Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better

• URL: http://arxiv.org/abs/2505.23705v1
• Date: Thu, 29 May 2025 17:40:09 GMT
• Title: Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better
• Authors: Danny Driess, Jost Tobias Springenberg, Brian Ichter, Lili Yu, Adrian Li-Bell, Karl Pertsch, Allen Z. Ren, Homer Walke, Quan Vuong, Lucy Xiaoyang Shi, Sergey Levine,
• Abstract summary: Vision-language-action (VLA) models combine end-to-end learning with transfer of semantic knowledge from web-scale vision-language model (VLM) training.<n>The most powerful VLMs have tens or hundreds of billions of parameters, presenting an obstacle to real-time inference.<n>Recent VLA models have used specialized modules for efficient continuous control, such as action experts or continuous output heads.<n>We show that naively including such experts significantly harms both training speed and knowledge transfer.
• Score: 58.559985503802054
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-language-action (VLA) models provide a powerful approach to training control policies for physical systems, such as robots, by combining end-to-end learning with transfer of semantic knowledge from web-scale vision-language model (VLM) training. However, the constraints of real-time control are often at odds with the design of VLMs: the most powerful VLMs have tens or hundreds of billions of parameters, presenting an obstacle to real-time inference, and operate on discrete tokens rather than the continuous-valued outputs that are required for controlling robots. To address this challenge, recent VLA models have used specialized modules for efficient continuous control, such as action experts or continuous output heads, which typically require adding new untrained parameters to the pretrained VLM backbone. While these modules improve real-time and control capabilities, it remains an open question whether they preserve or degrade the semantic knowledge contained in the pretrained VLM, and what effect they have on the VLA training dynamics. In this paper, we study this question in the context of VLAs that include a continuous diffusion or flow matching action expert, showing that naively including such experts significantly harms both training speed and knowledge transfer. We provide an extensive analysis of various design choices, their impact on performance and knowledge transfer, and propose a technique for insulating the VLM backbone during VLA training that mitigates this issue. Videos are available at https://pi.website/research/knowledge_insulation.

Related papers

• Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting [70.83781268763215]
  Vision-language models (VLMs) have achieved impressive performance across diverse multimodal tasks by leveraging large-scale pre-training.<n>VLMs face unique challenges such as cross-modal feature drift, parameter interference due to shared architectures, and zero-shot capability erosion.<n>This survey aims to serve as a comprehensive and diagnostic reference for researchers developing lifelong vision-language systems.
  arXiv  Detail & Related papers  (2025-08-06T09:03:10Z)
• Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends [11.678954304546988]
  Vision-language-action (VLA) models extend vision-language models (VLM)<n>This paper reviews post-training strategies for VLA models through the lens of human motor learning.
  arXiv  Detail & Related papers  (2025-06-26T03:06:57Z)
• Weakly-supervised VLM-guided Partial Contrastive Learning for Visual Language Navigation [36.17444261325021]
  Visual Language Navigation (VLN) is a fundamental task within the field of Embodied AI, focusing on the ability of agents to navigate complex environments based on natural language instructions.<n>Existing methods rely on pre-trained backbone models for visual perception, which struggle with the dynamic viewpoints in VLN scenarios.<n>We propose Weakly-supervised Partial Contrastive Learning (WPCL), a method that enhances an agent's ability to identify objects from dynamic viewpoints in VLN scenarios without requiring VLM fine-tuning.
  arXiv  Detail & Related papers  (2025-06-18T11:43:50Z)
• CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering [27.812611421754482]
  We propose an MLLMs-based dual momentum Mixture-of-Experts (CL-MoE) framework for continual visual question answering (VQA)<n>We integrate MLLMs with continual learning to utilize the rich commonsense knowledge in LLMs.<n>Our method achieves state-of-the-art performance on 10 VQA tasks, proving the effectiveness of our approach.
  arXiv  Detail & Related papers  (2025-03-01T09:25:23Z)
• Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation [90.00687889213991]
  Solving complex long-horizon robotic manipulation problems requires sophisticated high-level planning capabilities.<n>Vision-language models (VLMs) pretrained on Internet data could in principle offer a framework for tackling such problems.<n>In this paper, we introduce a novel test-time framework that enhancesVLMs' physical reasoning capabilities for multi-stage manipulation tasks.
  arXiv  Detail & Related papers  (2025-02-23T20:42:15Z)
• VLM-Assisted Continual learning for Visual Question Answering in Self-Driving [26.413685340816436]
  We propose a novel approach for solving the Visual Question Answering (VQA) task in autonomous driving.<n>In autonomous driving, VQA plays a vital role in enabling the system to understand and reason about its surroundings.<n>We present a novel continual learning framework that combines Vision-Language Models with selective memory replay and knowledge distillation.
  arXiv  Detail & Related papers  (2025-02-02T16:27:44Z)
• VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision [20.43366384946928]
  Vision-language models (VLMs) as teachers to enhance training.<n>VLM-AD achieves significant improvements in planning accuracy and reduced collision rates on the nuScenes dataset.
  arXiv  Detail & Related papers  (2024-12-19T01:53:36Z)
• Vision Language Models are In-Context Value Learners [89.29486557646624]
  We present Generative Value Learning (GVL), a universal value function estimator that leverages the world knowledge embedded in vision-language models (VLMs) to predict task progress. Without any robot or task specific training, GVL can in-context zero-shot and few-shot predict effective values for more than 300 distinct real-world tasks.
  arXiv  Detail & Related papers  (2024-11-07T09:17:50Z)
• 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)
• Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models [79.28821338925947]
  Domain-Class Incremental Learning is a realistic but challenging continual learning scenario. To handle these diverse tasks, pre-trained Vision-Language Models (VLMs) are introduced for their strong generalizability. This incurs a new problem: the knowledge encoded in the pre-trained VLMs may be disturbed when adapting to new tasks, compromising their inherent zero-shot ability. Existing methods tackle it by tuning VLMs with knowledge distillation on extra datasets, which demands heavy overhead. We propose the Distribution-aware Interference-free Knowledge Integration (DIKI) framework, retaining pre-trained knowledge of
  arXiv  Detail & Related papers  (2024-07-07T12:19:37Z)
• Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models [77.2078051555533]
  We propose a novel and affordable solution for the effective VL adaption of large language models (LLMs) Instead of using large neural networks to connect the image encoder and LLM, MMA adopts lightweight modules, i.e., adapters. MMA is also equipped with a routing algorithm to help LLMs achieve an automatic shift between single- and multi-modal instructions.
  arXiv  Detail & Related papers  (2023-05-24T11:06:15Z)

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.