compute scaling
Compute scaling refers to the practice of increasing computational resources (e.g., processing power, memory) to train AI models more effectively. Larger models and datasets often require more compute resources, impacting training times and costs.
- Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies
- Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies
- Compute-Optimal Scaling for Value-Based Deep RL
- Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
- Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions
- When Worse is Better: Navigating the Compression Generation Trade-off In Visual Tokenization