MoSE: Skill-by-Skill Mixture-of-Expert Learning for Autonomous Driving

• URL: http://arxiv.org/abs/2507.07818v1
• Date: Thu, 10 Jul 2025 14:48:08 GMT
• Title: MoSE: Skill-by-Skill Mixture-of-Expert Learning for Autonomous Driving
• Authors: Lu Xu, Jiaqian Yu, Xiongfeng Peng, Yiwei Chen, Weiming Li, Jaewook Yoo, Sunghyun Chunag, Dongwook Lee, Daehyun Ji, Chao Zhang,
• Abstract summary: We propose a skill-oriented MoE, called MoSE, which mimics human drivers' learning process, skill-by-skill and step-by-step.<n>We build a hierarchical skill dataset and pretrain the router to encourage the model to think step-by-step.<n>With less than 3B sparsely activated parameters, our model outperforms several 8B+ parameters on CODA AD corner case reasoning task.
• Score: 14.042949333988785
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent studies show large language models (LLMs) and vision language models (VLMs) trained using web-scale data can empower end-to-end autonomous driving systems for a better generalization and interpretation. Specifically, by dynamically routing inputs to specialized subsets of parameters, the Mixture-of-Experts (MoE) technique enables general LLMs or VLMs to achieve substantial performance improvements while maintaining computational efficiency. However, general MoE models usually demands extensive training data and complex optimization. In this work, inspired by the learning process of human drivers, we propose a skill-oriented MoE, called MoSE, which mimics human drivers' learning process and reasoning process, skill-by-skill and step-by-step. We propose a skill-oriented routing mechanism that begins with defining and annotating specific skills, enabling experts to identify the necessary driving competencies for various scenarios and reasoning tasks, thereby facilitating skill-by-skill learning. Further align the driving process to multi-step planning in human reasoning and end-to-end driving models, we build a hierarchical skill dataset and pretrain the router to encourage the model to think step-by-step. Unlike multi-round dialogs, MoSE integrates valuable auxiliary tasks (e.g.\ description, reasoning, planning) in one single forward process without introducing any extra computational cost. With less than 3B sparsely activated parameters, our model outperforms several 8B+ parameters on CODA AD corner case reasoning task. Compared to existing methods based on open-source models and data, our approach achieves state-of-the-art performance with significantly reduced activated model size (at least by $62.5\%$) with a single-turn conversation.

Related papers

• Multi-modal Knowledge Distillation-based Human Trajectory Forecasting [35.060041571520024]
  Pedestrian trajectory forecasting is crucial in various applications such as autonomous driving and mobile robot navigation.<n>In such applications, camera-based perception enables the extraction of additional modalities (human pose, text) to enhance prediction accuracy.<n>We propose a multi-modal knowledge distillation framework: a student model with limited modality is distilled from a teacher model trained with full range of modalities.
  arXiv  Detail & Related papers  (2025-03-28T07:32:51Z)
• MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models [34.138699712315]
  This paper introduces a novel vision--action (VLA) model, mixture of robotic experts (MoRE) for quadruped robots.<n>MoRE integrates multiple low-rank adaptation modules as distinct experts within a dense multi-modal large language model.<n>Experiments demonstrate that MoRE outperforms all baselines across six different skills and exhibits superior generalization capabilities in out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-03-11T03:13:45Z)
• LLMs Can Evolve Continually on Modality for X-Modal Reasoning [62.2874638875554]
  Existing methods rely heavily on modal-specific pretraining and joint-modal tuning, leading to significant computational burdens when expanding to new modalities. We propose PathWeave, a flexible and scalable framework with modal-Path sWitching and ExpAnsion abilities. PathWeave performs comparably to state-of-the-art MLLMs while concurrently reducing parameter training burdens by 98.73%.
  arXiv  Detail & Related papers  (2024-10-26T13:19:57Z)
• MoExtend: Tuning New Experts for Modality and Task Extension [61.29100693866109]
  MoExtend is an effective framework designed to streamline the modality adaptation and extension of Mixture-of-Experts (MoE) models. MoExtend seamlessly integrates new experts into pre-trained MoE models, endowing them with novel knowledge without the need to tune pretrained models.
  arXiv  Detail & Related papers  (2024-08-07T02:28:37Z)
• Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters [65.15700861265432]
  We present a parameter-efficient continual learning framework to alleviate long-term forgetting in incremental learning with vision-language models. Our approach involves the dynamic expansion of a pre-trained CLIP model, through the integration of Mixture-of-Experts (MoE) adapters. To preserve the zero-shot recognition capability of vision-language models, we introduce a Distribution Discriminative Auto-Selector.
  arXiv  Detail & Related papers  (2024-03-18T08:00:23Z)
• Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives [56.2139730920855]
  We present a systematic analysis of MM-VUFMs specifically designed for road scenes. Our objective is to provide a comprehensive overview of common practices, referring to task-specific models, unified multi-modal models, unified multi-task models, and foundation model prompting techniques. We provide insights into key challenges and future trends, such as closed-loop driving systems, interpretability, embodied driving agents, and world models.
  arXiv  Detail & Related papers  (2024-02-05T12:47:09Z)
• When Parameter-efficient Tuning Meets General-purpose Vision-language Models [65.19127815275307]
  PETAL revolutionizes the training process by requiring only 0.5% of the total parameters, achieved through a unique mode approximation technique. Our experiments reveal that PETAL not only outperforms current state-of-the-art methods in most scenarios but also surpasses full fine-tuning models in effectiveness.
  arXiv  Detail & Related papers  (2023-12-16T17:13:08Z)
• eP-ALM: Efficient Perceptual Augmentation of Language Models [70.47962271121389]
  We propose to direct effort to efficient adaptations of existing models, and propose to augment Language Models with perception. Existing approaches for adapting pretrained models for vision-language tasks still rely on several key components that hinder their efficiency. We show that by freezing more than 99% of total parameters, training only one linear projection layer, and prepending only one trainable token, our approach (dubbed eP-ALM) significantly outperforms other baselines on VQA and Captioning.
  arXiv  Detail & Related papers  (2023-03-20T19:20:34Z)
• Skill-based Model-based Reinforcement Learning [18.758245582997656]
  Model-based reinforcement learning (RL) is a sample-efficient way of learning complex behaviors. We propose a Skill-based Model-based RL framework (SkiMo) that enables planning in the skill space. We harness the learned skill dynamics model to accurately simulate and plan over long horizons in the skill space.
  arXiv  Detail & Related papers  (2022-07-15T16:06:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.