learning efficiency
The rate at which an AI model improves its performance as it is exposed to more training data. It assesses how well the model utilizes its training time and data to enhance its learning outcomes.
- Adaptable Safe Policy Learning from Multi-task Data with Constraint Prioritized Decision Transformer
- Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning
- Diffusion Generative Modeling on Lie Group Representations
- Dynamic Diffusion Schrödinger Bridge in Astrophysical Observational Inversions
- ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning
- HubGT: Fast Graph Transformer with Decoupled Hierarchy Labeling
- Leveraging Conditional Dependence for Efficient World Model Denoising
- Meta-learning how to Share Credit among Macro-Actions
- PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning
- Policy Compatible Skill Incremental Learning via Lazy Learning Interface
- Predictive Preference Learning from Human Interventions
- Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling
- Straight-Line Diffusion Model for Efficient 3D Molecular Generation
- WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents