Search Results for author:
Found 2 papers, 0 papers with code
Informal Safety Guarantees for Simulated Optimizers Through Extrapolation from Partial Simulations
This variant leveraging scaling dimensionality is named the Cartesian object, and is used to represent simulations (where individual simulacra are the agents and devices in that object).
Beyond Training Objectives: Interpreting Reward Model Divergence in Large Language Models
Large language models (LLMs) fine-tuned by reinforcement learning from human feedback (RLHF) are becoming more widely deployed.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
