Before Parc Ferm'e: RL-Time Pruning for Efficient Embodied LLMs in Autonomous Driving

arXiv:2605.31256 · cs.RO · Submitted 2026-05-29 · Read on arXiv

cs.RO

Submitted: 2026-05-29

Updated: 2026-10-13

Code: https://github.com/ggerganov/llama.cpp

Terminology

• Pruning — 12× in this paper · explained in 4 episodes
• Adaptability — 1× in this paper · explained in 1 episode
• Decode — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes

Sources

• A Survey on Efficient Vision-Language-Action Models
• Qwen2.5-Coder Technical Report
• Enhancing Autonomous Driving Systems with On-Board Deployed Large Language Models
• SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
• PAT: Pruning-Aware Tuning for Large Language Models
• Adapt-Pruner: Adaptive Structural Pruning for Efficient Small Language Model Training
• RL-Pruner: Structured Pruning Using Reinforcement Learning for CNN Compression and Acceleration

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies