| Name | Description | Git repository link(s) | Other access link (data/tool/docs) | Paper Link | Citation |
| AnomalyDiscovery_Examples | Tree-ensemble anomaly detection with batch and streaming active learning from analyst feedback | https://github.com/shubhomoydas/ad_examples | https://jair.org/index.php/jair/article/view/14741 | Das, S., Islam, M.R., Jayakodi, N.K., & Doppa, J.R. Effectiveness of Tree-based Ensembles for Anomaly Discovery: Insights, Batch and Streaming Active Learning | |
| AL-GSA-DGSMs | Active learning method for global sensitivity analysis with Gaussian processes, finding which inputs matter most with few experiments | https://github.com/belakaria/AL-GSA-DGSMs | https://proceedings.neurips.cc/paper_files/paper/2024/hash/60f81431bdf32f139438c69787e12b3f-Abstract.html | Belakaria, S., Letham, B., Doppa, J.R., Engelhardt, B., Ermon, S., & Bakshy, E. Active Learning for Derivative-Based Global Sensitivity Analysis with Gaussian Processes | |
| CAPS | Offline safe reinforcement learning method that switches between policies to adapt to different safety constraints | https://github.com/yassineCh/CAPS | https://ojs.aaai.org/index.php/AAAI/article/view/33726 | Chemingui, Y., Deshwal, A., Wei, H., Fern, A., & Doppa, J. Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning | |
| Conformal Prediction for Generative Models | Method producing prediction sets with guaranteed coverage for deep generative models, by reducing the problem to conformal regression | https://github.com/Varal7/conformal-language-modeling (baseline) | https://proceedings.mlr.press/v286/shahrokhi25a.html | Shahrokhi, H., Roy, D., Yan, Y., Arnaoudova, V., & Doppa, J. Conformal Prediction Sets for Deep Generative Models via Reduction to Conformal Regression | |
| DTW-AR | Framework that generates adversarial examples for time-series models using dynamic time warping, to test and improve robustness | https://github.com/tahabelkhouja/DTW-AR | https://arxiv.org/abs/2207.04308 | Belkhouja, T., Yan, Y., & Doppa, J.R. Dynamic Time Warping Based Adversarial Framework for Time-Series Domain | |
| GenAI Student Cognition Study Data | Study data on how generative AI use affects students’ thinking habits and trust | https://zenodo.org/records/19467287 | https://www.sciencedirect.com/science/article/abs/pii/S0950584926003356?via%3Dihub | Choudhuri, R., Sanchez, C.A., Burnett, M., & Sarma, A. Thinking Less, Trusting More: GenAI’s Impacts on Students’ Cognitive Habits | |
| Grape Cold Hardiness Model | Web model forecasting grapevine cold hardiness across cultivars using multi-task learning, to help growers protect vines from freeze damage | https://weather.wsu.edu/models/grape_cold_hardiness | https://ojs.aaai.org/index.php/AAAI/article/view/26865 | Saxena, A., Pesantez-Cabrera, P., Ballapragada, R., Lam, K.-H., Keller, M., & Fern, A. (2023). Grape Cold Hardiness Prediction via Multi-Task Learning | |
| NCP (Neighborhood Conformal Prediction) | Algorithm that improves uncertainty estimates of deep classifiers by using neighboring examples in conformal prediction | https://github.com/1995subhankar1995/NCP | https://doi.org/10.1609/aaai.v37i6.25936 | Ghosh, S., Belkhouja, T., Yan, Y., & Doppa, J.R. Improving Uncertainty Quantification of Deep Classifiers via Neighborhood Conformal Prediction: Novel Algorithm and Theoretical Analysis | |
| O3SRL | Offline safe reinforcement learning method that learns safe policies from logged data using online optimization | https://github.com/yassineCh/O3SRL | https://proceedings.neurips.cc/paper_files/paper/2025/hash/cdc099a583d760335ee9b5ab21626a48-Abstract-Conference.html | Chemingui, Y., Deshwal, A., Fern, A., Nguyen-Tang, T., & Doppa, J.R. Online Optimization for Offline Safe Reinforcement Learning | |
| OptBias | Black-box optimization method that works from small offline datasets by meta-learning on synthetic tasks | https://github.com/azzafadhel/OptBias | https://proceedings.mlr.press/v300/fadhel26a.html | Fadhel, A., Tran, T.H., Hoang, T.N., & Doppa, J. Black-Box Optimization From Small Offline Datasets via Meta Learning with Synthetic Tasks | |
| PhenoTracker | Machine learning model that tracks grapevine phenological (growth) stages | https://github.com/AgAIDInstitute/PhenoTracker | https://doi.org/10.1145/3750720.3758079 | Balcarcel, N., Pesantez-Cabrera, P., Goebel, K., Keller, M., Khot, L., Fern, A., & Kalyanaraman, A. PhenoTracker: A machine learning model to track grape | |
| Robotic Hand Slip Detection Data | Inertial sensor recordings used to train deep learning models that detect when objects slip in compliant robotic hands | https://zenodo.org/records/15886336 | https://doi.org/10.3389/frobt.2025.1698591 | Cravetz, M., Vyas, P., Grimm, C., & Davidson, J.R. Slip detection for compliant robotic hands using inertial signals and deep learning | |
| Robust Training for Time-Series | Algorithms for training deep time-series models that resist adversarial noise and perturbations | https://github.com/tahabelkhouja/Robust-Training-for-Time-Series | https://doi.org/10.1609/aaai.v36i6.20552 | Belkhouja, T., Yan, Y., & Doppa, J.R. Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis | |
| SRS (Seasonal Ratio Scoring) | Method that flags time-series data that differs from what a model was trained on (out-of-distribution detection), using seasonal patterns | https://github.com/tahabelkhouja/SRS | https://doi.org/10.1145/3630633 | Belkhouja, T., Yan, Y., & Doppa, J.R. Out-of-distribution Detection in Time-series Domain: A Novel Seasonal Ratio Scoring Approach | |
| SteinGate | Safe reinforcement learning method that guards against rare, high-cost failures using Stein discrepancy | https://github.com/yassineCh/SteinGate | https://proceedings.mlr.press/v337/chemingui26a.html | Chemingui, Y., Fan, C., Wei, H., & Doppa, J.R. SteinGate: Tail-Sensitive Safe Reinforcement Learning via Stein Discrepancy | |
| StreamPred (Streamflow GNN) | Streamflow prediction with uncertainty for water management; combines learning with physical constraints (Gaussian-process deep kernels) so physical laws hold at test time | https://github.com/aminegha/StreamPred | https://www.ijcai.org/proceedings/2024/804 | Gharsallaoui, M.A., Singh, B., Savalkar, S., Deshwal, A., Kalyanaraman, A., Rajagopalan, K., & Doppa, J.R. Streamflow Prediction with Uncertainty Quantification for Water Management: A Constrained Reasoning and Learning Approach. IJCAI 2024 | |
| Subdaily Precipitation Extremes | Code for the climatology and trends of annual maximum sub-daily rainfall in the western US | https://github.com/dmitri1357/subdaily_precipitation_extremes | https://escholarship.org/uc/item/3z42s601 | Kalashnikov, D.A., Abatzoglou, J.T., & Swain, D.L. Climatology and trends of annual maximum subdaily precipitation in the Western United States | |
| SWE-Attention | Attention-based deep learning models that predict snow-water equivalent (the water stored in snowpack) for water-supply planning | https://github.com/Krishuthapa/SWE-Attention | https://ojs.aaai.org/index.php/AAAI/article/view/30337 | Thapa, K.K., Singh, B., Savalkar, S., Fern, A., Rajagopalan, K., & Kalyanaraman, A. Attention-Based Models for Snow-Water Equivalent Prediction | |
| Tropical Cyclone Precipitation Analysis | Data and code quantifying how much tropical cyclones contribute to extreme hourly rainfall across the contiguous US | https://github.com/dmitri1357/TC-precipitation-paper | https://zenodo.org/records/18853289 | https://escholarship.org/uc/item/6wt112qk | Kalashnikov, D.A., Abatzoglou, J.T., & Stansfield, A.M. Contribution of Tropical Cyclones to Hourly Precipitation Extremes in the Contiguous United States |
| Western US Heatwave–Wildfire Data | Ecoregion-aggregated dataset and code linking heatwaves to wildfire activity in the western US | Data: https://doi.org/10.5281/zenodo.15748738 ; Code: https://doi.org/10.5281/zenodo.18895413 | https://doi.org/10.1126/sciadv.aea1277 | Kalashnikov, D.A., Abatzoglou, J.T., Williams, E.L., Yin, C., Gurazada, M., Kumar, M., Thomas, A.P., & Ebiendele, P.E. Heatwaves enable wildfire activity in the western United States | |
| WOFOSTGym | Crop simulator for training reinforcement learning agents on management strategies for 23 annual and 2 perennial crops across single and multiple farms; built because no existing simulator suited specialty crops | https://github.com/Intelligent-Reliable-Autonomous-Systems/WOFOSTGym | Docs: https://intelligent-reliable-autonomous-systems.github.io/WOFOSTGym-Docs/ | https://rlj.cs.umass.edu/2025/papers/Paper55.html | Solow, W., Saisubramanian, S., & Fern, A. (2025). WOFOSTGym: A Crop Simulator for Learning Annual and Perennial Crop Management Strategies. Reinforcement Learning Journal, 6, 671–689. (RLC 2025 Distinguished Paper) |
| Hybrid Modeling for Crop Prediction | A hybrid modeling approach that uses a neural network to parameterize a differentiable biophysical model and leverages multi-task learning for efficient data sharing across crop cultivars for crop state prediction | https://github.com/Intelligent-Reliable-Autonomous-Systems/DMC-MTL | https://ijcai.org/proceedings/2026/826 | Solow, W., Pesantez-Cabrera, P., Keller, M., Khot, L., Saisubramanian, S., & Fern, A. (2026). A Hybrid Modeling Framework for Crop Prediction Tasks via Dynamic Parameter Calibration and Multi-Task Learning. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26 (pp. 7428–7436). IJCAI. https://doi.org/10.24963/ijcai.2026/826 |
