token usage
Refers to how the individual units of input data (tokens), typically in natural language processing, are utilized within models for tasks such as encoding and decoding information.
- Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
- Don’t Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
- Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning
- Teaching Language Models to Reason with Tools
- Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens
- Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models