Papers › RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models

RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models

16 Oct 2023arXiv:2310.10221archive 2025-07-28

Zijun Long, George Killick, Richard McCreadie, Gerardo Aragon Camarasa

Robotic vision applications often necessitate a wide range of visual perception tasks, such as object detection, segmentation, and identification. While there have been substantial advances in these individual tasks, integrating specialized models into a unified vision pipeline presents significant engineering challenges and costs. Recently, Multimodal Large Language Models (MLLMs) have emerged as novel backbones for various downstream tasks. We argue that leveraging the pre-training capabilities of MLLMs enables the creation of a simplified framework, thus mitigating the need for task-specific encoders. Specifically, the large-scale pretrained knowledge in MLLMs allows for easier fine-tuning to downstream robotic vision tasks and yields superior performance. We introduce the RoboLLM framework, equipped with a BEiT-3 backbone, to address all visual perception tasks in the ARMBench challenge-a large-scale robotic manipulation dataset about real-world warehouse scenarios. RoboLLM not only outperforms existing baselines but also substantially reduces the engineering burden associated with model selection and tuning. The source code is publicly available at https://github.com/longkukuhi/armbench.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

longkukuhi/armbench officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Instance SegmentationModel SelectionObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation ARMBench RoboLLM (VIT-B) AP50 82.0 #4 of 7 Archive leaderboard report
Instance Segmentation ARMBench RoboLLM (VIT-B) AP75 74 #4 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections