RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception

Joshua R. Waite, Md Zahid Hasan, Qisai Liu, Zhanhong Jiang, Chinmay Hegde, Soumik Sarkar

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Vision-language model (VLM) fine-tuning for application-specific visual grounding based on natural language instructions has become one of the most popular approaches for learning-enabled autonomous systems. However, such fine-tuning relies heavily on high-quality datasets to achieve successful performance in various downstream tasks. Additionally, VLMs often encounter limitations due to insufficient and imbalanced fine-tuning data. To address these issues, we propose a new generalizable framework to improve VLM fine-tuning by integrating it with a reinforcement learning (RL) agent. Our method utilizes the RL agent to manipulate objects within an indoor setting to create synthetic data for fine-tuning to address certain vulnerabilities of the VLM. Specifically, we use the performance of the VLM to provide feedback to the RL agent to generate informative data that efficiently fine-tune the VLM over the targeted task (e.g. spatial reasoning). The key contribution of this work is developing a framework where the RL agent serves as an informative data sampling tool and assists the VLM in order to enhance performance and address task-specific vulnerabilities. By targeting the data sampling process to address the weaknesses of the VLM, we can effectively train a more context-aware model. In addition, generating synthetic data allows us to have precise control over each scene and generate granular ground truth captions. Our results show that the proposed data generation approach improves the spatial reasoning performance of VLMs, which demonstrates the benefits of using RL-guided data generation in vision-language tasks.

    Original languageEnglish (US)
    Title of host publicationProceedings of the ACM/IEEE 16th International Conference on Cyber-Physical Systems, ICCPS 2025, held as part of the CPS-IoT Week 2025
    PublisherAssociation for Computing Machinery, Inc
    ISBN (Electronic)9798400714986
    DOIs
    StatePublished - May 7 2025
    Event16th Annual ACM/IEEE International Conference on Cyber-Physical Systems, ICCPS 2025, held as part of the CPS-IoT Week 2025 - Irvine, United States
    Duration: May 6 2025May 9 2025

    Publication series

    NameProceedings of the ACM/IEEE 16th International Conference on Cyber-Physical Systems, ICCPS 2025, held as part of the CPS-IoT Week 2025

    Conference

    Conference16th Annual ACM/IEEE International Conference on Cyber-Physical Systems, ICCPS 2025, held as part of the CPS-IoT Week 2025
    Country/TerritoryUnited States
    CityIrvine
    Period5/6/255/9/25

    Keywords

    • self-improving sampling
    • spatial reasoning
    • synthetic data generation
    • vision-language models

    ASJC Scopus subject areas

    • Computer Networks and Communications
    • Hardware and Architecture

    Fingerprint

    Dive into the research topics of 'RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception'. Together they form a unique fingerprint.

    Cite this