model scaling
The process of increasing the size or capacity of machine learning models, typically by enlarging architectures or data, often aimed at improving performance on complex tasks.
- AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
- Critical Batch Size Revisited: A Simple Empirical Approach to Large-Batch Language Model Training
- Do Language Models Use Their Depth Efficiently?
- Exploring the limits of strong membership inference attacks on large language models
- Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads
- Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning