out-of-distribution
Out-of-distribution (OOD) refers to data that significantly deviates from the training distribution. Models may struggle on OOD samples, leading to poor performance; therefore, handling OOD scenarios is crucial for robust AI systems.
- BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
- FLiP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learning
- HiMoLE: Towards OOD-Robust LoRA via Hierarchical Mixture of Experts
- IDOL: Meeting Diverse Distribution Shifts with Prior Physics for Tropical Cyclone Multi-Task Estimation
- Language‑Bias‑Resilient Visual Question Answering via Adaptive Multi‑Margin Collaborative Debiasing
- Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution
- MetaGS: A Meta-Learned Gaussian-Phong Model for Out-of-Distribution 3D Scene Relighting
- OOD Detection with Relative Angles
- Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies
- REDOUBT: Duo Safety Validation for Autonomous Vehicle Motion Planning
- Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding
- Results of the Big ANN: NeurIPS’23 competition
- Rethinking Out-of-Distribution Detection and Generalization with Collective Behavior Dynamics
- RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
- Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens