhancing accuracy and interpretability of multimodal physiological and sensor data | Repo |
| 20 | TabPFN was applied as a robust and data-efficient alternative for tabular learning in drug discovery, improving performance on small and medium datasets and under out-of-distribution conditions | Paper |
| 21 | TabPFN was used to enhance clinical risk prediction from electronic health records by providing robust modeling under real-world constraints, improving prognosis accuracy and reliability | Paper |
| 22 | TabPFN achieved the highest performance in predicting BCRL risk with strong minority-class discrimination and accurate calibration | Paper |
| 23 | TabPFN achieved strong generalization performance in predicting adsorption capacity in zeolites, with physically meaningful interpretability | Paper |
| 24 | TabPFN achieved superior discriminative performance in predicting RSA risk by integrating multidimensional clinical data into accurate and interpretable screening models | Paper |
| 25 | TabPFN was used to encode structured EHR data for predicting peak VO₂ and identifying high-risk heart failure patients | Paper |
| 26 | TabPFN provided highly accurate predictions of donor mobilization success using baseline and post-mobilization variables, facilitating early triage and improved transplantation outcomes | Paper |
| 27 | TabPFN was integrated into the FocalTab framework to improve classification accuracy, handle class imbalance, and support early identification of adolescent alcohol use | Paper |
| 28 | TabPFN demonstrated strong robustness in cross-cohort microbiome disease prediction under domain shift, maintaining competitive performance across datasets | Paper |
| 29 | TabPFN was used as a meta-learner combining predictions of multiple base models to capture complex interactions and enhance early coronary artery disease prediction accuracy | Paper |
| 30 | TabPFN enables Bayesian inference via in-context learning without per-dataset training, improving accuracy, calibration, and inference speed in scientific disease modeling tasks | Paper |
| 31 | TabPFN was extended to multimodal learning through MMPFN, enabling effective integration of non-tabular modalities with structured clinical data | Paper |
| 32 | TabPFN enables unified Bayesian modeling to improve bioactivity prediction across the ChEMBL database, supporting more efficient drug discovery pipelines | Paper |
| 33 | TabPFN was used for effective differentiation between psychotic and non-psychotic major depression, improving classification accuracy and supporting psychiatric diagnosis | Paper |
| 34 | TabPFN enables more accurate and efficient causal inference to aid early diagnosis and understanding of Long COVID | Repo |
| 35 | TabPFN was utilized to improve clinical risk prediction models on MIMIC-III data, enhancing both accuracy and efficiency | Repo |
| 36 | TabPFN replaced an underperforming deep learning approach in glioblastoma trial matching, achieving significant accuracy gains in few-shot clinical prediction settings | Paper |
| 37 | TabPFN outperformed current methods in predicting HFNC therapy outcomes and demonstrated potential for improved performance with additional clinical measurements | Paper |
| 38 | TabPFN was used in a hybrid model combining radiomics and deep learning features to improve risk stratification for post-TIPS hepatic encephalopathy | Paper |
| 39 | TabPFN was fine-tuned as a proxy model to predict synthetic likelihood of hMOFs, enabling high-fidelity large-scale screening in materials-related biomedical contexts | Paper |
| 40 | TabPFN improved intra-European ancestry prediction accuracy when combined with ML-based marker selection, outperforming traditional approaches | Paper |
| 41 | TabPFN improves renal tumor classification accuracy in CT radiomics by effectively handling small, high-dimensional datasets without extensive tuning | Paper |
| 42 | TabPFN demonstrates competitive performance as a count-based model for clinical prediction on structured EHR data compared to transformer-based pipelines | Paper |
| 43 | TabPFN improves empathy detection accuracy and cross-subject generalization in human-centered video datasets | Paper |
| 44 | TabPFN enables accurate prediction of reaction kinetics, facilitating mechanistic understanding in biochar-catalyzed antibiotic degradation processes | Paper |
| 45 | TabPFN yields competitive or superior performance for multiple imputation tasks compared to alternative statistical and ML methods | Paper |
| 46 | TabPFN improves survival analysis performance by leveraging survival-aware priors, enhancing both prediction accuracy and model transparency | Repo |
| 47 | TabPFN improves multimodal skin cancer diagnosis by combining structured lesion features with clinical data for more accurate and interpretable predictions | Paper |
| 48 | TabPFN supports pediatric disease classification in clinical decision support systems, reducing misdiagnosis in emergency settings | Paper |
| 49 | TabPFN improves EEG seizure classification across subjects, achieving high accuracy and strong generalization | Paper |
| 50 | TabPFN improves kelp origin prediction using stable isotope data, providing robust and interpretable environmental insights | Paper |
| 51 | TabPFN predicts CO₂ frosting temperatures in natural gas mixtures with high accuracy and interpretability | Paper |
| 52 | TabPFN improves ADMET modeling by increasing prediction accuracy, simplifying deployment, and producing compact models | Paper |
| 53 | TabPFN enhances analysis and classification of volatile organic compounds using mass spectrometry data, improving efficiency in chemical and biomedical analysis | Paper |
| 54 | TabPFN was applied to distinguish cancer patients from healthy individuals using immune system profiles from peripheral blood, facilitating predictions of immunotherapy responses | Media |
| 55 | A machine learning model employing TabPFN was developed for non-invasive diagnostic prediction of minimal change disease in patients with nephrotic syndrome, utilizing clinical biomarkers | Paper |
| 56 | TabPFN was integrated into a system for analyzing T-cell receptor repertoires combined with clinical biomarkers to forecast immunotherapy outcomes in cancer patients, as explored by researchers at BostonGene | Paper |
| 57 | TabPFN enabled early detection of stillbirth risks through analysis of cardiotocography data, supporting improved prenatal care | Paper |
| 58 | Predictive modeling for postoperative outcomes following anterior cervical corpectomy utilized TabPFN to assess patient demographics and surgical parameters | Paper |
| 59 | A hybrid model incorporating TabPFN was introduced to predict dementia progression in Parkinson's disease patients, handling small datasets and missing values effectively | Paper |
| 60 | A machine learning model based on TabPFN was developed to predict 90-day unfavorable outcomes in stroke patients with distal vessel occlusions using CT perfusion imaging | Paper |
| 61 | TabPFN was utilized in chemoproteomics for identifying small-molecule fragment-protein interactions, aiding ligand discovery in drug development | Paper |
| 62 | TabPFN facilitated the prediction of non-invasive ventilation outcomes in patients with acute hypoxemic respiratory failure, supporting early identification of treatment failures | Paper |
| 63 | An interpretable Transformer-based model leveraging TabPFN was created to predict intravenous immunoglobulin resistance in pediatric patients with Kawasaki disease | Paper |
| 64 | TabPFN was employed in visual representation techniques for prostate cancer diagnosis, converting clinical biomarkers and symptom data into formats suitable for analysis | Paper |
| 65 | TabPFN was used to combine clinical, MR morphological, and delta-radiomics features to predict lymphovascular invasion in invasive breast cancer patients | Paper |
| 66 | TabPFN is proposed to predict mental health trajectories through digital phenotyping, enabling proactive and personalized interventions in precision psychiatry | Paper |
| 67 | TabPFN contributed to cardiovascular disease risk stratification using clinical features from a large patient cohort, incorporating interpretability techniques | Repo |
| 68 | TabPFN outperformed traditional machine learning models for early prediction of acute kidney injury in hospitalized patients, demonstrating generalizability across datasets | Paper |
| 69 | TabPFN was integrated into a framework for predicting postoperative mobility and discharge destinations in older adults using sensor data | Paper |
| 70 | TabPFN supported the prediction of infant temperament from maternal mental health data, aiding early identification of at-risk infants | Paper |
| 71 | TabPFN was employed to characterize clinical risk profiles for complications in type 2 diabetes mellitus patients, focusing on neuropathy and retinopathy | Paper |
| 72 | TabPFN was extended with a longitudinal-to-cross-sectional transformation to forecast Alzheimer's disease progression on neuroimaging datasets | Paper |
| 73 | TabPFN supported uncertainty calibration evaluation in medical data using variational techniques | Paper |
| 74 | TabPFN was applied to predict tumor response to chemotherapy in cholangiocarcinoma patients using RNA expression landscapes | Paper |
| 75 | TabPFN was incorporated into a generative model framework for tasks like data augmentation and imputation in biomedicine | Paper |
| 76 | TabPFN facilitated the prediction of gallstone malignancy risks through analysis of associated disease factors | Paper |
| 77 | TabPFN was used in classifying tuberculosis treatment outcomes based on clinical and sociodemographic data from national registries | Paper |
| 78 | TabPFN contributed to early prediction of gestational diabetes using cell-free DNA and genetic scores from early pregnancy blood samples | Paper |
| 79 | TabPFN was used for predicting schizophrenia based on sense of agency features, emphasizing interpretability | Paper |
| 80 | TabPFN was integrated into a physiologically based pharmacokinetic model for predicting dissolution and absorption of amorphous solid dispersions in drug development | Paper |
| 81 | TabPFN enabled classification of respiratory diseases from sound data, addressing clinical spectrum diversity | Paper |
| 82 | TabPFN was applied to small-data tabular learning in drug discovery, handling data scarcity and distribution shifts | Paper |
| 83 | TabPFN facilitated prediction of coronary heart disease risk in patients with cardiovascular-kidney-metabolic syndrome, optimizing evaluation in small samples | Paper |
| 84 | TabPFN was used to predict success of allogeneic stem cell mobilization in donors, aiding transplant therapies | Paper |
| 85 | TabPFN contributed to predicting manual strength using anthropometric data, focusing on accuracy and interpretability | Paper |
| 86 | TabPFN supported uncertainty-guided model selection for biomolecule efficacy prediction, enhancing ensemble optimization in drug discovery, as studied at GSK | Paper |
| 87 | TabPFN was utilized in a multitask deep learning framework for optimizing in vitro fertilization decisions, including embryo transfer and pregnancy prediction | Paper |
| 88 | TabPFN enabled a framework for early Long COVID detection through causal gene identification and interpretability | Paper |
| 89 | TabPFN was used in a foundation model approach for neoadjuvant therapy recommendations in breast cancer, integrating multi-omics data | Paper |
| 90 | Recent work has demonstrated explainable machine learning pipelines for coronary artery disease stratification from routine clinical data | Paper |
| 91 | TabPFN facilitated prediction of recurrence and progression in oral potentially malignant disorder patients post-surgery | Paper |
| 92 | TabPFN supported prediction of occult lymph node metastasis in non-small cell lung cancer patients treated with stereotactic ablative radiotherapy | Paper |
| 93 | TabPFN was used in stroke diagnosis, addressing dataset imbalance and model interpretability for clinical decisions | Paper |
| 94 | TabPFN was integrated into a multimodal thesis framework for clinical predictions using tabular and phenotypic data from large-scale projects | Paper |
| 95 | TabPFN was used to predict diabetes-related hypo- and hyperglycemia during hemodialysis using continuous glucose monitoring data, facilitating improved patient management | Paper |
| 96 | TabPFN was applied to enhance diagnosis of hypervascular thyroid nodules using multimodal ultrasound features | Paper |
| 97 | TabPFN was integrated with radiomics and clinical features to predict endovascular treatment success in femoropopliteal chronic total occlusions, supporting interventional planning | Paper |
| 98 | TabPFN was applied to CorvisST biomechanical indices to classify corneal disorders, improving diagnostic accuracy in ophthalmology | Paper |
| 99 | TabPFN was incorporated into a non-invasive sleep staging framework using respiratory sound features, advancing passive sleep monitoring | Paper |
| 100 | TabPFN supported prediction of vancomycin blood concentrations to optimize antimicrobial dosing strategies in clinical practice | Paper |
| 101 | TabPFN was used to predict negative self-rated oral health in adults, identifying risk factors for targeted public-health interventions | Paper |
| 102 | TabPFN was extended to very high-dimensional feature spaces to enable robust analysis of biomedical data, improving stability and interpretability in clinical applications | Paper |
| 103 | TabPFN predicted gastrointestinal bleeding risk in pediatric Henoch–Schönlein purpura patients, supporting early clinical intervention | Paper |
| # | Application | Link |
|---|---|---|
| 1 | TabPFN improves low-supervision transaction analytics by doubling zero-shot MCC on churn prediction and enhancing few-shot MCC, enabling better knowledge-grounded reasoning in financial transaction analysis | Paper |
| 2 | TabPFN serves as a strong tabular baseline for financial transaction analytics (e.g., churn prediction) | Paper |
| 3 | TabPFN was employed as a core modeling component for learning from multimodal tabular data under strict temporal constraints, enabling strong discriminative performance, improved probability calibration, and effective causal forecasting in early rug-pull detection | Paper |
| 4 | TabPFN was used to predict forward financial returns, aiding investment strategy evaluation with the adjusted Sharpe ratio to enhance financial forecasting accuracy | Repo |
| 5 | TabPFN was fine-tuned into a domain-specific model (FinPFN) for regime-aware stock return prediction, improving performance in non-stationary financial markets by adapting to evolving feature--return relationships | Paper |
| 6 | TabPFN was benchmarked against leading AutoML frameworks on financial classification tasks, demonstrating strong performance in multiclass settings | Paper |
| 7 | TabPFN was applied to usage-based premium calculations in actuarial science, leveraging driving behavior data from IoT devices | Paper |
| 8 | TabPFN facilitated cross-selling of health insurance products through deep learning analysis of customer data | Paper |
| 9 | TabPFN was used in corporate bond recovery rate prediction for credit risk management | Repo |
| # | Application | Link |
|---|---|---|
| 1 | TabPFN serves as the top-performing regression model to estimate degradation kinetics from multi-source experimental data | Paper |
| 2 | TabPFN was used to improve the accuracy and reliability of modeling industrial carbon emissions data across regions and over time | Paper |
| 3 | TabPFN was used as a surrogate model for fast one-step predictions under irregular measurements, aiding the delay-aware digital twin framework in handling nonlinear dynamics and operational delays in biogas production control | Paper |
| 4 | TabPFN provided superior fitting performance for models analyzing biochar's impact on soil cadmium contamination, improving prediction accuracy in artificial and natural aging scenarios | Paper |
| 5 | TabPFN was used to improve the robustness and accuracy of photovoltaic power forecasting models by providing unified in-context prediction and strong generalization with heterogeneous inputs | Paper |
| 6 | TabPFN enables effective learning and prediction with very limited data by leveraging pretrained tabular inference, improving model performance in challenging geological prediction tasks | Paper |
| 7 | TabPFN was used as a baseline for comparison in spatiotemporal forecasting of small Earth data, demonstrating value despite being surpassed in accuracy and robustness by the proposed method | Paper |
| 8 | TabPFN demonstrated superior predictive performance under sparse sampling conditions, enabling accurate high-resolution mapping of groundwater bicarbonate concentrations and evaluation of scaling risks | Paper |
| 9 | TabPFN was used for slope stability assessment, providing superior accuracy and robustness with limited sample sizes and enhancing regional scale evaluation efficiency | Paper |
| 10 | TabPFN surpasses other models in solar energy meteorology | Paper |
| 11 | TabPFN Regression was used as a predictive model for evaluating trophic level index from multi-source remote sensing data within the modeling framework | Paper |
| 12 | TabPFN-based data augmentation improved model robustness under limited data, enabling accurate predictions of electrochemical performance and efficient screening of hard carbon candidates | Paper |
| 13 | TabPFN was employed to predict river algal blooms through multi-classification of chlorophyll-a concentrations, aiding water management | Paper |
| 14 | TabPFN facilitated wildfire propagation prediction in Canadian conifer forests, classifying fire types for environmental risk assessment | Paper |
| 15 | TabPFN was integrated into a machine learning framework for optimizing energy consumption at wastewater treatment plants | Paper |
| 16 | TabPFN supported rainfall forecast post-processing using historical error patterns from environmental data | Repo |
| 17 | TabPFN enabled solar forecast error adjustment, particularly during rapid weather changes, as developed by Open Climate Fix | Repo |
| 18 | TabPFN was applied to predict ash fusibility in high-alkali coal for improved energy production | Paper |
| 19 | TabPFN contributed to predicting Henry coefficients for alkanes in zeolites, aiding hydroisomerization in sustainable fuel production | Paper |
| 20 | TabPFN facilitated shape-selectivity modeling in zeolites for long-chain alkane hydroisomerization, optimizing catalyst design | Paper |
| 21 | TabPFN was used in an integrated framework for estimated ultimate recovery prediction and fracturing optimization in shale gas reservoirs | Paper |
| 22 | TabPFN supported core data augmentation for enhanced reservoir parameter prediction in oil and gas exploration | Paper |
| 23 | TabPFN was employed to optimize energy performance in multistage centrifugal pumps through entropy generation analysis | Paper |
| 24 | TabPFN contributed to physics-informed regression for evaluating solar-reflective materials in facade temperature modeling | Paper |
| 25 | TabPFN was applied to generate advanced global heat flow maps at 0.2° resolution, integrating high-resolution geophysical data to improve geothermal resource modeling | Paper |
| 26 | TabPFN contributed to FuelCast, standardizing benchmarks for ship fuel consumption prediction and improving efficiency in maritime operations | Paper |
| 27 | TabPFN was used as the main supervised classifier to automatically identify thunderstorm ground enhancements from particle detector and environmental measurements | Paper |
| # | Application | Link |
|---|---|---|
| 1 | TabPFN served as a high-fidelity surrogate model for optimizing geopolymer concrete mix design, achieving superior accuracy, generalization, and low-uncertainty predictions compared to other ML approaches | Paper |
| 2 | TabPFN enables rapid prediction of structural crack behavior, supporting reliability assessment and failure analysis in ultra-high-performance concrete | Paper |
| 3 | TabPFN leveraged prior-data pretraining to predict WCFZ height from only 76 field samples without extensive tuning, providing superior and generalizable performance compared to other ML models | Paper |
| 4 | TabPFN's multitask-aware prior adaptation improves predictive accuracy and computational efficiency in steel property prediction, enabling scalable, rapid, and reliable deployment for industrial quality control and process optimization | Paper |
| 5 | TabPFN's pre-trained foundation model enables strong small-data regression and well-calibrated uncertainty estimates in a single forward pass, significantly reducing evaluation cycles for active learning in materials discovery | Paper |
| 6 | TabPFN demonstrated strong generalization ability in predicting crash severity, contributing to improved data-driven safety interventions in electric vehicle crash contexts | Paper |
| 7 | TabPFN excelled in zero-shot inference and robustness for rare crash categories, enhancing classification of uncommon SAE automation levels with limited data | Paper |
| 8 | TabPFN 2.5's dataset-level embedding identified 'engineering-like' synthetic datasets to enable continued pre-training on synthetic tasks, significantly improving accuracy and data efficiency over baseline models and AutoGluon on engineering regression datasets | Paper |
| 9 | TabPFN achieved the highest prediction accuracy in predicting concrete fracture properties and, combined with SHAP analysis, provided detailed and unbiased insights into nonlinear and interaction effects | Paper |
| 10 | TabPFN significantly reduces computational overhead and data requirements while enabling rapid, flexible, and data-efficient engineering design with competitive diversity and low performance error in generated designs | Paper |
| 11 | TabPFN served as a backbone combined with graph neural network embeddings and MagpieEX descriptors for effective, data-efficient, and physics-aware materials property prediction, outperforming sophisticated models | Paper |
| 12 | TabPFN was used for spatial predictions and imputations in geotechnical modeling, achieving superior accuracy, faster inference, and well-calibrated predictive distributions compared to hierarchical Bayesian baselines | Paper |
| 13 | TabPFN provided strong prediction ability, outperforming alternatives and enabling more accurate performance prediction of biochar-modified concrete | Paper |
| 14 | TabPFN was used for accurate and reliable monitoring of driver alertness levels in challenging driving environments, proving more effective than traditional models like logistic regression and XGBoost | Paper |
| 15 | TabPFN enabled highly accurate and unbiased prediction of RAC's elastic modulus, improving trustworthiness and interpretability in a challenging heterogeneous materials domain | Paper |
| 16 | TabPFN provided meta-learned prior knowledge that enhanced predictive performance and uncertainty quantification in the PSF-Net model for reliable 5G RF-EMF exposure assessment | Paper |
| 17 | TabPFN showed superior predictive performance in predicting the hardgrove grindability index, improving model accuracy | Paper |
| 18 | TabPFN supported multiscale modeling to predict soil salinity in arid farmland, advancing sustainable agricultural management in regions such as Xinjiang | Paper |
| 19 | TabPFN delivered the best overall performance with the lowest error metrics and highest R² and composite score, demonstrating superior predictive capability for asphalt concrete strength | Paper |
| 20 | TabPFN was applied to efficient multi-objective optimization of non-linear mixture designs, improving strength, reducing costs, and lowering carbon emissions for sustainable mining applications | Paper |
| 21 | TabPFN was employed for highly accurate and statistically superior predictions of pavement roughness by capturing complex interactions among traffic loads, structural parameters, and climatic factors | Paper |
| 22 | TabPFN enables accurate prediction of CPB strength with limited data, improving efficiency and supporting theoretical understanding and practical application in mining industry tailings management | Paper |
| 23 | TabPFN's improved spatiotemporal architecture enhances robustness and accuracy in geological condition detection, enabling better multi-step predictions with uncertainty quantification in tunnel construction | Paper |
| 24 | TabPFN was integrated into a multimodal fusion framework linking microstructure to friction behavior in martensitic stainless steel, improving wear resistance in materials engineering applications | Paper |
| 25 | TabPFN was utilized as a core component in a multi-objective optimization framework to design cemented foam backfill optimizing high strength, low cost, and low carbon emissions | Paper |
| 26 | TabPFN enhances prediction accuracy and reliability with small sample sizes and missing features in geotechnical engineering | Paper |
| 27 | TabPFN enabled interpretable and uncertainty-aware parameter inference, improving predictions and revealing geotechnical relationships without model retraining for data-scarce applications | Paper |
| 28 | TabPFN was used to accurately predict compressive strength in geopolymer concrete from small datasets, supporting optimization of material composition and process parameters in construction material science | Paper |
| 29 | TabPFN was used to improve prediction accuracy in concrete property estimation by integrating knowledge-constrained data augmentation | Paper |
| 30 | TabPFN enabled efficient and accurate mapping of key leaf-vein texture parameters to lubrication performance metrics, facilitating multi-objective optimization to identify optimal texture designs that improve journal bearing performance | Paper |
| 31 | TabPFN enables robust mapping between operating boundary conditions and latent features to manage data scarcity and enhance regression accuracy, resulting in faster and more accurate temperature field reconstruction | Paper |
| 32 | TabPFN enables encoding of structured device-physics primitives for reliable and precise analog circuit optimization, outperforming Gaussian-process methods in sample efficiency and final metric quality | Paper |
| 33 | TabPFN enabled early fault classification in rotating machinery, addressing data scarcity in industrial scenarios | Paper |
| 34 | TabPFN facilitated microcontroller performance prediction, aiding semiconductor screening with minimal supervision, as studied at Infineon Technologies | Paper |
| 35 | TabPFN was applied to caisson inclination prediction in ultra-deep construction, combining data denoising techniques | Paper |
| 36 | TabPFN supported event classification in phase-sensitive optical time-domain reflectometry systems for distributed fiber sensing | Paper |
| 37 | TabPFN was integrated into an adaptive ensemble for intrusion detection in Industrial Internet of Things networks | Paper |
| 38 | TabPFN enabled a random forest-based framework for attack recognition in Internet of Things networks, improving interpretability | Paper |
| 39 | TabPFN was used in cryogenic-assisted abrasive waterjet machining for improving surface integrity in titanium alloys | Paper |
| 40 | TabPFN supported in-context learning for thermal behavior prediction in nano-phase change materials for battery systems | Paper |
| 41 | TabPFN was applied to explainable strength evaluation in multicomponent concrete mixtures | Paper |
| # | Application | Link |
|---|---|---|
| 1 | TabPFN enables the construction of credal sets for models where it was previously infeasible, broadening uncertainty representation and improving uncertainty estimation | Paper |
| 2 | TabPFN enables efficient and valid hypothesis testing for feature relevance in tabular data, allowing accurate statistical inference in nonlinear and correlated settings | Paper |
| 3 | TabPFN enables efficient computation of conditional Shapley values, resulting in faster and often more accurate explainable AI analysis | Paper |
| 4 | TabPFN enables effective node classification by leveraging engineered tabular features from graph data as a practical and competitive alternative to graph-specific and language-based foundation models | Paper |
| 5 | TabPFN was integrated as the surrogate model enabling accurate and efficient prediction with uncertainty estimation, enhancing the performance, scalability, and zero-shot transfer capability of the DB-SAEA framework | Paper |
| 6 | TabPFN was used to model the relationship between nuclear structure properties and α-particle preformation factors, improving α-decay half-life predictions and enabling insights into nuclear shell effects and magic numbers | Paper |
| 7 | TabPFN was used as a benchmark model for predicting avocado alternate bearing from Sentinel-2 and climate features. | Paper |
| 8 | TabPFN served as the foundation for TabMGP, enabling state-of-the-art predictive capabilities with effective epistemic uncertainty quantification and improved posterior inference in tabular data contexts | Paper |
| 9 | TabPFN demonstrated superior utility for real-world operational yield forecasting due to faster tuning and reduced feature engineering requirements | Paper |
| 10 | TabPFN serves as the base learner in a multi-stage ensemble to model recognition probabilities of rural villages, enabling identification of high-potential but under-observed candidates in geospatial, highly imbalanced datasets | Paper |
| 11 | TabPFN was used as a base learner in a stacking ensemble model, improving prediction accuracy and performance for soil salinity retrieval from multispectral imagery data | Paper |
| 12 | TabPFN serves as the foundational model for ExplainerPFN, enabling zero-shot estimation of Shapley values for feature importance without access to the predictive model or reference explanations | Paper |
| 13 | TabPFN enables accurate classification of Near-Earth Objects as Potentially Hazardous, facilitating early identification and monitoring of potential asteroid threats | Repo |
| 14 | TabPFN improves malware detection performance in limited data scenarios by outperforming traditional ensemble models, enhancing cybersecurity workflows | Paper |
| 15 | TabPFN achieved the best performance in predicting mycotoxin contamination, outperforming baseline and transfer learning models to enhance prediction accuracy for early interventions | Paper |
| 16 | TabPFN was used in a classification pipeline whose latent space provided a 2D representation of the blazar population, revealing a continuum between blazar types | Paper |
| 17 | TabPFN enhances accuracy and efficiency in predicting grapevine diseases by processing complex environmental data and providing per-pixel disease probabilities for precise vineyard disease management | Paper |
| 18 | TabPFN enhances synthetic tabular data generation by providing probabilistic modeling capabilities that improve data quality, realism, and utility | Repo |
| 19 | TabPFN was modified for microbiome data classification in metagenomics, matching species abundance patterns with synthetic priors | Paper |
| 20 | TabPFN enabled lunar regolith analysis for classifying meteorite compositions from spectral data | Paper |
| 21 | TabPFN facilitated winter wheat yield forecasting in agricultural regions by integrating climate and remote sensing data | Paper |
| 22 | TabPFN was applied to flood impact assessment on housing prices by geographic areas | Repo |
| 23 | TabPFN showed the strongest performance on 31 predictive soil modeling datasets containing 30 to 460 samples | Paper |
| 24 | TabPFN was applied to shallow natural gas hazard prediction in tunnel construction | Paper |
| 25 | TabPFN supported automated feature engineering for energy consumption forecasting in domain-specific applications | Paper |
| 26 | TabPFN enabled Australian rice phenology prediction using remote sensing and weather data for crop management | Paper |
| 27 | TabPFN was applied to a multi-stage framework for predicting fuel blend properties through automated feature engineering | Paper |
| 28 | TabPFN enabled kriging prior regression for incorporating spatial context in soil mapping predictions | Paper |
| 29 | TabPFN enhanced clone-type recognition across programming languages through metrics-driven analysis, improving stability and interpretability in software engineering | Paper |
| 30 | TabPFN informed the development of TabImpute, enabling efficient zero-shot imputation for missing tabular data and improving preprocessing pipelines | Paper |
| 31 | TabPFN, alongside TabICL and related foundation models, was evaluated for intrusion detection, improving cybersecurity performance in IoT networks | Paper |
| 32 | TabPFN supported continual learning for tabular data streams in resource-constrained environments | Paper |
| 33 | TabPFN contributed to assessing robustness of language models for data fitting under irrelevant variations | Paper |
| 34 | TabPFN was used in forensic science to advance biogeographical ancestry predictions | Paper |
We welcome contributions!
- Add a new usecase
- Improve existing ones
Please only submit usecases where TabPFN shows improvement.