model accuracy
A measure of the correct predictions made by a model relative to the total predictions. It is a key performance metric used in evaluating classifiers, representing the fraction of true results over total cases.
- CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
- Causal Climate Emulation with Bayesian Filtering
- DUO: No Compromise to Accuracy Degradation
- FedEL: Federated Elastic Learning for Heterogeneous Devices
- Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning
- Revolutionizing Graph Aggregation: From Suppression to Amplification via BoostGCN
- Scaling Up Active Testing to Large Language Models
- SeerAttention: Self-distilled Attention Gating for Efficient Long-context Prefilling
- Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks