out-of-distribution scenarios
These scenarios refer to situations where the data encountered by a model during evaluation or deployment diverges significantly from the data it was trained on. They pose challenges in generalization and robustness in machine learning applications.
- 3D Interaction Geometric Pre-training for Molecular Relational Learning
- A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding
- Factor Decorrelation Enhanced Data Removal from Deep Predictive Models
- Prompt Tuning Decision Transformers with Structured and Scalable Bandits
- RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning
- Uncertainty-Informed Meta Pseudo Labeling for Surrogate Modeling with Limited Labeled Data