cross-task generalization
The ability of an AI model trained on one task to perform well on different but related tasks, highlighting the model’s adaptability and the efficiency of learning shared representations across diverse applications.
- A Bayesian Fast-Slow Framework to Mitigate Interference in Non-Stationary Reinforcement Learning
- Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs
- DyFlow: Dynamic Workflow Framework for Agentic Reasoning
- Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization
- Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning
- Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression Recognition
- Unified Transferability Metrics for Time Series Foundation Models