optimization objective
The goal of an optimization problem posed to an AI model, often expressed as a loss function that the learning algorithm seeks to minimize or maximize.
- A Partition Cover Approach to Tokenization
- An Efficient Local Search Approach for Polarized Community Discovery in Signed Networks
- Rethinking Losses for Diffusion Bridge Samplers
- SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning
- Spectral Graph Coarsening Using Inner Product Preservation and the Grassmann Manifold
- Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning