EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training

• URL: http://arxiv.org/abs/2604.20012v1
• Date: Tue, 21 Apr 2026 21:40:58 GMT
• Title: EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training
• Abstract summary: Vision-Language-Action Models (VLAs) inherit their visual and linguistic capabilities from Vision-Language Models (VLMs)<n>Most VLAs are built from off-the-shelf VLMs that are not adapted to the embodied domain, limiting their downstream performance.<n>We propose EmbodiedMidtrain to bridge the gap between VLMs and VLAs.
• Score: 36.75413663296722
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language-Action Models (VLAs) inherit their visual and linguistic capabilities from Vision-Language Models (VLMs), yet most VLAs are built from off-the-shelf VLMs that are not adapted to the embodied domain, limiting their downstream performance. In this work, we propose EmbodiedMidtrain to bridge the gap between VLMs and VLAs. We first characterize the data distribution gap between them, showing that VLA data occupy compact regions that are largely separated from the broader VLM distribution, while the degree of alignment varies substantially both across and within VLM data sources. Then, we build a mid-training data engine that leverages a lightweight learnable proximity estimator to select the most VLA-aligned candidates from a large VLM pool, and mid-trains the VLM on this curated mixture before downstream VLA fine-tuning. Experiments on three robot manipulation benchmarks show that mid-training consistently improves performance across different VLM backbones, achieving results competitive with expert VLAs and off-the-shelf VLMs trained with larger model scale and training budgets. Further analysis reveals that mid-training provides a stronger initialization for VLA fine-tuning, with gains emerging from the earliest steps and widening throughout training. Moreover, the data engine captures both dataset-level and sample-level alignment signals, favoring spatial reasoning over text-centric tasks while preserving the diversity of the VLM data. We will release all code, data and models for future research.

Related papers

• Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data [93.7685703383343]
  Vision-language models (VLMs) are powerful general-purpose reasoners, yet converting them into robot control policies is surprisingly difficult.<n>We argue that this gap can be bridged gradually with the right intermediate data.<n>We show that mixing task-relevant out-of-distribution ETC data with a small amount of action data enables the model to generalize to novel visual-language conditions.
  arXiv  Detail & Related papers  (2026-06-07T08:57:51Z)
• VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models [43.09726338623949]
  Vision-Language-Action (VLA) models integrate pretrained large Vision-Language Models (VLM) into their policy backbone.<n>This paper revisits a fundamental yet seldom systematically studied question: how VLM choice and competence translate to downstream VLA policies performance.<n>We introduce VLM4VLA, a minimal adaptation pipeline that converts general-purpose VLMs into VLA policies using only a small set of new learnable parameters.
  arXiv  Detail & Related papers  (2026-01-06T09:58:24Z)
• Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone [93.0075191741086]
  We investigate the potential of constructing Vision-Language Models upon diffusion-based large language models.<n>We introduce Dream-VL, an open diffusion-based VLM that achieves state-of-the-art performance.<n>We build upon Dream-VLA, a dLLM-based Vision-Language-Action model (dVLA) developed through continuous pre-training on open robotic datasets.
  arXiv  Detail & Related papers  (2025-12-27T14:46:24Z)
• Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation [109.5893580175657]
  In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision.<n>This approach often causes models to lean towards language comprehension and undermine the rich visual perception signals present in the data.<n>We propose VisPer-LM, the first approach that infuses visual perception knowledge from expert vision encoders into the LLM's hidden representations.
  arXiv  Detail & Related papers  (2024-12-12T18:55:18Z)
• VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models [84.84277196012907]
  We propose VLsI: Verbalized Layers-to-Interactions, a new VLM family in 2B and 7B model sizes.<n>We validate VLsI across ten challenging vision-language benchmarks, achieving notable performance gains (11.0% for 2B and 17.4% for 7B) over GPT-4V.
  arXiv  Detail & Related papers  (2024-12-02T18:58:25Z)
• NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
  We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks. We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
  arXiv  Detail & Related papers  (2024-09-17T17:59:06Z)
• MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning [25.45278447786954]
  We introduce a novel federated learning framework, named Multimodal Large Language Model Assisted Federated Learning (MLLM-LLaVA-FL)<n>Our framework is adept at harnessing the extensive, yet previously underexploited, open-source data accessible from websites and powerful server-side computational resources.
  arXiv  Detail & Related papers  (2024-09-09T21:04:16Z)
• Bridge the Modality and Capability Gaps in Vision-Language Model Selection [62.26769826687365]
  Vision Language Models (VLMs) excel in zero-shot image classification by pairing images with textual category names.<n>To better reuse the VLM resource, a promising strategy is selecting appropriate Pre-Trained VLMs from the VLM Zoo.<n>We analyze two inherent challenges in assessing the ability of a VLM in this Language-Only VLM selection.<n>We propose VLM Selection With gAp Bridging to mitigate the negative impact of two gaps.
  arXiv  Detail & Related papers  (2024-03-20T17:54:58Z)
• VILA: On Pre-training for Visual Language Models [74.08039416548209]
  We study the design options for VLM pre-training through step-by-step controllable comparisons. We build VILA, a Visual Language model family that consistently outperforms the state-of-the-art models.
  arXiv  Detail & Related papers  (2023-12-12T18:58:18Z)

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.