real-world benchmarks
Standards or datasets derived from actual conditions used to assess the performance of AI models against realistic scenarios and challenges.
- Conditioning Matters: Training Diffusion Policies is Faster Than You Think
- FAME: Adaptive Functional Attention with Expert Routing for Function-on-Function Regression
- Fairness-aware Anomaly Detection via Fair Projection
- Inductive Domain Transfer In Misspecified Simulation-Based Inference
- InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction
- Masked Diffusion Models as Energy Minimization
- Model Provenance Testing for Large Language Models
- Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning
- SONAR: Long-Range Graph Propagation Through Information Waves
- Thought Communication in Multiagent Collaboration
- Toward Interpretable Evaluation Measures for Time Series Segmentation
- Train on Pins and Test on Obstacles for Rectilinear Steiner Minimum Tree