predictive accuracy
A measure of how well a model's predictions align with actual outcomes, critical for evaluating the effectiveness of AI systems.
- A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities
- Automatic Auxiliary Task Selection and Adaptive Weighting Boost Molecular Property Prediction
- Collaborative and Confidential Junction Trees for Hybrid Bayesian Networks
- ELECTRA: A Cartesian Network for 3D Charge Density Prediction with Floating Orbitals
- Factor Decorrelation Enhanced Data Removal from Deep Predictive Models
- From Black-box to Causal-box: Towards Building More Interpretable Models
- Improving Time Series Forecasting via Instance-aware Post-hoc Revision
- Incremental Sequence Classification with Temporal Consistency
- Informed Initialization for Bayesian Optimization and Active Learning
- KSP: Kolmogorov-Smirnov metric-based Post-Hoc Calibration for Survival Analysis
- Learning Gradient Boosted Decision Trees with Algorithmic Recourse
- Learning Stochastic Multiscale Models
- ML4CFD Competition: Results and Retrospective Analysis
- MLIP Arena: Advancing Fairness and Transparency in Machine Learning Interatomic Potentials via an Open, Accessible Benchmark Platform
- Model–Behavior Alignment under Flexible Evaluation: When the Best-Fitting Model Isn’t the Right One
- Neuro-Spectral Architectures for Causal Physics-Informed Networks
- R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization
- Simple and Effective Specialized Representations for Fair Classifiers
- Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness
- SpectraLDS: Provable Distillation for Linear Dynamical Systems
- TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrieval
- Test Time Scaling for Neural Processes
- What Moves the Eyes: Doubling Mechanistic Model Performance Using Deep Networks to Discover and Test Cognitive Hypotheses