parameter scaling
The process of adjusting the number of parameters in a model, either through increasing or decreasing them to improve efficiency, performance, or adaptability.
- Blackbox Model Provenance via Palimpsestic Membership Inference
- Exploring the limits of strong membership inference attacks on large language models
- Model Provenance Testing for Large Language Models
- MoonCast: High-Quality Zero-Shot Podcast Generation
- Parallel Scaling Law for Language Models
- Scaling Embedding Layers in Language Models
- Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
- The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text
- Training a Scientific Reasoning Model for Chemistry
- What Makes a Reward Model a Good Teacher? An Optimization Perspective