AIBullisharXiv – CS AI · 5h ago7/10
🧠
Planning-aligned Token Compression for Long-Context Autonomous Driving
Researchers propose COMPACT-VA, a planning-aligned token compression framework using conditional VQ-VAE to enable vision-action models in autonomous driving to process extended temporal context within real-time computational budgets. The approach achieves over 6% improvement in driving success rates while delivering 3.3x speedup and 2.7x memory reduction compared to uncompressed processing.