MARVL: Multi-Stage Guidance for Robotic Manipulation via Vision-Language Models

• URL: http://arxiv.org/abs/2602.15872v1
• Date: Wed, 28 Jan 2026 11:25:13 GMT
• Title: MARVL: Multi-Stage Guidance for Robotic Manipulation via Vision-Language Models
• Abstract summary: We propose MARVL-Multi-stAge guidance for Robotic manipulation via Vision-Language models.<n> MARVL fine-tunes a VLM for spatial and semantic consistency and decomposes tasks into multi-stage subtasks with task direction projection for trajectory sensitivity.<n> Empirically, MARVL significantly outperforms existing VLM-reward methods on the Meta-World benchmark, demonstrating superior sample efficiency and robustness on sparse-reward manipulation tasks.
• Score: 42.20216799801145
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Designing dense reward functions is pivotal for efficient robotic Reinforcement Learning (RL). However, most dense rewards rely on manual engineering, which fundamentally limits the scalability and automation of reinforcement learning. While Vision-Language Models (VLMs) offer a promising path to reward design, naive VLM rewards often misalign with task progress, struggle with spatial grounding, and show limited understanding of task semantics. To address these issues, we propose MARVL-Multi-stAge guidance for Robotic manipulation via Vision-Language models. MARVL fine-tunes a VLM for spatial and semantic consistency and decomposes tasks into multi-stage subtasks with task direction projection for trajectory sensitivity. Empirically, MARVL significantly outperforms existing VLM-reward methods on the Meta-World benchmark, demonstrating superior sample efficiency and robustness on sparse-reward manipulation tasks.

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)
• ProgVLA: Progress-Aware Robot Manipulation Skill Learning [13.001629637153583]
  We present ProgVLA, a compact vision-language-action (VLA) model for reliable robot manipulation under tight compute and memory budgets.<n>A multi-modal encoder with a two-stage Perceiver resampling scheme compresses variable-length visual, language, and proprioceptive streams into a fixed set of control-ready context tokens.<n>An auxiliary set of progress heads is trained with offline reinforcement learning objectives to jointly learn critics over normalized remaining-horizon targets.
  arXiv  Detail & Related papers  (2026-05-27T09:44:46Z)
• $M^2$-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)
• AnoleVLA: Lightweight Vision-Language-Action Model with Deep State Space Models for Mobile Manipulation [2.2357163812666716]
  Vision-Language-Action models (VLAs) have demonstrated strong performance for this task.<n>But their deployment in resource-constrained environments remains challenging because of the computational cost of standard transformer backbones.<n>We propose AnoleVLA, a lightweight VLA that uses a deep state space model to process multimodal sequences efficiently.
  arXiv  Detail & Related papers  (2026-03-16T09:57:45Z)
• VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimization [87.26383908243878]
  We show that vision encoders within Multimodal Large Language Models exhibit deficiencies in their dense feature representations.<n>We propose VersaViT, a well-rounded vision transformer that instantiates a novel multi-task framework for collaborative post-training.
  arXiv  Detail & Related papers  (2026-02-10T16:08:19Z)
• dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought [66.78110237549087]
  Vision-Language-Action (VLA) models are emerging as a next-generation paradigm for robotics.<n>We introduce dVLA, a diffusion-based VLA that unifies visual perception, language reasoning, and robotic control in a single system.
  arXiv  Detail & Related papers  (2025-09-30T02:36:11Z)
• ROSA: Harnessing Robot States for Vision-Language and Action Alignment [24.426285156386715]
  Vision-Language Models (VLMs) have made significant advance in end-to-end robotic control.<n>We propose a novel training paradigm, ROSA, which leverages robot state estimation to improve alignment between vision-language and action spaces.
  arXiv  Detail & Related papers  (2025-06-16T16:34:20Z)
• Hierarchical Language Models for Semantic Navigation and Manipulation in an Aerial-Ground Robotic System [8.88014241557266]
  Heterogeneous multirobot systems show great potential in complex tasks requiring coordinated hybrid cooperation.<n>Existing methods that rely on static or task-specific models often lack generalizability across diverse tasks and dynamic environments.<n>We propose a hierarchical multimodal framework that integrates a prompted large language model (LLM) with a fine-tuned vision-language model (VLM)
  arXiv  Detail & Related papers  (2025-06-05T13:27:41Z)
• MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation [24.200547898713126]
  Multimodal Large Language Models (MLLMs) excel in understanding complex language and visual data.<n>Their real-world deployment is hindered by substantial computational and storage demands.<n>We propose a Mixture-of-Layers Vision-Language-Action model (MoLe) architecture for dynamic LLM layer activation.
  arXiv  Detail & Related papers  (2025-03-26T10:05:38Z)
• ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model [21.844214660424175]
  ChatVLA is a novel framework featuring Phased Alignment Training, which incrementally integrates multimodal data after initial control mastery, and a Mixture-of-Experts architecture to minimize task interference.<n>ChatVLA demonstrates competitive performance on visual question-answering datasets and significantly surpasses state-of-the-art vision-language-action (VLA) methods on multimodal understanding benchmarks.<n>Our findings highlight the potential of our unified framework for achieving both robust multimodal understanding and effective robot control.
  arXiv  Detail & Related papers  (2025-02-20T10:16:18Z)
• 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)
• Affordance-Guided Reinforcement Learning via Visual Prompting [51.361977466993345]
  Keypoint-based Affordance Guidance for Improvements (KAGI) is a method leveraging rewards shaped by vision-language models (VLMs) for autonomous RL.<n>On diverse real-world manipulation tasks specified by natural language descriptions, KAGI improves the sample efficiency of autonomous RL and enables successful task completion in 30K online fine-tuning steps.
  arXiv  Detail & Related papers  (2024-07-14T21:41:29Z)
• TaskBench: Benchmarking Large Language Models for Task Automation [82.2932794189585]
  We introduce TaskBench, a framework to evaluate the capability of large language models (LLMs) in task automation. Specifically, task decomposition, tool selection, and parameter prediction are assessed. Our approach combines automated construction with rigorous human verification, ensuring high consistency with human evaluation.
  arXiv  Detail & Related papers  (2023-11-30T18:02:44Z)

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.