Technology ❯ Machine Learning

Model Optimization

Generative AI Quantization Techniques Document Intelligence Attention Mechanisms Parameter Efficient Adaptation Fine-Tuning Techniques Dynamic Selection Performance Improvement Generalization Techniques Token Pruning Techniques

XPENG–Peking University’s FastDriveVLA Accepted at AAAI 2026, Cutting VLA Compute Nearly 7.5x

The reconstruction-based token pruning method reports state-of-the-art nuScenes results with far fewer visual tokens.

Developers Embrace RAG to Ground Language Models in Accurate, Up-to-Date Data