Incentivizing Multimodal Reasoning in Large Models for Direct Robot Manipulation

• URL: http://arxiv.org/abs/2505.12744v1
• Date: Mon, 19 May 2025 06:00:14 GMT
• Title: Incentivizing Multimodal Reasoning in Large Models for Direct Robot Manipulation
• Authors: Weiliang Tang, Dong Jing, Jia-Hui Pan, Zhiwu Lu, Yun-Hui Liu, Li Erran Li, Mingyu Ding, Chi-Wing Fu,
• Abstract summary: We show how to make Large Multimodal Models (LMMs) understand the spatial action space.<n>We also show how to fully exploit the reasoning capacity of LMMs in solving these tasks.<n>Our resulting reasoning model built upon a 7B backbone, named ReasonManip, demonstrates three notable advantages.
• Score: 89.5123417007126
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent Large Multimodal Models have demonstrated remarkable reasoning capabilities, especially in solving complex mathematical problems and realizing accurate spatial perception. Our key insight is that these emerging abilities can naturally extend to robotic manipulation by enabling LMMs to directly infer the next goal in language via reasoning, rather than relying on a separate action head. However, this paradigm meets two main challenges: i) How to make LMMs understand the spatial action space, and ii) How to fully exploit the reasoning capacity of LMMs in solving these tasks. To tackle the former challenge, we propose a novel task formulation, which inputs the current states of object parts and the gripper, and reformulates rotation by a new axis representation instead of traditional Euler angles. This representation is more compatible with spatial reasoning and easier to interpret within a unified language space. For the latter challenge, we design a pipeline to utilize cutting-edge LMMs to generate a small but high-quality reasoning dataset of multi-round dialogues that successfully solve manipulation tasks for supervised fine-tuning. Then, we perform reinforcement learning by trial-and-error interactions in simulation to further enhance the model's reasoning abilities for robotic manipulation. Our resulting reasoning model built upon a 7B backbone, named ReasonManip, demonstrates three notable advantages driven by its system-2 level reasoning capabilities: i) exceptional generalizability to out-of-distribution environments, objects, and tasks; ii) inherent sim-to-real transfer ability enabled by the unified language representation shared across domains; iii) transparent interpretability connecting high-level reasoning and low-level control. Extensive experiments demonstrate the effectiveness of the proposed paradigm and its potential to advance LMM-driven robotic manipulation.

Related papers

• RemoteReasoner: Towards Unifying Geospatial Reasoning Workflow [19.502882116487005]
  Remote sensing imagery presents vast, inherently unstructured spatial data.<n>We propose RemoteReasoner, a flexible and robust workflow for remote sensing reasoning tasks.<n>Preliminary experiments demonstrated that RemoteReasoner achieves remarkable performance across multi-granularity reasoning tasks.
  arXiv  Detail & Related papers  (2025-07-25T13:58:11Z)
• Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing [62.447497430479174]
  Drawing to reason in space is a novel paradigm that enables LVLMs to reason through elementary drawing operations in the visual space.<n>Our model, named VILASR, consistently outperforms existing methods across diverse spatial reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-06-11T17:41:50Z)
• Reinforcing Multimodal Understanding and Generation with Dual Self-rewards [56.08202047680044]
  Large language models (LLMs) unify cross-model understanding and generation into a single framework.<n>Current solutions require external supervision (e.g., human feedback or reward models) and only address unidirectional tasks.<n>We introduce a self-supervised dual reward mechanism to reinforce the understanding and generation capabilities of LMMs.
  arXiv  Detail & Related papers  (2025-06-09T17:38:45Z)
• Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models [45.15161506154318]
  Infi-MMR is a framework to systematically unlock the reasoning potential of Multimodal Small Language Models.<n>The first phase, Foundational Reasoning Activation, leverages high-quality textual reasoning datasets to activate and strengthen the model's logical reasoning capabilities.<n>The second phase, Cross-Modal Reasoning Adaptation, utilizes caption-augmented multimodal data to facilitate the progressive transfer of reasoning skills to multimodal contexts.<n>The third phase, Multimodal Reasoning Enhancement, employs curated, caption-free multimodal data to mitigate linguistic biases and promote robust cross-modal reasoning.
  arXiv  Detail & Related papers  (2025-05-29T04:51:56Z)
• Modular Machine Learning: An Indispensable Path towards New-Generation Large Language Models [45.05285463251872]
  We introduce a novel learning paradigm -- Modular Machine Learning (MML) -- as an essential approach toward new-generation large language models (LLMs)<n>MML decomposes the complex structure of LLMs into three interdependent components: modular representation, modular model, and modular reasoning.<n>We present a feasible implementation of MML-based LLMs via leveraging advanced techniques such as disentangled representation learning, neural architecture search and neuro-symbolic learning.
  arXiv  Detail & Related papers  (2025-04-28T17:42:02Z)
• A Call for New Recipes to Enhance Spatial Reasoning in MLLMs [85.67171333213301]
  Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in general vision-language tasks.<n>Recent studies have exposed critical limitations in their spatial reasoning capabilities.<n>This deficiency in spatial reasoning significantly constrains MLLMs' ability to interact effectively with the physical world.
  arXiv  Detail & Related papers  (2025-04-21T11:48:39Z)
• Large Multi-modal Models Can Interpret Features in Large Multi-modal Models [45.509307983813336]
  We first apply a Sparse Autoencoder to disentangle the representations into human understandable features. We then present an automatic interpretation framework to interpreted the open-semantic features learned in SAE by the LMMs themselves.
  arXiv  Detail & Related papers  (2024-11-22T14:41:36Z)
• Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models [64.1799100754406]
  Large Language Models (LLMs) demonstrate enhanced capabilities and reliability by reasoning more.<n>Despite various efforts to improve LLM reasoning, high-quality long-chain reasoning data and optimized training pipelines still remain inadequately explored in vision-language tasks.<n>We present Insight-V, an early effort to 1) scalably produce long and robust reasoning data for complex multi-modal tasks, and 2) an effective training pipeline to enhance the reasoning capabilities of MLLMs.
  arXiv  Detail & Related papers  (2024-11-21T18:59:55Z)
• Cantor: Inspiring Multimodal Chain-of-Thought of MLLM [83.6663322930814]
  We argue that converging visual context acquisition and logical reasoning is pivotal for tackling visual reasoning tasks. We propose an innovative multimodal CoT framework, termed Cantor, characterized by a perception-decision architecture. Our experiments demonstrate the efficacy of the proposed framework, showing significant improvements in multimodal CoT performance.
  arXiv  Detail & Related papers  (2024-04-24T17:59:48Z)
• Conditional Neural Expert Processes for Learning Movement Primitives from Demonstration [1.9336815376402723]
  Conditional Neural Expert Processes (CNEP) learns to assign demonstrations from different modes to distinct expert networks. CNEP does not require supervision on which mode the trajectories belong to. Our system is capable of on-the-fly adaptation to environmental changes via an online conditioning mechanism.
  arXiv  Detail & Related papers  (2024-02-13T12:52:02Z)
• Large Multi-Modal Models (LMMs) as Universal Foundation Models for AI-Native Wireless Systems [57.41621687431203]
  Large language models (LLMs) and foundation models have been recently touted as a game-changer for 6G systems. This paper presents a comprehensive vision on how to design universal foundation models tailored towards the deployment of artificial intelligence (AI)-native networks.
  arXiv  Detail & Related papers  (2024-01-30T00:21:41Z)
• ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation [22.071450379253235]
  We introduce an innovative approach for robot manipulation that leverages the robust reasoning capabilities of Multimodal Large Language Models (MLLMs) By fine-tuning the injected adapters, we preserve the inherent common sense and reasoning ability of the MLLMs while equipping them with the ability for manipulation. Experiments in simulator and real-world show the promising performance of ManipLLM.
  arXiv  Detail & Related papers  (2023-12-24T06:38:11Z)

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.