#model-optimization4 articles

4 articles

AIBullisharXiv – CS AI · 4h ago7

🧠

Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty

Researchers developed ARLCP, a reinforcement learning framework that reduces unnecessary reflection in Large Reasoning Models, achieving 53% shorter responses while improving accuracy by 5.8% on smaller models. The method addresses computational inefficiencies in AI reasoning by dynamically balancing efficiency and accuracy through adaptive penalties.

AIBullisharXiv – CS AI · 4h ago4

🧠

TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation

Researchers have developed TIGER, a new speech separation model that reduces parameters by 94.3% and computational costs by 95.3% while outperforming current state-of-the-art models. The team also introduced EchoSet, a new dataset with realistic acoustic environments that shows better generalization for speech separation models.

AIBullisharXiv – CS AI · 4h ago4

🧠

Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization

Researchers propose MetaAPO, a new framework for aligning large language models with human preferences that dynamically balances online and offline training data. The method uses a meta-learner to evaluate when on-policy sampling is beneficial, resulting in better performance while reducing online annotation costs by 42%.

AINeutralarXiv – CS AI · 4h ago0

🧠

FedVG: Gradient-Guided Aggregation for Enhanced Federated Learning

Researchers introduce FedVG, a new federated learning framework that uses gradient-guided aggregation and global validation sets to improve model performance in distributed training environments. The approach addresses client drift issues in heterogeneous data settings and can be integrated with existing federated learning algorithms.