MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization

• URL: http://arxiv.org/abs/2511.19878v1
• Date: Tue, 25 Nov 2025 03:39:37 GMT
• Title: MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization
• Abstract summary: We present MAPS, the first robust fine-tuning framework for Vision-Language-Action (VLA) models.<n>Through systematic analysis, we uncover an empirical order in which proximity constraints should be relaxed to balance stability and flexibility.<n> MAPS linearly schedules this relaxation, enabling visual encoders to stay close to their pretrained priors while action-oriented language layers adapt more freely.
• Score: 30.871663465403625
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language-Action (VLA) models inherit strong priors from pretrained Vision-Language Models (VLMs), but naive fine-tuning often disrupts these representations and harms generalization. Existing fixes -- freezing modules or applying uniform regularization -- either overconstrain adaptation or ignore the differing roles of VLA components. We present MAPS (Module-Wise Proximity Scheduling), the first robust fine-tuning framework for VLAs. Through systematic analysis, we uncover an empirical order in which proximity constraints should be relaxed to balance stability and flexibility. MAPS linearly schedules this relaxation, enabling visual encoders to stay close to their pretrained priors while action-oriented language layers adapt more freely. MAPS introduces no additional parameters or data, and can be seamlessly integrated into existing VLAs. Across MiniVLA-VQ, MiniVLA-OFT, OpenVLA-OFT, and challenging benchmarks such as SimplerEnv, CALVIN, LIBERO, as well as real-world evaluations on the Franka Emika Panda platform, MAPS consistently boosts both in-distribution and out-of-distribution performance (up to +30%). Our findings highlight empirically guided proximity to pretrained VLMs as a simple yet powerful principle for preserving broad generalization in VLM-to-VLA transfer.

Related papers

• CLAP: Direct VLM-to-VLA Adaptation via Language-Action Grounding [16.03159066719039]
  CLAP (Causal Language-Action Prediction) prepends each numeric action sequence with a natural-language action description.<n>We will release CLAP at 0.8B, 2B, and 4B as an open-weight, multi-scale compact VLA family from a single VLM lineage.
  arXiv  Detail & Related papers  (2026-07-09T22:34:11Z)
• PrimitiveVLA: Learning Reusable Motion Primitives for Efficient and Generalizable Robotic Manipulation [50.8450025321217]
  Vision-Language-Action (VLA) models offer a promising paradigm for generalist robotic policies.<n>We argue that these bottlenecks stem from the prevailing Direct Instruction-to-Control Mapping.<n>We propose PrimitiveVLA, a framework that shifts this paradigm toward a Primitive-Centric Disassemble & Assemble paradigm.
  arXiv  Detail & Related papers  (2026-05-27T15:41:18Z)
• Rethinking VLM Representation for VLA Initialization [44.662878535366985]
  Vision-Language-Action (VLA) models widely adopt pretrained Vision-Language Models (VLMs) as policy backbones.<n>It remains unclear what kind of pretrained VLM representation is useful as a VLA initialization.
  arXiv  Detail & Related papers  (2026-05-25T12:51:35Z)
• QuoVLA: Quotient Space for Vision-Language-Action Models [51.02329790939691]
  Vision-Language-Action (VLA) models commonly adapt pretrained VLM latents to robot control by mapping visual observations and language instructions to continuous actions.<n>Our textitQuotient Theory for VLA shows that pretrained VLM latents are not action-insufficient but action-sufficient.<n>We propose QuoVLA, a quotient-space framework for VLA that compresses pretrained VLM latents into action-sufficient representations.
  arXiv  Detail & Related papers  (2026-05-24T06:28:53Z)
• $M^2$-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills [25.17452377052361]
  Current Vision-Language-Action (VLA) models predominantly rely on end-to-end fine-tuning.<n>We propose $M2$-VLA, which demonstrates that a generalized VLM is able to serve as a powerful backbone for robotic manipulation directly.<n>To overcome this, we introduce the Mixture of Layers (MoL) strategy that selectively extracts task-critical information from dense semantic features.
  arXiv  Detail & Related papers  (2026-04-27T08:44:12Z)
• DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA [72.9197085473598]
  DIAL is a framework bridging high-level decision making and low-level motor execution through a differentiable latent intent bottleneck.<n>A VLM-based System-2 performs latent world modeling by latent visual foresight within the VLM's native feature space.<n>A lightweight System-1 policy then decodes this predicted intent together with the current observation into precise robot actions.
  arXiv  Detail & Related papers  (2026-03-31T15:02:27Z)
• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination [55.982504915794514]
  We propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination.<n>SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines.
  arXiv  Detail & Related papers  (2026-02-25T06:58:06Z)
• Reshaping Action Error Distributions for Reliable Vision-Language-Action Models [69.38615670891038]
  In robotic manipulation, vision-language-action (VLA) models have emerged as a promising paradigm for learning generalizable and scalable robot policies.<n>We focus on continuous-action VLA models and move beyond conventional MSE-based regression by reshaping action error distributions during training.<n>We evaluate our approaches across standard, few-shot, and noisy settings on multiple representative VLA architectures.
  arXiv  Detail & Related papers  (2026-02-04T05:37:09Z)
• Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision [79.06371915084833]
  We introduce Youtu-VL, a framework leveraging the Vision-Language Unified Autoregressive Supervision (VLUAS) paradigm.<n>Youtu-VL applies unified autoregressive supervision to both visual details and linguistic content.<n>We extend this paradigm to encompass vision-centric tasks, enabling a standard VLM to perform vision-centric tasks without task-specific additions.
  arXiv  Detail & Related papers  (2026-01-27T17:01:16Z)
• 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)
• Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization [42.41263928527529]
  Vision-Language-Action (VLA) models can endow agents with transferable world knowledge and vision-language grounding.<n>Yet when these VLMs are adapted to the action modality, it remains unclear to what extent their original visual representations and knowledge are preserved.<n>We conduct a systematic study of representation retention during VLA fine-tuning, showing that naive action fine-tuning leads to degradation of visual representations.
  arXiv  Detail & Related papers  (2025-10-29T15:20:10Z)
• Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success [5.617637951327993]
  We introduce Vision-Language Decoupled Actor-Critic (VLDAC), a lightweight reinforcement learning algorithm.<n>VLDAC applies PPO updates to action while learning value only at the environment-step level.<n>Training a single VLM with VLDAC in one inexpensive simulator at a time produces policies that generalize widely.
  arXiv  Detail & Related papers  (2025-08-06T10:08:48Z)
• 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)
• EdgeVLA: Efficient Vision-Language-Action Models [0.4005096060512278]
  This paper introduces Edge VLA, a novel approach designed to significantly enhance the inference speed of Vision-Language-Action (VLA) models.<n>We achieve this through two key innovations: 1) Eliminating the autoregressive requirement for end-effector position prediction, leading to a 7x speedup in inference, and 2) Leveraging the efficiency of Small Language Models (SLMs)<n>Our early results demonstrate that EVLA achieves comparable training characteristics to OpenVLA while offering substantial gains in inference speed and memory efficiency.
  arXiv  Detail & Related papers  (2025-07-18T16:15:09Z)
• CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling [84.51372201195132]
  CronusVLA is a unified framework that extends single-frame VLA models to the multi-frame paradigm.<n>CronusVLA achieves leading performance and superior robustness, with a 70.9% success rate.<n>These results highlight the potential of efficient multi-frame adaptation in VLA models for more powerful and robust real-world deployment.
  arXiv  Detail & Related papers  (2025-06-24T17:30:27Z)
• CF-VLM:CounterFactual Vision-Language Fine-tuning [10.299136720220416]
  CounterFactual Vision-Language Fine-tuning (CF-VLM) is a novel framework that enhances causal reasoning capabilities of vision-language models.<n>CF-VLM introduces three complementary training objectives: maintaining foundational cross-modal alignment, reinforcing the uniqueness and stability of factual scene representations, and sharpening the model's sensitivity to minimal but critical causal edits.
  arXiv  Detail & Related papers  (2025-06-10T20:20:05Z)
• 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)
• Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training [48.455597568212944]
  We present Mono-InternVL, a novel monolithic MLLM that seamlessly integrates a set of visual experts via a multimodal mixture-of-experts structure.<n>In particular, EViP is designed as a progressive learning process for visual experts, which aims to fully exploit the visual knowledge from noisy data to high-quality data.
  arXiv  Detail & Related papers  (2024-10-10T17:59:22Z)
• SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs [31.88022265176855]
  Supervised Embedding Alignment (SEA) is a token-level supervision alignment method that enables more precise visual-text alignment during pretraining.<n>Our comprehensive analyses reveal critical insights into the adapter's role in multimodal integration, and extensive experiments demonstrate that SEA consistently improves performance across various model sizes.
  arXiv  Detail & Related papers  (2024-08-21T17:58:02Z)
• Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models [55.5610165938949]
  Fine-tuning vision-language models (VLMs) has gained increasing popularity due to its practical value. This paper explores the collaborative potential of leveraging much weaker VLMs to enhance the generalization of a robust single model. We introduce three customized ensemble strategies, each tailored to one specific scenario. The proposed ensemble strategies are evaluated on zero-shot, base-to-new, and cross-dataset generalization, achieving new state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-11-28T05:17:25Z)

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.